Добірка наукової літератури з теми "Activation parameters optimization"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся зі списками актуальних статей, книг, дисертацій, тез та інших наукових джерел на тему "Activation parameters optimization".
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.
Статті в журналах з теми "Activation parameters optimization":
1
Fuzeau, J., M. Vasudevan, and V. Maduraimuthu. "Optimization of Welding Process Parameters for Reduced Activation Ferritic-Martensitic (RAFM) Steel." Transactions of the Indian Institute of Metals 69, no. 8 (January 9, 2016): 1493–99. http://dx.doi.org/10.1007/s12666-015-0717-3.
2
Natrayan, L., S. Kaliappan, S. Chinