Дисертації з теми "Transformers network"
Щоб переглянути інші типи публікацій з цієї теми, перейдіть за посиланням: Transformers network.
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-50 дисертацій для дослідження на тему "Transformers network".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте дисертації для різних дисциплін та оформлюйте правильно вашу бібліографію.
1
Hughes, Timothy Howard. "On the synthesis of passive networks without transformers." Thesis, University of Cambridge, 2014. https://www.repository.cam.ac.uk/handle/1810/265924.
Анотація:
This thesis is concerned with the synthesis of passive networks, motivated by the recent invention of a new mechanical component, the inerter, which establishes a direct analogy between mechanical and electrical networks. We investigate the minimum numbers of inductors, capacitors and resistors required to synthesise a given impedance, with a particular focus on transformerless network synthesis. The conclusions of this thesis are relevant to the design of compact and cost-effective mechanical and electrical networks for a broad range of applications. In Part 1, we unify the Laplace-domain and phasor approach to the analysis of transformerless networks, using the framework of the behavioural approach. We show that the autonomous part of any driving-point trajectory of a transformerless network decays to zero as time passes. We then consider the trajectories of a transformerless network, which describe the permissible currents and voltages in the elements and at the driving-point terminals. We show that the autonomous part of any trajectory of a transformerless network is bounded into the future, but need not decay to zero. We then show that the value of the network's impedance at a particular point in the closed right half plane can be determined by finding a special type of network trajectory. In Part 2, we establish lower bounds on the numbers of inductors and capacitors required to realise a given impedance. These lower bounds are expressed in terms of the extended Cauchy index for the impedance, a property defined in that part. Explicit algebraic conditions are also stated in terms of a Sylvester and a Bezoutian matrix. The lower bounds are generalised to multi-port networks. Also, a connection is established with continued fraction expansions, with implications for network synthesis. In Part 3, we first present four procedures for the realisation of a general impedance with a transformerless network. These include two known procedures, the Bott-Duffin procedure and the Reza-Pantell-Fialkow-Gerst simplification, and two new procedures. We then show that the networks produced by the Bott-Duffin procedure, and one of our new alternatives, contain the least possible number of reactive elements (inductors and capacitors) and resistors, for the realisation of a certain type of impedance (called a biquadratic minimum function), among all series-parallel networks. Moreover, we show that these procedures produce the only series-parallel networks which contain exactly six reactive elements and two resistors and realise a biquadratic minimum function. We further show that the networks produced by the Reza-Pantell-Fialkow-Gerst simplification, and the second of our new alternatives, contain the least possible number of reactive elements and resistors for the realisation of almost all biquadratic minimum functions among the class of transformerless networks. We group the networks obtained by these two procedures into two quartets, and we show that these are the only quartets of transformerless networks which contain exactly five reactive elements and two resistors and realise all of the biquadratic minimum functions. Finally, we investigate the minimum number of reactive elements required to realise certain impedances, of greater complexity than the biquadratic minimum function, with series-parallel networks.
2
Das, Debrup. "Dynamic control of grid power flow using controllable network transformers." Diss., Georgia Institute of Technology, 2011. http://hdl.handle.net/1853/43739.
Анотація:
The objective of the research is to develop a cost-effective, dynamic grid controller called the controllable network transformer (CNT) that can be implemented by augmenting existing load tap changing (LTC) transformers with an AC-AC converter. The concept is based on using a fractionally rated direct AC-AC converter to control the power through an existing passive LTC. By using a modulation strategy based on virtual quadrature sources (VQS), it is possible to control both the magnitude and the phase angle of the output voltage of the CNT without having any inter-phase connections. The CNT architecture has many advantages over existing power flow controllers, like absence of low frequency storage, fractional converter rating, retro-fitting existing assets and independent per-phase operation making it potentially attractive for utility applications.
The independent control of the magnitude and the phase angle of the output voltage allow independent real and reactive power flow control through the CNT-controlled line. In a meshed network with asymmetric network stresses this functionality can be used to redirect power from critically loaded assets to other relatively under-utilized parallel paths. The power flow controllability of CNT can thus be used to lower the overall cost of generation of power. The solid state switches in the CNT with fast response capability enable incorporation of various additional critical functionalities like grid fault ride through, bypassing internal faults and dynamic damping. This bouquet of features makes the CNT useful under both steady state and transient conditions without compromising the grid reliability.
3
Wu, Wei. "CFD calibrated thermal network modelling for oil-cooled power transformers." Thesis, University of Manchester, 2011. https://www.research.manchester.ac.uk/portal/en/theses/cfd-calibrated-thermal-network-modelling-for-oilcooled-power-transformers(9199cbcc-c6df-4f26-aa9b-dde055ef44ea).html.
Анотація:
Power transformers are key components of electric system networks; their performance inevitably influences the reliability of electricity transmission and distribution systems. To comprehend the thermal ageing of transformers, hot-spot prediction becomes of significance. As the current method to estimate the hot-spot temperature is based on empirical hot-spot factor and is over-simplified, thermal network modelling has been developed due to its well balance between computation speed and approximation details. The application of Computational Fluid Dynamics (CFD) on transformer thermal analysis could investigate detailed and fundamental phenomena of cooling oil flow, and the principle of this PhD thesis is then to develop more accurate and reliable network modelling tools by utilising CFD.In this PhD thesis the empirical equations employed in network model for Nusselt number (Nu), friction coefficient and junction pressure losses (JPL) are calibrated for a wide range of winding dimensions used by power transformer designs from 22 kV to 500 kV, 20 MVA to 500 MVA, by conducting large sets of CFD simulations. The newly calibrated Nu equation predicts a winding temperature increase as the consequence of on average 15% lower Nu values along horizontal oil ducts. The new friction coefficient equation predicts a slightly more uniform oil flow rate distribution across the ducts, and also calculates a higher pressure drop over the entire winding. The new constant values for the JPL equations shows much better match to experimental results than the currently used 'off-the-shelf' constants and also reveals that more oil will tend to flow through the upper half of a pass if at a high inlet oil flow rate. Based on a test winding model in the laboratory, the CFD calibrated network model's calculation results are compared to both CFD and experimental results. It is concluded that the deviation between the oil pressure drop over the pass calculated by the network model and the CFD and the measured values is acceptably low. It proves that network modelling could deliver quick and reliable calculation results of the oil pressure drop over windings and thereby assist to choose capable oil pumps at the thermal design stage. However the flow distribution predicted by network model deviates from the one by CFD; this is particularly obvious for the cases with high flow rates probably due to the entry eddy circulation phenomena observed in CFD. As no experiment validation has been conducted, further investigation is necessary. The CFD calibrated network model is also applied to conduct a set of sensitivity studies on various thermal design parameters as well as loads. Because the studies are on a directed oil cooling winding case, an oil pump model is incorporated. From the studies recommendations are given for optimising thermal design, e.g. narrowed horizontal ducts will reduce average winding and hot-spot temperatures, and narrowed vertical ducts will however increase the temperatures. Doubled oil block washers are found to be able to significantly reduce the disc temperatures, although there is a slight reduction of the total oil flow rate, due to the increase of winding hydraulic impedance. The impact of different loadings, 50%~150% of rated load, upon the forced oil flow rate is limited, relative change below 5%. The correlations between the average winding and hot-spot temperatures versus the load factors follow parabolic trends.
4
Mousavi, Seyed Ali. "Electromagnetic Modelling of Power Transformers with DC Magnetization." Licentiate thesis, KTH, Elektroteknisk teori och konstruktion, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-105395.
Анотація:
DC currents that flow through the ground can be injected to the star windings of power transformers from their grounded neutral points and close their path with transmission lines. The geomagnetically induced currents (GICs) and AC/DC convertors of high voltage direct current (HVDC) systems are the sources of such DC currents. These currents may cause saturation of the core in power transformers that leads to destruction in the transformer performance. This phenomenon results in unwanted influences on power transformers and the power system. Very asymmetric magnetization current, increasing losses and creation of hot spots in the core, in the windings, and the metallic structural parts are adverse effects that occur in transformers. Also, increasing demand of reactive power and misoperation of protective relays menaces the power network. Damages in large power transformers and blackouts in networks have occurred due to this phenomenon Hence, studies regarding this subject have taken the attention of researchers during the last decades. However, a gap of a comprehensive analysis still remains. Thus, the main aim of this project is to reach to a deep understanding of the phenomena and to come up with a solution for a decrease of the undesired effects of GIC. Achieving this goal requires an improvement of the electromagnetic models of transformers which include a hysteresis model, numerical techniques, and transient analysis. In this project until now, a new algorithm for digital measurement of the core materials is developed and implemented. It enhances the abilities of accurate measurements and an improved hysteresis model has been worked out. Also, a novel differential scalar hysteresis model is suggested that easily can be implemented in numerical methods. Three dimensional finite element models of various core types of power transformers are created to study the effect on them due to DC magnetization. In order to enhance the numerical tools for analysis of low frequency transients related to power transformers and the network, a distributed reluctance network method has been outlined. In this thesis a method for solving such a network problem with coupling to an electrical circuit and taking hysteresis into account is suggested.QC 20121121
5
Cozzi, Riccardo. "Using semantic entities to improve the distillation of transformers." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2022.
Анотація:
In the last decade, the size of deep neural architectures implied in Natural Language Processing (NLP) has increased exponentially, reaching in some cases with hundreds of billions of parameters. Although, training and deploying these huge architectures is an extremely resource-demanding process and the costs are often not affordable in real-world applications. For these reasons, lots of research and industrial efforts are investigating solutions to reduce the size of these models but at the same time maintain high performance.
This work was about studying and experimenting Knowledge Distillation techniques with the goal of training smaller and cheaper models while attempting to produce a good approximation of large pre-trained ones. The conducted experiments consist of a first reproduction of a recent promising work of DistilBERT while trying to further reduce the resources implied in the process. In fact, we discovered it is possible to achieve approximately the same score of the state-of-the-art but involving only a small fraction of data and training resources.
The second proposed experiment consists of an attempt of performing the same distillation task with an architecture based on LUKE, a powerful entity-aware transformer that has recently shown how injecting semantic entities can positively influence the training of these models. Unfortunately, this second experiment, as we will see, did not give us the result we hoped, meaning that the task needs additional research effort.
6
Moses, Paul S. "Operation and performance of three-phase asymmetric multi-leg power transformers subjected to nonlinear and dynamic electromagnetic disturbances." Thesis, Curtin University, 2012. http://hdl.handle.net/20.500.11937/1529.
Анотація:
Three-phase power transformers continue to be an important fixture in modern power systems since their initial development in the 1880s. While transformer design has fundamentally remained the same, the operating environment has significantly changed. This is apparent through new flexible network operations (e.g., integration of renewable energy sources), growing network complexities (e.g., deployment of micro-grids, smart grids, etc.) and increasing use of nonlinear power electronic equipment (e.g., power converters and motor drives). Thus the issue of power quality in power systems has become an important consideration to utilities and industries as the performance of electrical machines and devices could be adversely affected. This doctoral thesis focuses on the performance of three-phase power transformers under various nonlinear and dynamic electromagnetic disturbances in distorted power networks.The first part of this work is devoted to the development and improvement of nonlinear electromagnetic models of three-phase multi-leg transformer cores for the study of steady-state and transient electromagnetic disturbances. This is mainly achieved by developing new detailed magnetic models for ferromagnetic nonlinearities (e.g., hysteresis) as well as considering core asymmetry and magnetic couplings of core-leg fluxes in three-phase multi-leg iron-core structures. These combined effects have not been considered in conventional electromagnetic transient studies of transformers and are shown in this work for the first time to have a significant impact on predicted steady-state and transient electromagnetic behaviour.In subsequent parts of this thesis, the developed models are applied to the examination of selected nonlinear electromagnetic phenomena such as transformer operation in harmonically distorted power systems (e.g., terminal voltage distortions and nonlinear loads), dc bias caused by geomagnetically induced currents, ferroresonance, and no-load magnetisation and inrush current effects. Furthermore, based on the new modelling approaches, improved methods are presented for estimating transformer aging with wider applicability to three-phase transformers considering load and source imbalances with harmonic distortions.With the advent of newly emerging smart grids, the last part of this thesis is devoted to exploring future transformer operation in new smart grid operating conditions such as plug-in electric vehicle charging. Transformer loading patterns with random uncoordinated PEV charging compared to coordinated charging activity in smart grids is investigated. The investigation highlights the notion of harnessing future smart grid technologies to better manage transformer health and performance.
7
Mousavi, Seyedali. "Electromagnetic Modelling of Power Transformers for Study and Mitigation of Effects of GICs." Doctoral thesis, KTH, Elektroteknisk teori och konstruktion, 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-159747.
Анотація:
Geomagnetic disturbances that result from solar activities can affect technological systems such as power networks. They may cause DC currents in power networks and saturation of the core in power transformers that leads to destruction in the transformer performance. This phenomena result in unwanted influences on power transformers and the power system. Very asymmetric magnetization current, increasing losses and creation of hot spots in the core, in the windings, and the metallic structural parts are adverse effects that occur in transformers. Also, increasing demand of reactive power and malfunction of protective relays menaces the power network stability. Damages in large power transformers and blackouts in networks have occurred due to this phenomenon. Hence, studies regarding this subject have taken the attention of researchers during the last decades. However, a gap of a comprehensive analysis still remains. Thus, the main aim of this project is to reach to a deep understanding of the phenomena and to come up with a solution for a decrease of the undesired effects of GIC. Achieving this goal requires an improvement of the electromagnetic models of transformers which include a hysteresis model, numerical techniques, and transient analysis. In this project, a new algorithm for digital measurement of the magnetic materials is developed and implemented. It enhances the abilities of accurate measurements and an improved hysteresis model has been worked out. Also, a novel differential scalar hysteresis model is suggested that easily can be implemented in numerical methods. Two and three dimensional finite element models of various core types of power transformers are created to study the effect of DC magnetization on transformers. In order to enhance the numerical tools for analysis of low frequency transients related to power transformers and the network, a novel topological based time step transformer model has been outlined. The model can employ a detailed magnetic circuit and consider nonlinearity, hysteresis and eddy current effects of power transformers. Furthermore, the proposed model can be used in the design process of transformers and even extend other application such as analysis of electrical machines. The numerical and experimental studies in this project lead to understanding the mechanism that a geomantic disturbance affects power transformers and networks. The revealed results conclude with proposals for mitigation strategies against these phenomena.QC 20150210
8
Kaminskas, Almundas. "Elektros tinklų rekonstrukcija Skomantų kaime." Bachelor's thesis, Lithuanian Academic Libraries Network (LABT), 2013. http://vddb.laba.lt/obj/LT-eLABa-0001:E.02~2013~D_20130823_095922-30435.
Анотація:
Elektros inžinerijos bakalauro baigiamojo darbo tema yra aktuali, nes elektros tinklai sumontuoti prieš 30–40 metų jau yra pasenę ir nebeatitinka šiuolaikinių poreikių. Vis daugiau elektros vartotojų keičia dujines virykles į elektrines, įsigija naujų elektros prietaisų, elektros suvartojimas auga, todėl būtina atnaujinti elektros tinklus, siekiant užtikrinti patikimą kokybiškos elektros energijos tiekimą. Šiuo projektu Skomantų kaime numatoma esamos oro linijos L-300 iš transformatorinės KT-V-305 rekonstravimas, ją pakeičiant apskaičiuoto skerspjūvio 0,4 kV elektros kabelių linijomis su reikiamu skaičiumi 0,4 kV skirstomųjų spintų (SS), įvadinių apskaitų skirstomųjų spintų (ĮASS) ir įvadinių apskaitų spintų (ĮAS). Numatoma trumpinti esamą oro liniją L-100 iš transformatorinės KT-V-305, pastatant dvi stulpines transformatorines su 25 kVA ir 40 kVA galios transformatoriais. Planuojamas oro linijos L-100 iš transformatorinės KT-V-305 ruožų nuo atramos Nr. 100/9 iki atramos Nr. 100/25 ir nuo atramos Nr. 101/18 iki atramos Nr. 101/25 demontavimas.His Bachelors’ degree electrical engineering thesis is relevant, because the electricity network built 30-40 years ago in Skomantai village is already old and no longer meets todays’ needs. More and more electricity consumers change gas stoves into electrical stoves, purchase new electrical devices. The usage of electricity is increasing. That’s why the renewal of electrical network is needed in order to maintain reliable supply of high quality electric power. The plan of this project in Skomantai village is the reconstruction of existing transmission line L-300 from the transformer KT-V-305 reconstructing it by changing with calculated cross-section 0,4 kV electricity cables’ lines with needed number 0,4 kV 0,4kV distribution boards (SS), electrical distribution and metering equipment boards (ĮASS) and lead-in metering boards (ĮAS). Shortening of the existing transmission lines L-100 from transformer KT-V-305 and building two pole transformers with 25 kVA and 40 kVA power transformers. Dismantling of transmission line L-100 from transformer KT-V-305 parts from pole No. 100/9 up to pole No. 100/25, and from pole No. 101/18 up to No. 101/25.
9
Lecesne, Erwan. "Planification et assistance par fusion d'images multimodales pour l'optimisation de gestes de réparation tissulaire en insuffisance cardiaque." Electronic Thesis or Diss., Université de Rennes (2023-....), 2024. http://www.theses.fr/2024URENS001.
Анотація:
Les travaux de cette thèse s’inscrivent dans le contexte clinique visant à optimiser le geste lors des interventions endoventriculaires cardiaques. Cette recherche se concentre principalement sur le guidage en vue du diagnostic et du traitement des affections endoventriculaires à l’aide de cathéters. L’intervention considérée est la biopsie endoventriculaire utilisée pour diagnostiquer les patients atteints de sarcoïdose cardiaque. En effet, le cathéter doit être guidé avec précision vers la zone de fibrose. Cependant, l’absence d’informations visuelles précises sur la localisation de la fibrose pendant l’intervention accroît le risque de faux négatifs pour les échantillons prélevés. De plus, il existe un risque de complications telles que la perforation myocardique, également appelée tamponnade cardiaque. Les objectifs de cette thèse sont articulés en deux parties distinctes :La première partie, préopératoire, consiste à élaborer un modèle 3D du cœur, englobant le ventricule gauche, le ventricule droit et le myocarde. Ce modèle est construit à partir de segmentations d’images d’IRM, notamment des séquences ciné pour les structures principales et LGE pour localiser les zones de fibrose. Les méthodes de segmentation développées reposent sur l’apprentissage profond, et la méthode de segmentation de la fibrose fait l’objet d’une publication en cours. La seconde partie, peropératoire, vise à assis- ter la procédure en fournissant des informa- tions précises sur l’anatomie et la localisation de la zone fibrosée. Cela permet d’optimiser le positionnement du cathéter en périphérie de cette zone fibrosée, contribuant ainsi à améliorer la précision et l’efficacité de l’intervention. Enfin, l’ensemble de la chaîne de traitement a été expérimenté avec succès sur trois patients, procurant ainsi un retour d’expérience du clinicien. Ces avancées visent à réduire les risques liés à la biopsie endoventriculaire et à accroître la précision du diagnostic de la sarcoïdose cardiaque, ouvrant ainsi la voie à des progrès significatifs dans la prise en charge de cette pathologieThe research in this thesis is situated in the clinical context aimed at optimizing procedures during cardiac endoventricular interventions. This study primarily focuses on guidance for the diagnosis and treatment of endoventricular conditions using catheters. The specific intervention under consideration is the endoventricular biopsy used for diagnosing patients with cardiac sarcoidosis. Indeed, the catheter must be precisely guided to the fibrotic zone. However, the lack of precise visual information on the location of fibrosis during the intervention increases the risk of false negatives for the collected samples. Additionally, there is a risk of complications such as myocardial perforation, also known as cardiac tamponade. The objectives of this thesis are articulated in two distinct parts: The first part, preoperative, involves developing a 3D model of the heart, encompassing the left ventricle, right ventricle, and myocardium. This model is constructed from segmentations of MRI images, including cine sequences for the main structures and late gadolinium-enhanced (LGE) images to locate fibrotic zones. The segmentation methods developed rely on deep learning, and the fibrosis segmentation method is the subject of an ongoing publication. The second part, intraoperative, aims to assist the procedure by providing precise information about the anatomy and location of the fibrotic zone. This optimizes the positioning of the catheter on the periphery of this fibrotic zone, thereby contributing to improving the precision and efficiency of the intervention. Finally, the entire processing pipeline has been successfully tested on three patients, providing valuable feedback for clinicians. These advancements aim to reduce the risks associated with endoventricular biopsy and enhance the precision of cardiac sarcoidosis diagnosis, paving the way for significant progress in the management of this pathology
10
Smailes, Michael Edward. "Hybrid HVDC transformer for multi-terminal networks." Thesis, University of Edinburgh, 2018. http://hdl.handle.net/1842/31173.
Анотація:
There is a trend for offshore wind farms to move further from the point of common coupling to access higher and more consistent wind speeds to reduce the levelised cost of energy. To accommodate these rising transmission distances, High Voltage Direct Current (HVDC) transmission has become increasingly popular. However, existing HVDC wind farm topologies and converter systems are ill suited to the demands of offshore operation. The HVDC and AC substations have been shown to contribute to more than 20% of the capital cost of the wind farm and provide a single point of failure. Therefore, many wind farms have experienced significant delays in construction and commissioning, or been brought off line until faults could be repaired. What is more, around 75% of the cost of the HVDC and AC substations can be attributed to structural and installation costs. Learning from earlier experiences, industry is now beginning to investigate the potential of a modular approach. In place of a single large converter, several converters are connected in series, reducing substation individual size and complexity. While such options somewhat reduce the capital costs, further reductions are possible through elimination of the offshore substations altogether. This thesis concerns the design and evaluation the Hybrid HVDC Transformer, a high power, high voltage, DC transformer. This forms part of the platform-less (i.e. without substations) offshore DC power collection and distribution concept first introduced by the Offshore Renewable Energy Catapult. By operating in the medium frequency range the proposed Hybrid HVDC Transformer can be located within each turbine’s nacelle or tower and remove the need for expensive offshore AC and DC substations. While solid state, non-isolating DC-DC transformers have been proposed in the literature, they are incapable of achieving the step up ratios required for the Hybrid HVDC transformer [1]– [3]. A magnetic transformer is therefore required, although medium frequency and non-sinusoidal operation does complicate the design somewhat. For example, inter-winding capacitances are more significant and core losses are increased due to the added harmonics injected by the primary and secondary converters [1], [2]. To mitigate the impact of these complications, an investigation into the optimal design was conducted, including all power converter topologies, core shapes and winding configurations. The modular multilevel converter in this case proved to be the most efficient and practical topology however, the number of voltage levels that could be generated on the primary converter was limited by the DC bus voltage. To avoid the use of pulse width modulation and hence large switching losses, a novel MMC control algorithm is proposed to reduce the magnitude of the converter generated harmonics while maintaining a high efficiency. The development and analysis of this High Definition Modular Multilevel Control algorithm forms the bulk of this thesis’ contribution. While the High Definition Modular Multilevel Control algorithm was developed initially for the Hybrid HVDC Transformer, analysis shows it has several other potential applications particularly in medium and low voltage ranges.
11
Zhang, Yuwen. "An artificial neural network approach to transformer fault diagnosis." Thesis, This resource online, 1996. http://scholar.lib.vt.edu/theses/available/etd-08222008-063051/.
12
Lorello, Luca Salvatore. "Small transformers for Bioinformatics tasks." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2021. http://amslaurea.unibo.it/23883/.
Анотація:
Recent trends in bioinformatics are trying to align the techniques to more modern approaches based on statistical natural language processing and deep learning, however state-of-the-art neural natural language processing techniques remain relatively unexplored in this domain.
Large models are capable of achieving state-of-the-art performances, however, a typical bioinformatics lab has limited hardware resources. For this reason, this thesis focuses on small architectures, the training of which can be performed in a reasonable amount of time, while trying to limit or even negate the performance loss compared to SOTA.
In particular, sparse attention mechanisms (such as the one proposed by Longformer) and parameter sharing techniques (such as the one proposed by Albert) are jointly explored with respect to two genetic languages: human genome and eukaryotic mitochondrial genome of 2000+ different species.
Contextual embeddings for each token are learned via pretraining on a language understanding task, both in RoBERTa and Albert styles to highlight differences in performance and training efficiency.
The learned contextual embeddings are finally exploited for fine tuning a task of localization (transcription start site in human promoters) and two tasks of sequence classification (12S metagenomics in fishes and chromatin profile prediction, single-class and multi-class respectively).
Using smaller architectures, near SOTA performances are achieved in all the tasks already explored in literature, and a new SOTA has been established for the other tasks. Further experiments with larger architectures consistently improved the previous SOTA for every task.
13
Dronzeková, Michaela. "Analýza polygonálních modelů pomocí neuronových sítí." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2020. http://www.nusl.cz/ntk/nusl-417253.
Анотація:
This thesis deals with rotation estimation of 3D model of human jaw. It describes and compares methods for direct analysis od 3D models as well as method to analyze model using rasterization. To evaluate perfomance of proposed method, a metric that computes number of cases when prediction was less than 30° from ground truth is used. Proposed method that uses rasterization, takes three x-ray views of model as an input and processes it with convolutional network. It achieves best preformance, 99% with described metric. Method to directly analyze polygonal model as a sequence uses attention mechanism to do so and was inspired by transformer architecture. A special pooling function was proposed for this network that decreases memory requirements of the network. This method achieves 88%, but does not use rasterization and can process polygonal model directly. It is not as good as rasterization method with x-ray display, byt it is better than rasterization method with model not rendered as x-ray. The last method uses graph representation of mesh. Graph network had problems with overfitting, that is why it did not get good results and I think this method is not very suitable for analyzing plygonal model.
14
Siraj, Tammeen. "Seismic risk assessment of high-voltage transformers using Bayesian belief networks." Thesis, University of British Columbia, 2013. http://hdl.handle.net/2429/44245.
Анотація:
Past earthquake records showed that a large magnitude earthquake can cause severe damage to high-voltage substations, which may lead to power disruption for a significant amount of time. A high-voltage transformer is one of the key components of a substation. This thesis proposes a probabilistic framework using Bayesian belief network (BBN) model to predict the vulnerability of a high-voltage transformer for a seismic event. BBN has many capabilities that make it well suited for the proposed risk assessment method. This thesis considers past studies, expert knowledge and reported causes of failures to develop an initial integrated risk assessment framework that acknowledges multiple failure modes. Therefore, the framework incorporates major causes of transformer vulnerability due to seismicity, such as liquefaction, rocking response of transformer, or interaction between interconnected equipment. To demonstrate the application of this framework, this thesis elaborates each step of the framework. Finally, the sensitivity analysis was carried out to evaluate the effects of input variables on transformer damage. The paper also illustrates two predictive models using response surface method (RSM) and Markov chain. The proposed framework is particularly handy to perform, and the results can be useful to support decisions on mitigation measures and seismic risk prediction.
15
FONTE, RICARDO CUNHA DA. "FORECASTING TEMPERATURES IN POWER TRANSFORMERS COMBINING LINEAR MODELS AND NEURAL NETWORKS." PONTIFÍCIA UNIVERSIDADE CATÓLICA DO RIO DE JANEIRO, 2002. http://www.maxwell.vrac.puc-rio.br/Busca_etds.php?strSecao=resultado&nrSeq=3036@1.
Анотація:
ELETROBRAS - CENTRAIS ELÉTRICAS BRASILEIRAS S. A.O novo cenário competitivo, inaugurado com a reformulação do Setor Elétrico Brasileiro, impõe a seus agentes, principalmente as concessionárias de energia elétrica, a necessidade de ferramentas que os possibilitem gerenciar melhor seus recursos. No caso específico dos ransformadores de potência, ativos cujo investimento inicial é muito elevado,a otimização do retorno financeiro envolve o balanço adequado entre as receitas advindas da energia por ele transportada e os custos decorrentes da depreciação real, principalmente os relacionados à perda de vida útil do transformador como resultado da exposição do isolamento sólido a níveis de temperatura prejudiciais. A presente dissertação propõe o emprego de um modelo para previsão de séries temporais, aplicado a séries de elevação de temperatura do enrolamento de transformador de potência, combinando modelos lineares e Redes Neurais Artificiais. São revistos e analisados os principais métodos lineares de previsão baseados em variáveis explicativas, sendo estes, juntamente com o modelo proposto,aplicados à previsão da elevação de temperatura de transformadores reais. Os resultados obtidos comprovam o efeito sinérgico conseguido com a combinação de modelos lineares com Redes Neurais.
The new competitive scenario, that came up as result of the restructuring of the Brazilian Electric Energy Sector, imposes to its agents the need of tools suitable for better resource management. On the specific case of power transformers, which represent one of the most important investment items, the optimal payback involves a suitable balance between revenues related to the energy transported and the actual depreciation costs, mainly those related to the loss of the transformer s useful life, due the degradation of solid insulation by temperature. The present dissertation proposes a time series model, applied to power transformer winding temperature rise forecasting, which combines linear models and artificial neural networks. The main linear forecast methods based on explanatory variables are revised and analyzed, and, together with the proposed model, applied to temperature forecast on real transformers. The results confirm the synergic effect obtained when using linear models with artificial neural networks.
16
Gao, Chao. "Voltage control in distribution networks using on-load tap changer transformers." Thesis, University of Bath, 2013. https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.607476.
Анотація:
Voltage is one of the most important parameters for electrical power networks. The Distribution Network Operators (DNOs) have the responsibility to maintain the voltage supplied to consumers within statutory limits. On-Load Tap Changer (OLTC) transformer equipped with Automatic Voltage Control (AVC) relay is the most widely used and effective voltage control device. Due to a variety of advantages of adding Distributed Generation (DG), more and more distributed resources are connected to local distribution networks to solve constraints of networks, reduce the losses from power supply station to consumers. When DG is connected, the direction of power flow can be reversed when the DG output power exceeds the local load. This means that the bidirectional power flow can either be from power grid towards loads, or vice versa. The connection point of DG may suffer overvoltage when the DG is producing a large amount of apparent power. The intermittent nature of renewable energy resources which are most frequently used in DG technology results in uncertainty of distribution network operation. Overall, conventional OLTC voltage control methods need to be changed when DG is connected to distribution networks. The required voltage control needs to address challenges outlined above and new control method need to be formulated to reduce the limitations of DG output restricted by current operational policies by DNOs. The thesis presents an analysis of voltage control using OLTC transformer with DG in distribution networks. The thesis reviews conventional OLTC voltage control schemes and existing policies of DNOs in the UK. An overview of DG technologies is also presented with their operation characteristics based on power output. The impact of DG on OLTC voltage control schemes in distribution networks is simulated and discussed. The effects of different X/R ratio of overhead line and underground cable are also considered. These impacts need to be critically assessed before any new method implementation. The thesis also introduces the new concepts of Smart Grid and Smart Meter in terms of the transition from passive to active distribution networks. The role of Smart Meter and an overview of communication technologies that could be used for voltage control are investigated. The thesis analyses the high latency of an example solution of which cost and availability are considered to demonstrate the real-time voltage control using Smart Metering with existing communication infrastructures cannot be achieved cost-effectively. The thesis provides an advanced compensation-based OLTC voltage control algorithm using Automatic Compensation Voltage Control (ACVC) technique to improve the voltage control performance with DG penetration without communication. The proposed algorithm is simulated under varying load and DG conditions based on Simulink MATLAB to show the robustness of the proposed method. A generic 11kV network in the UK is modelled to evaluate the correct control performance of the advanced voltage control algorithm while increasing the DG capacity.
17
Hardie, Stewart Ramon. "A Prototype Transformer Partial Discharge Detection System." Thesis, University of Canterbury. Electrical and Computer Engineering, 2006. http://hdl.handle.net/10092/1114.
Анотація:
Increased pressure on high voltage power distribution components has been created in recent years by a demand to lower costs and extend equipment lifetimes. This has led to a need for condition based maintenance, which requires a continuous knowledge of equipment health. Power transformers are a vital component in a power distribution network. However, there are currently no established techniques to accurately monitor and diagnose faults in real-time while the transformer is on-line. A major factor in the degradation of power transformer insulation is partial discharging. Left unattended, partial discharges (PDs) will eventually cause complete insulation failure. PDs generate a variety of signals, including electrical pulses that travel through the windings of the transformer to the terminals. A difficulty with detecting these pulses in an on-line environment is that they can be masked by external electrical interference. This thesis develops a method for identifying PD pulses and determining the number of PD sources while the transformer is on-line and subject to external interference. The partial discharge detection system (PDDS) acquires electrical signals with current and voltage transducers that are placed on the transformer bushings, making it unnecessary to disconnect or open the transformer. These signals are filtered to prevent aliasing and to attenuate the power frequency, and then digitised and analysed in Matlab, a numerical processing software package. Arbitrary narrowband interference is removed with an automated Fourier domain threshold filter. Internal PD pulses are separated from stochastic wideband pulse interference using directional coupling, which is a technique that simultaneously analyses the current and voltage signals from a bushing. To improve performance of this stage, the continuous wavelet transform is used to discriminate time and frequency information. This provides the additional advantage of preserving the waveshapes of the PD pulses for later analysis. PD pulses originating within the transformer have their waveshapes distorted when travelling though the windings. The differentiation of waveshape distortion of pulses from multiple physical sources is used as an input to a neural network to group pulses from the same source. This allows phase resolved PD analysis to be presented for each PD source, for instance, as phase/magnitude/count plots. The neural network requires no prior knowledge of the transformer or pulse waveshapes. The thesis begins with a review of current techniques and trends for power transformer monitoring and diagnosis. The description of transducers and filters is followed by an explanation of each of the signal processing steps. Two transformers were used to conduct testing of the PDDS. The first transformer was opened and modified so that internal PDs could be simulated by injecting artificial pulses. Two test scenarios were created and the performance of the PDDS was recorded. The PDDS identified and extracted a high rate of simulated PDs and correctly allocated the pulses into PD source groups. A second identically constructed transformer was energised and analysed for any natural PDs while external interference was present. It was found to have a significant natural PD source.
18
Mao, Peilin. "Power transformer fault diagnosis based on wavelet transform and artificial neural network." Thesis, University of Bath, 2000. https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.760740.
19
Sun, Renfei. "Attention Network for Video Based Freezing of Gait Detection." Thesis, The University of Sydney, 2022. https://hdl.handle.net/2123/28908.
Анотація:
Freezing of gait (FoG) is a typical symptom of Parkinson's disease (PD), which is a brief, episodic absence or marked reduction despite the patients' intention of walking.
It is important to timely identify FoG events for clinical assessments. However, well-trained experts are required to identify FoG events, which is subjective and time-consuming.
Therefore, automatic FoG identification methods are highly demanded. In this study, we address this task as a human action detection problem based on vision inputs. Two novel attention based deep learning architectures, namely convolutional 3D attention network (C3DAN) and higher order polynomial transformer (HP-Transformer), are proposed to investigate fine-grained FoG patterns.
The C3DAN addresses the FoG detection task by exploring the appearance features in detail to learn an informative region for more effective detection. The network consists of two main parts: Spatial Attention Network (SAN) and 3-dimensional convolutional network (C3D). SAN aims to generate an attention regions from coarse to fine, while C3D extracts discriminative features. Our proposed approach is able to localize attention region without manual annotation and to extract discriminative features in an end-to-end way.
The HP-Transformer incorporates pose and appearance feature sequences to formulate fine-grained FoG patterns. In particular, higher order self-attentions are proposed based on higher order polynomials. To this end, linear, bilinear and trilinear transformers are formulated in pursuit of discriminative fine-grained representations. These representations are treated as multiple streams and further fused by a self-attention based fusion strategy for FoG detection.
Comprehensive experiments on a large in-house dataset collected during clinical assessments demonstrate the effectiveness of the proposed methods. The two methods both achieved promising results and in particular, the HP-Transformer achieved an AUC of 0.92 in the FoG detection task.
20
Zhang, Yuanhua. "Wavelet transforms, neural networks and migration applied to magnetotellurics." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1997. http://www.collectionscanada.ca/obj/s4/f2/dsk3/ftp04/nq23897.pdf.
21
Конденко, Віктор Анатолійович. "Електропостачання станційного виробничо-побутового приміщення залізничої станції". Bachelor's thesis, КПІ ім. Ігоря Сікорського, 2021. https://ela.kpi.ua/handle/123456789/43036.
Анотація:
Під час виконання дипломного проекту було проведено розрахунок навантажень цеху залізничної станції. Вибрано живлячі мережі напругою до 1 кВ та вище 1 кВ, силові трансформатори, апарати захисту та автоматики. Проведено розрахунок струмів короткого замикання.
У якості спец питання було проаналізовано проблеми якості та надійності електропостачання цеху, вибрано найбільш доступне можливе технічне рішення та підібрано електричні установки з необхідними характеристиками.During the implementation of the diploma project, the load calculations of the railway station shop were calculated. Supply networks up to 1 kV and above 1 kV, power transformers, protection devices and automation are selected. The calculation of short-circuit currents is carried out. As a special issue, the problems of quality and reliability of power supply of the shop were analyzed, the most accessible possible technical solution was selected and electrical installations with the necessary characteristics were selected.
22
GUSMAN, CHRISTIANE SAMPAIO DE ALMEIDA. "UNCERTAINTY OF MEASUREMENT IN ARTIFICIAL NEURAL NETWORKS APPLIED ON THE PREVENTATIVE MAINTENANCE OF TRANSFORMERS." PONTIFÍCIA UNIVERSIDADE CATÓLICA DO RIO DE JANEIRO, 2011. http://www.maxwell.vrac.puc-rio.br/Busca_etds.php?strSecao=resultado&nrSeq=19358@1.
Анотація:
Diversas pesquisas sobre monitoramento e diagnóstico de equipamentos do sistema elétrico foram iniciadas com o objetivo de elevar a garantia e confiabilidade no sistema. Autores, não somente no Brasil, desenvolveram pesquisas sobre o tema, dentre eles (Bengtson, 1996; Kovacevic & Dominelli, 2003; Freitas, 2000). O objetivo é garantir a confiabilidade dos equipamentos instalados e incrementar o desempenho aumentando a vida útil dos mesmos. Nesse contexto (Freitas, 2000; Cavaleiro, 2003; dentre outros) discorrem sobre o tema. As redes neurais artificiais são utilizadas como uma das possíveis ferramentas disponíveis para análise, diagnóstico e monitoramento de equipamentos. A inovação deste trabalho está em apresentar uma nova metodologia desenvolvida para analisar a propagação das incertezas de medição das variáveis de entrada em redes neurais artificiais aplicadas à Manutenção Preditiva de Transformadores. Com base nos conceitos da metrologia foram analisados não somente os dados de entrada como também a incerteza de medição associadas aos mesmos. O método desenvolvido permite que se estime a incerteza de medição das variáveis de saída, contribuindo para a avaliação da confiabilidade de modelagens baseadas em redes neurais. Também foi realizado um estudo de caso, no qual se avaliou a propagação das incertezas de medição em sete redes neurais destinadas a estimar a concentração dos gases (saídas das redes) dissolvidos no óleo de transformadores de potência, com base nas características físico-químicas do óleo (variáveis de entrada). A metodologia utilizada baseou-se na introdução de perturbações na
entrada das redes analisadas e na consequente análise de como estas perturbações afetam a saída das redes, permitindo-se assim calcular os coeficientes de sensibilidade de cada entrada. Em seguida, combinando-se as incertezas de medição das variáveis de entrada (disponíveis nos certificados de calibração dos instrumentos utilizados nas respectivas medições), por meio dos coeficientes de sensibilidade, é possível estimar a incerteza de medição das variáveis de saída.Research about monitoring and diagnostics of electrical system equipment was initiated with the objective of upgrading the guarantee and trust of a system. Authors, not only in Brazil, have developed research about the subject, among them (Bengtson, 1996; Kovacevic & Dominelli, 2003; Freitas, 2000). The objective is to guarantee the confidence in the equipment installed and enhance the performance and increase the durability of the equipment. Within this context (Freitas, 2000; Cavaleiro, 2003; among others) talk about this subject. The artificial Neural Networks are used as one of the possible available tools for analysis, diagnostics and monitoring of equipment. The innovation of this paper is to present a new methodology developed to analyze the propagation of uncertainty measurement variables of input in artificial neural networks applied to predictive maintenance of transformers. Based on the concepts of metrology, not only the input data was analyzed but also the uncertainty measurements that were associated with the equipment. The method that was developed allows us to estimate the measurement of uncertainty of output variables, contributing to the evaluation of confidence of models based on neural networks. There was also a case study, in which the propagation of uncertainties of measurement were evaluated within seven designated neural networks to estimate the concentration of gases (output of the networks) dissolved in potency transformer oil, based on the physical-chemical characteristics of the oil (input variables). The methodology that was utilized was based on the introduction of perturbation at the input of the networks that were analyzed and the consequent analysis of how these perturbation affect the output of the networks, this way allowing the calculation of the coefficients of sensibility of each entry. Then we match the input variables of the uncertainty measurements (available on the calibration certificates of the instruments utilized on the respective measurements), through the coefficients of sensibility, it is possible to estimate the output variables of the uncertainty measurements.
23
Tuan, Abdullah Tuan Ab Rashid Bin. "Optimal management of failures, spare parts and transformer reconnections in an electrical distribution network." Thesis, University of Strathclyde, 2009. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.501838.
24
Zheng, Cong. "Loosely Coupled Transformer and Tuning Network Design for High-Efficiency Inductive Power Transfer Systems." Diss., Virginia Tech, 2015. http://hdl.handle.net/10919/52893.
Анотація:
Transfer signal without wire has been widely accepted after the introduction of cellular technology and WiFi technology, hence the power cable is the last wire that has yet to be eliminated. Inductive power transfer (IPT) has drawn substantial interest in both academia and industry due to its advantages including convenience, nonexistence of cable and connector, no electric shock issue, ability to work under some extreme environment, and so on. After performing thorough literature review of IPT systems, two major drawbacks including low power efficiency and coil displacement sensitivity are identified as the main obstacles that have to be solved in order for these systems to reach full functionality and compete with existing wired solutions.
To address the limitations and design challenges in the IPT systems, a detailed electric circuit modeling of individual part of the IPT DC-DC stage is performed. Several resonant DC-AC inverters and output AC-DC rectifiers are compared based on their performance and feasibility in inductive charging applications. Different equivalent circuit models for the loosely coupled
transformer (LCT) are derived which allows for better understanding on how power is distributed among the circuit components. Five compensation networks to improve the power transfer efficiency are evaluated and their suitable application occasions are identified.
With comprehensive circuit model analysis, the influence of the resonant compensation tank parameters has been investigated carefully for efficient power transfer. A novel tuning network parameters design methodology is proposed based on multiple given requirement such as battery charging profile, geometry constraints and operating frequency range, with the aim of avoiding bifurcation phenomenon during the whole charging process and achieving decent efficiency. A 4-kW hardware prototype based on the proposed design approach is built and tested under different gap and load conditions. Peak IPT system DC-DC efficiencies of 98% and 96.6% are achieved with 4-cm and 8-cm air gap conditions, which is comparable to the conventional plug-in type or wired charging systems for EVs. A long-hour test with real EV batteries is conducted to verify the wireless signal transmission and CC/CV mode seamless transition during the whole charging profile without bifurcation.
To reduce the IPT system sensitivity to the gap variation or misalignment, a novel LCT design approach without additional complexity for the system is proposed. With the aid of FEA simulation software, the influence of coil relative position and geometry parameters on the flux distribution and coupling coefficient of the transmitter and receiver is studied from an electromagnetic perspective. An asymmetrical LCT based on the proposed design method is built to compare with a traditional symmetrical LCT. With fixed 10-mm gap and 0 to 40-mm misalignment variation, the coupling coefficient for the symmetrical LCT drops from 0.354 to 0.107, and the corresponding efficiency decrease is 16.6%. The operating frequency variation is nearly 100 kHz to maintain same input/output condition. When employing the proposed asymmetrical LCT, the coupling coefficient changes between 0.312 and 0.273, and the maximum efficiency deviation is kept within 0.67% over the entire 40-mm misalignment range. Moreover, the required frequency range to achieve same operation condition is less than 10 kHz.
Lastly, some design considerations to further improve the IPT system efficiency are proposed on the basis of the designed asymmetrical LCT geometry. For given circuit specifications and LCT coupling conditions, determination of the optimal primary winding turns number could help achieve minimal winding loss and core loss. For lower output power, the optimal primary winding turns number tends to be larger compared to that for higher output power IPT system. Two asymmetrical LCT with similar dimension but different number of turns are built and tested with a 100-W hardware prototype for laptop inductive charging. The proposed efficiency improvement methodology is validated by the winding loss and core loss from experimental results.Ph. D.
25
Alarcon, Aquino Vicente. "Anomaly detection and prediction in communication networks using wavelet transforms." Thesis, Imperial College London, 2003. http://hdl.handle.net/10044/1/11475.
26
Tuerk, Christine M. "Automatic speech synthesis using auditory transforms and artificial neural networks." Thesis, University of Cambridge, 1992. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.385362.
27
Singh, Arvind. "A multi-layer neural network approach to identification of mechanical damage in power transformer windings." Thesis, University of British Columbia, 2009. http://hdl.handle.net/2429/5677.
Анотація:
Power transformers are among the most critical of assets for electric utilities, in the financial
impact that their failure can bring. Asset Managers need to be able to determine the
right time for replacement, refurbishment or relocation of these devices, with an increasing
degree of confidence, in order to minimize the total cost of operation over the equipments’
life. This has brought a change from scheduled maintenance to condition based monitoring
(CBM), where the state of the transformer is continuously monitored to evaluate its working
condition.
A key method of transformer CBM, which effectively detects mechanical damage to the
structure of the transformer windings, is Frequency Response Analysis (FRA). FRA relies
on comparison of electrical admittance signatures to determine if the winding has become
deformed. One of the major problems it still faces is the interpretation of differences in
the signatures. To date, experts are needed to analyse graphs, drawing from experience in
order to produce educated guesses as to what the differences in admittance functions denote.
However, in the recent past, there has been some headway in programming computer based
solutions for the problem of interpretation.
The use of Artificial Neural Networks (ANNs) has perhaps been the most promising in this
respect. ANNs perform in the same way that human experts do, drawing upon experience to
map a change in shape of a signature to a physical change in the winding system. However,
one of the major drawbacks of these methods is the large training data-sets required for the
neural network to learn.
The work reported in this thesis seeks to address this problem by generating training datasets
from analytical models of the transformer. Due to the large number of simulations that
need to be performed a customized solution method was developed to speed up computations.
A combination of back propagation and radial basis function networks were then used
to classify the type, location and severity of winding movement. The results showed that
the neural network approach was not only accurate but tolerant to high noise levels.
28
Segatto, Ênio Carlos. "Relé diferencial para transformadores de potência utilizando ferramentas inteligentes." Universidade de São Paulo, 2005. http://www.teses.usp.br/teses/disponiveis/18/18133/tde-19022016-144637/.
Анотація:
Este trabalho apresenta a proposta de um sistema completo de proteção diferencial de transformadores de potência, aplicando-se as técnicas de Redes Neurais Artificiais (RNAs). O esquema proposto busca a classificação do sistema de proteção como um problema de reconhecimento e reconstrução de padrões, representando um método alternativo aos algoritmos convencionais. Vários fatores como, por exemplo, as situações de energização do transformador e a saturação dos transformadores de corrente, podem causar uma má operação do dispositivo de proteção. Com o objetivo de melhoramento na proteção digital de transformadores de potência, desenvolveu-se um sistema de proteção diferencial, incluindo dispositivos com base em RNAs, em substituição à filtragem harmônica de sinais existente no algoritmo convencional. Em complementação, esquemas de reconstrução das ondas distorcidas provenientes da saturação dos TCs são também propostos e adicionados ao algoritmo final de proteção, sendo esses comparados ao algoritmo convencional de proteção diferencial de transformadores. Com a referida adição de ferramentas de inteligência artificial a um algoritmo completo de proteção diferencial de transformadores, obteve-se uma solução bastante precisa e eficiente, capaz de responder em um tempo reduzido, se comparada aos métodos convencionais.This work proposes a complete differential protection system for power transformers, applying the Artificial Neural Network (ANN) theory. The proposed approach treat the classification of the protection system as a problem of pattern recognition and as an alternative method to the conventional algorithms. Several factors such as, for example, transformer energization and CT saturation can cause an inadequate operation of the protection relay. With the objective of improving the power transformer digital protection, a complete protection system was developed, including an ANN-based device in substitution to harmonic filters, in use in the conventional algorithm. Some approaches concerning the reconstruction of the distorted signals caused by the CTs saturation are also proposed. These routines are added to the final protection algorithm and they are compared to the conventional algorithm for power transformer protection. With the use of artificial intelligence tools in a complete power transformer protection algorithm, one intends to obtain a very precise, fast and efficient solution, if compared to the conventional methods.
29
Tavakoli, Hanif. "An FRA Transformer Model with Application on Time Domain Reflectometry." Doctoral thesis, KTH, Elektroteknisk teori och konstruktion, 2011. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-48568.
Анотація:
Frequency response analysis (FRA) is a frequency-domain method which is used to detect mechanical faults in transformers. The frequency response of a transformer is determined by its geometry and material properties, and it can be considered as the transformer’s fingerprint. If there are any mechanical changes in the transformer, for example if the windings are moved or distorted, its fingerprint will also be changed so, theoretically, mechanical changes in the transformer can be detected with FRA. A problem with FRA is the fact that there is no general agreement about how to interpret the measurement results for detection of winding damages. For instance, the interpretation of measurement results has still not been standardized.The overall goal of this thesis is to try to enhance the understanding of the information contained in FRA measurements. This has been done in two ways: (1) by examining the FRA method for (much) higher frequencies than what is usual, and (2) by developing a new method in which FRA is combined with the ideas of Time Domain Reflectometry (TDR). As tools for carrying out the above mentioned steps, models for the magnetic core and the winding have been developed and verified by comparison to measurements.The usual upper frequency limit for FRA is around 2 MHz, which in this thesis has been extended by an order of magnitude in order to detect and interpret new phenomena that emerge at high frequencies and to investigate the potential of this high-frequency region for detection of winding deteriorations.Further, in the above-mentioned new method developed in this thesis, FRA and TDR are combined as a step towards an easier and more intuitive detection and localization of faults in transformer windings, where frequency response measurements are visualized in the time domain in order to facilitate their interpretation.QC 20111122
30
Westermark, Pontus. "Wavelets, Scattering transforms and Convolutional neural networks : Tools for image processing." Thesis, Uppsala universitet, Analys och sannolikhetsteori, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-337570.
31
Adjei, Osei Nana. "The use of radon transforms and neural networks in image recognition." Thesis, Cranfield University, 1996. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.359966.
32
Зарва, В. Ю. "Розрахунок техніко-економічного обґрунтування переведення розподільчих мереж 35 кВ на 20 кВ". Master's thesis, Сумський державний університет, 2019. http://essuir.sumdu.edu.ua/handle/123456789/76099.
Анотація:
Розроблено проект реконструкції підстанції на нижчий клас напруги 20 кВ, розраховані капітальні затрати на реконструкцію, проведений економічний аналіз доцільності правильного вибору перерізу провідників, обґрунтована доцільність переходу на клас напруги 20 кВ.
33
Wang, Zhenyuan. "Artificial Intelligence Applications in the Diagnosis of Power Transformer Incipient Faults." Diss., Virginia Tech, 2000. http://hdl.handle.net/10919/28594.
Анотація:
This dissertation is a systematic study of artificial intelligence (AI) applications for the diagnosis of power transformer incipient fault.
The AI techniques include artificial neural networks (ANN, or briefly neural networks - NN), expert systems, fuzzy systems and multivariate regression.
The fault diagnosis is based on dissolved gas-in-oil analysis (DGA). A literature review showed that the conventional fault diagnosis methods, i.e. the ratio methods (Rogers, Dornenburg and IEC) and the key gas method, have limitations such as the "no decision" problem. Various AI techniques may help solve the problems and present a better solution.
Based on the IEC 599 standard and industrial experiences, a knowledge-based inference engine for fault detection was developed. Using historical transformer failure data from an industrial partner, a multi-layer perceptron (MLP) modular neural network was identified as the best choice among several neural network architectures. Subsequently, the concept of a hybrid diagnosis was proposed and implemented, resulting in a combined neural network and expert system tool (the ANNEPS system) for power transformer incipient diagnosis. The abnormal condition screening process, as well as the principle and algorithms of combining the outputs of knowledge based and neural network based diagnosis, were proposed and implemented in the ANNEPS. Methods of fuzzy logic based transformer oil/paper insulation condition assessment, and estimation of oil sampling interval and maintenance recommendations, were also proposed and implemented.
Several methods of power transformer incipient fault location were investigated, and a 7Ã 21Ã 5 MLP network was identified as the best choice. Several methods for on-load tap changer (OLTC) coking diagnosis were also investigated, and a MLP based modular network was identified as the best choice. Logistic regression analysis was identified as a good auditor in neural network input pattern selection processes.
The above results can help developing better power transformer maintenance strategies, and serve as the basis of on-line DGA transformer monitors.Ph. D.
34
Paya, Basir Abdul. "Vibration condition monitoring and fault diagnostics of rotating machinery using artificial neural networks." Thesis, Brunel University, 1998. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.390220.
35
Monteiro, Thiago Costa. "Proposta de modelo e método para determinação dos parâmetros de transformadores operando em saturação." Universidade de São Paulo, 2011. http://www.teses.usp.br/teses/disponiveis/3/3143/tde-31052011-154602/.
Анотація:
Uma série de equipamentos de eletrônica de potência é ligada à rede de corrente alternada através de transformadores, que exercem as funções de isolamento galvânico, elevação/abaixamento de tensão, etc. Estes transformadores podem sofrer saturação em condições transitórias (inrush) ou quando o conversor ligado a ele impõe valor médio não nulo de tensão. O problema é normalmente sanado nas malhas de controle do conversor, no entanto o ajuste destas malhas em ambiente de simulação computacional requer um modelo que represente adequadamente a característica de saturação do núcleo ferromagnético. Este trabalho apresenta um modelo de simulação computacional adequado para transformadores operando em saturação intensa, visando aplicações em projetos de equipamentos de eletrônica de potência com transformador monofásico alimentado por inversor. Além disso, é demonstrado um método experimental de obtenção da característica de saturação do núcleo, sem necessidade das suas características construtivas. Resultados de simulação obtidos são comparados com resultados experimentais para validação do modelo e método.Several power electronics based equipments are connected to the alternating current network through transformers, which perform galvanic insulation, voltage increasing/lowering, etc. These transformers may experience saturation under transitory conditions (inrush), or when its converter imposes non-zero average voltage. Such problem is commonly treated in the converter\'s control loops, but the tuning of these loops in a computer simulation environment requires a transformer model that represents adequately the ferromagnetic core saturation effect. The current work proposes a computer simulation model that adequately describes the operation of the transformer at deep saturation, suitable for design of power electronics applications with single phase transformers connected to power inverter. Additionally, an experimental method for determining its core saturation characteristic is demonstrated. This method does not require previous knowledge of the core\'s constructive parameters. Simulation and experimental results are presented to confirm the validity of the model and the method.
36
Thang, Ka Fei. "An improved approach to data analysis & interpretation in transformer condition assessment based on unsupervised neutral network." Thesis, University of Bath, 2002. https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.760820.
37
Chen, Linwei. "Distribution network supports for transmission system reactive power management." Thesis, University of Manchester, 2015. https://www.research.manchester.ac.uk/portal/en/theses/distribution-network-supports-for-transmission-system-reactive-power-management(abcc8197-fd85-478b-b91a-fd3d0b3220db).html.
Анотація:
To mitigate high voltages in transmission systems with low demands, traditional solutions often consider the installation of reactive power compensators. The deployment and tuning of numbers of VAr compensators at various locations may not be cost-effective. This thesis presents an alternative method that utilises existing parallel transformers in distribution networks to provide reactive power supports for transmission systems under low demands. The operation of parallel transformers in small different tap positions, i.e. with staggered taps, can provide a means of absorbing reactive power. The aggregated reactive power absorption from many pairs of parallel transformers could be sufficient to provide voltage support to the upstream transmission network. Network capability studies have been carried out to investigate the reactive power absorption capability through the use of tap stagger. The studies are based on a real UK High Voltage distribution network, and the tap staggering technique has been applied to primary substation transformers. The results confirm that the tap staggering method has the potential to increase the reactive power demand drawn from the transmission grid. This thesis also presents an optimal control method for tap stagger to minimise the introduced network loss as well as the number of tap switching operations involved. A genetic algorithm (GA) based procedure has been developed to solve the optimisation problem. The GA method has been compared with two alternative solution approaches, i.e. the rule-based control scheme and the branch-and-bound algorithm. The results indicate that the GA method is superior to the other two approaches. The economic and technical impacts of the tap staggering technique on the transmission system has been studied. In the economic analysis, the associated costs of applying the tap staggering method have been investigated from the perspective of transmission system operator. The IEEE Reliability Test System has been used to carry out the studies, and the results have been compared with the installation of shunt reactors. In the technical studies, the dynamic impacts of tap staggering or reactor switching on transmission system voltages have been analysed. From the results, the tap staggering technique has more economic advantages than reactors and can reduce voltage damping as well as overshoots during the transient states.
38
Zhang, Boyi. "Distribution network automation for multi-objective optimisation." Thesis, University of Manchester, 2018. https://www.research.manchester.ac.uk/portal/en/theses/distribution-network-automation-for-multiobjective-optimisation(4d04be21-2ac5-4891-8bcf-9b8ed6532043).html.
Анотація:
Asset management and automation are acknowledged by distribution utilities as a useful strategy to improve service quality and reliability. However, the major challenge faced by decision makers in distribution utilities is how to achieve long-term return on the projects while minimising investment and operation costs. Distribution automation (DA) in terms of transformer economic operation (TEO), distribution network reconfiguration (DNR), and sectionalising switch placement (SSP) is recognised as the most effective way for distribution network operators (DNOs) to increase operation efficiency and reliability. Automated tie-switches and sectionalising switches play a fundamental role in distribution networks. A method based on the Monte Carlo simulation is discussed for transformer loss reduction, which comprises of profile generators of residential demand and a distribution network model. The ant colony optimisation (ACO) algorithm is then developed for optimal DNR and TEO to minimise network loss. An ACO algorithm based on a fuzzy multi-objective approach is proposed to solve SSP problem, which considers reliability indices and switch costs. Finally, a multi-objective ant colony optimisation (MOACO) and an artificial immune systems-ant colony optimisation (AIS-ACO) algorithm are developed to solve the reconfiguration problem, which is formulated within a multi-objective framework using the concept of Pareto optimality. The performance of the optimisation techniques has been assessed and illustrated by various case studies on three distribution networks. The obtained optimum network configurations indicate the effectiveness of the proposed methods for optimal DA.
39
Oriaifo, Stacey I. "Effects of Large-Scale Penetration of Electric Vehicles on the Distribution Network and Mitigation by Demand Side Management." Thesis, Virginia Tech, 2014. http://hdl.handle.net/10919/49681.
Анотація:
For the purpose of this study, data for low voltage distribution transformer loading in small communities in Maryland was collected from a local electric utility company. Specifically, analysis was done on three distribution transformers on their system. Each of these transformers serves at least one electric vehicle (EV) owner. Of the three transformers analyzed, Transformer 2 serves eight residential homes and has the highest risk of experiencing an overload if all customers purchase at least one EV. Transformer 2 has a nameplate rating of 25kVA (22.5kW assuming a 0.9 power factor).
With one EV owner, Transformer 2 has a peak load of 46.82kW during the study period between August 4 and August 17, 2013. When seven additional EVs of different types were added in a simulated scenario, the peak load for Transformer 2 increased from 46.82kW to 89.76kW, which is outside the transformer thermal limit. With the implementation of TOU pricing, the peak load was reduced to 56.71kW from 89.76kW. By implementing a combination of TOU pricing and appliance cycling through demand side management (DSM), the peak load was further reduced to 52.27kW.Master of Science
40
Dimitriadis, Spyridon. "Multi-task regression QSAR/QSPR prediction utilizing text-based Transformer Neural Network and single-task using feature-based models." Thesis, Linköpings universitet, Statistik och maskininlärning, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-177186.
Анотація:
With the recent advantages of machine learning in cheminformatics, the drug discovery process has been accelerated; providing a high impact in the field of medicine and public health. Molecular property and activity prediction are key elements in the early stages of drug discovery by helping prioritize the experiments and reduce the experimental work. In this thesis, a novel approach for multi-task regression using a text-based Transformer model is introduced and thoroughly explored for training on a number of properties or activities simultaneously. This multi-task regression with Transformer based model is inspired by the field of Natural Language Processing (NLP) which uses prefix tokens to distinguish between each task. In order to investigate our architecture two data categories are used; 133 biological activities from ExCAPE database and three physical chemistry properties from MoleculeNet benchmark datasets. The Transformer model consists of the embedding layer with positional encoding, a number of encoder layers, and a Feedforward Neural Network (FNN) to turn it into a regression problem. The molecules are represented as a string of characters using the Simplified Molecular-Input Line-Entry System (SMILES) which is a ’chemistry language’ with its own syntax. In addition, the effect of Transfer Learning is explored by experimenting with two pretrained Transformer models, pretrained on 1.5 million and on 100 million molecules. The text-base Transformer models are compared with a feature-based Support Vector Regression (SVR) with the Tanimoto kernel where the input molecules are encoded as Extended Connectivity Fingerprint (ECFP), which are calculated features. The results have shown that Transfer Learning is crucial for improving the performance on both property and activity predictions. On bioactivity tasks, the larger pretrained Transformer on 100 million molecules achieved comparable performance to the feature-based SVR model; however, overall SVR performed better on the majority of the bioactivity tasks. On the other hand, on physicochemistry property tasks, the larger pretrained Transformer outperformed SVR on all three tasks. Concluding, the multi-task regression architecture with the prefix token had comparable performance with the traditional feature-based approach on predicting different molecular properties or activities. Lastly, using the larger pretrained models trained on a wide chemical space can play a key role in improving the performance of Transformer models on these tasks.
41
Pezeshki, Houman. "Voltage balance improvement in urban low voltage distribution networks." Thesis, Queensland University of Technology, 2015. https://eprints.qut.edu.au/84155/1/Houman_Pezeshki_Thesis.pdf.
Анотація:
This project is a step forward in developing effective methods to mitigate voltage unbalance in urban residential networks. The method is proposed to reduce energy losses and improve quality of service in strongly unbalanced low-voltage networks. The method is based on phase swapping as well as optimal placement and sizing of Distribution Static Synchronous Compensator (D-STATCOM) using a Particle Swarm Optimisation method.
42
Niccolai, Lorenzo. "Distillation Knowledge applied on Pegasus for Summarization." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2020. http://amslaurea.unibo.it/22202/.
Анотація:
In the scope of Natural Language Processing one of the most intricate tasks is Text Summarization, in human terms: writing an essay. Something that we learn in primary school is yet very difficult to reproduce for a machine, it was almost impossible before the advent of Deep Learning. The trending technology to face up Summarization - and every task that involves generating text - is the Transformer. This thesis aims to experiment what entails reducing the complexity of Pegasus, a huge state-of-the-art model based on Transformers. Through a technique called Knowledge Distillation the original model can be compressed in a smaller one transferring the knowledge, but without losing much efficiency. For the experimentation part the distilled replicas were varied in size and their performance assessed evaluating some suitable metrics. Reducing the computational power needed by the models is crucial to deploy such technologies in devices with poor capabilities and a not reliable enough internet connection to use cloud computing, like mobile devices.
43
Маландій, Я. О. "Модернізація обладнання трансформаторної підстанції та його моделювання". Master's thesis, Сумський державний університет, 2020. https://essuir.sumdu.edu.ua/handle/123456789/82334.
44
Спірін, Д. В. "Проектування системи електропостачання Роменського мікрорайону м. Суми на напрузі 20 кВ". Master's thesis, Сумський державний університет, 2021. https://essuir.sumdu.edu.ua/handle/123456789/87274.
Анотація:
Розроблено проект для будівництва підстанції 110/20кВ, кабельної та повітряної лінії 20 кВ для електропостачання побутових споживачів. Виконані відповідні креслення до проекту. Проведено
вибір обладнання підстанції і креслення для його установки. Обрані марки та перетин проводів і кабелів на напругу 20 кВ. Подані розрахунки щодо вибору обладнання підстанції і кабельно-провідникової продукції.
Приведено техніко-економічне обґрунтування проекту та наведена порівняльна характеристика з мереж 6 і 20 кВ. Вирішені питання з охорони праці, пожежної безпеки і охорони середовища.
45
Клемберг, І. С. "Проектування системи електропостачання сушильного цеху елеватору філії АТ "ДПЗКУ" "Сумський КХП"". Master's thesis, Сумський державний університет, 2020. https://essuir.sumdu.edu.ua/handle/123456789/81984.
Анотація:
В даному дипломному проекті при «Проектування системи електропостачання сушильного цеху елеватору філії АТ «ДПЗКУ» «Сумський КХП»» розглядаються завдання: розрахунок електричних навантажень, вибір схем зовнішнього і внутрішнього електропостачання.
Визначення кількості трансформаторів і їх номінальної потужності, розрахунок перетинів кабельних ліній, вибір пуско-захистної апаратури – автоматичних вимикачів, проводиться вибір обладнання в схемах зовнішнього і внутрішнього електропостачання за умовами роботи в режимі короткого
замикання.
Огляд заходів з охорони праці, розрахунок і визначення кількості обслуговуючого персоналу, розрахунок орієнтовної оцінки необхідних
капітальних вкладень.
46
Мелащенко, Б. Г. "Техніко-економічне обґрунтування переведення розподільчих мереж 35 кВ на 20 кВ". Master's thesis, Сумський державний університет, 2020. https://essuir.sumdu.edu.ua/handle/123456789/82359.
Анотація:
Розроблено проект реконструкції підстанції на нижчий клас напруги 35 кВ. В ході реконструкції ліній електропередач порівнювались декілька варіантів на напругу 35 кВ та декілька варіантів на напругу 20 кВ. Головною причиною розрахунків декількох варіантів ЛЕП є застарілі значення економічної густини струму.
Розраховані капітальні затрати на реконструкцію, проведений економічний аналіз доцільності правильного вибору перерізу провідників, обґрунтована до-цільність переходу на клас напруги 20 кВ. Розглянуто питання безпеки праці. Зроблено аналіз небезпечних і шкідливих виробничих факторів, викладені роз-діли по техніці безпеки.
47
Васюков, А. О. "Розрахунок режимів роботи електричної мережі та вибір обладнання високовольтної підстанції". Master's thesis, Сумський державний університет, 2019. http://essuir.sumdu.edu.ua/handle/123456789/76137.
Анотація:
Розроблено мережу електропостачання для споживачів електричної енергії різних категорій. Спроектовано схему, розроблена однолінійна схема. Зроблено розрахунки всіх елементів мережі, перевірено розрахунком на міцність та витривалість елементів установок при повній завантаженості та аварійних режимів. Приведено техніко-економічне обґрунтування проекту з визначенням економічного ефекту від впровадження установки. Виконана робота з охорони праці, вирішено питання техніки безпеки, пожежної безпеки.
Проведено техніко-економічне обґрунтування побудови та розглянуто основні питання охорони праці під час робіт зі спорудження електричної мережі.
48
Nanda, Santosh Kumar. "Application Of Neural Network For Transformer Protection." Thesis, 2013. http://ethesis.nitrkl.ac.in/4699/1/211EE2135.pdf.
Анотація:
The demand for a reliable supply of electrical energy for the exigency of modern world in each and every field has increased considerably requiring nearly a no-fault operation of power systems. The crucial objective is to mitigate the frequency and duration of unwanted outages related to power transformer puts a high pointed demand on power transformer protective relays to operate immaculately and capriciously. The high pointed demand includes the requirements of dependability associated with no false tripping, and operating speed with short fault detection and clearing time. The second harmonic restrain principle is widely used in industrial application for many years, which uses discrete Fourier transform (DFT) often encounters some problems such as long restrain time and inability to discriminate internal fault from magnetizing inrush condition. Hence, artificial neural network (ANN), a powerful tool for artificial intelligence (AI), which has the ability to mimic and automate the knowledge, has been proposed for detection and classification of faults from normal and inrush condition. The wavelet transform(WT) which has the ability to extract information from transient signals in both time and frequency domain simultaneously is used for the analysis of power transformer transient phenomena in various conditions. All the above mentioned conditions of power transformer to be analysed in a power system are modelled in MATLAB/SIMULINK environment. Secondly the WT is applied to decompose the different current signals of the power transformer into a series of detailed wavelet components. The statistical features of the wavelet components are calculated and are used to train a multilayer feed forward neural network designed using back propagation algorithm to discriminate various conditions. The best suitable architecture of ANN is selected having least mean square error during training. The ANN model is implemented in LabVIEW environment.
49
Pramanik, Saurav. "Complex Network-Function-Loci For Localization Of Discrete Change In Transformer Windings." Thesis, 2010. https://etd.iisc.ac.in/handle/2005/1327.
Анотація:
Large capacity high voltage power transformers are one of the most expensive items of equipment in an electrical power network. Power utilities can ill-afford breakdown of transformers, especially, in a deregulated scenario. The consequences of such a failure are well known. Under these circumstances, utilities have figured-out that condition-based monitoring and diagnosis is worth pursuing, in spite of increased expenditure. Thus, monitoring and diagnosis is an integral part of operation and maintenance.
Mechanical forces generated during short-circuits is the main cause leading to displacement/deformation of windings. Frequency response measurements have attained worldwide acceptance as a highly sensitive monitoring tool for detecting occurrence of such events. This is evident from the fact that customized commercial equipment are available (popularly called FRA or SFRA instruments), and with recent introduction of an IEEE draft trial-use guide for application and interpretation of frequency response analysis. Once a damage is detected, the next task is to identify its location along the winding and, if possible, determine its extent of severity. Understandably, these two tasks are best achieved, without disassembling the transformer and should ideally be based on off-line and on-site terminal measurements.
In this regard, literature analysis reveals that recent research efforts have successfully demonstrated possibilities of using frequency response data for localization of discrete change in windings. This is indeed noteworthy, in spite of one major drawback. This pertains to excessive computing time needed to synthesize large-sized ladder-network, which automatically limits its practical use. Keeping these issues in mind, a research was initiated to find alternatives. The primary objective of this thesis is to examine the use of-
• Complexnetwork-function-lociforlocalizationofadiscretechangeinasingle,isolatedtransformerwinding,basedonterminalmeasurements
It goes without saying that the proposed method should be non-invasive, simple, time-efficient and overcome drawbacks in the earlier approach. A brief summary of the proposed method follows-
This thesis presents a different approach to tackle the problem of localization of winding deformation in a transformer. Within the context of this thesis, winding deformation means, a discrete and specific change imposed at a particular position on the winding. The proposed method is based on the principle of pre-computing and plotting the complex network-function-loci (e.g. driving-point-impedance) at a selected frequency, for a meaningful range of values for each element (increasing and decreasing) of the ladder network. This loci diagram is called the nomogram. After introducing a discrete change (to simulate a deformation), the driving-point-impedance (amplitude and phase) is measured again .By plotting this single measurement on the nomogram, it is straightforward to estimate the location and identify the extent of change. In contrast to the earlier approach (wherein the entire ladder-network had to be synthesized for every new measurement), the proposed method overcomes the drawbacks, is non-iterative and yields reasonably accurate localization. Experimental results on a model coil and two actual transformer windings (continuous-disc and interleaved-disc) were encouraging and demonstrate its potential.
Further details are presented in the thesis.
50
Pramanik, Saurav. "Complex Network-Function-Loci For Localization Of Discrete Change In Transformer Windings." Thesis, 2010. http://etd.iisc.ernet.in/handle/2005/1327.
Анотація:
Large capacity high voltage power transformers are one of the most expensive items of equipment in an electrical power network. Power utilities can ill-afford breakdown of transformers, especially, in a deregulated scenario. The consequences of such a failure are well known. Under these circumstances, utilities have figured-out that condition-based monitoring and diagnosis is worth pursuing, in spite of increased expenditure. Thus, monitoring and diagnosis is an integral part of operation and maintenance.
Mechanical forces generated during short-circuits is the main cause leading to displacement/deformation of windings. Frequency response measurements have attained worldwide acceptance as a highly sensitive monitoring tool for detecting occurrence of such events. This is evident from the fact that customized commercial equipment are available (popularly called FRA or SFRA instruments), and with recent introduction of an IEEE draft trial-use guide for application and interpretation of frequency response analysis. Once a damage is detected, the next task is to identify its location along the winding and, if possible, determine its extent of severity. Understandably, these two tasks are best achieved, without disassembling the transformer and should ideally be based on off-line and on-site terminal measurements.
In this regard, literature analysis reveals that recent research efforts have successfully demonstrated possibilities of using frequency response data for localization of discrete change in windings. This is indeed noteworthy, in spite of one major drawback. This pertains to excessive computing time needed to synthesize large-sized ladder-network, which automatically limits its practical use. Keeping these issues in mind, a research was initiated to find alternatives. The primary objective of this thesis is to examine the use of-
• Complexnetwork-function-lociforlocalizationofadiscretechangeinasingle,isolatedtransformerwinding,basedonterminalmeasurements
It goes without saying that the proposed method should be non-invasive, simple, time-efficient and overcome drawbacks in the earlier approach. A brief summary of the proposed method follows-
This thesis presents a different approach to tackle the problem of localization of winding deformation in a transformer. Within the context of this thesis, winding deformation means, a discrete and specific change imposed at a particular position on the winding. The proposed method is based on the principle of pre-computing and plotting the complex network-function-loci (e.g. driving-point-impedance) at a selected frequency, for a meaningful range of values for each element (increasing and decreasing) of the ladder network. This loci diagram is called the nomogram. After introducing a discrete change (to simulate a deformation), the driving-point-impedance (amplitude and phase) is measured again .By plotting this single measurement on the nomogram, it is straightforward to estimate the location and identify the extent of change. In contrast to the earlier approach (wherein the entire ladder-network had to be synthesized for every new measurement), the proposed method overcomes the drawbacks, is non-iterative and yields reasonably accurate localization. Experimental results on a model coil and two actual transformer windings (continuous-disc and interleaved-disc) were encouraging and demonstrate its potential.
Further details are presented in the thesis.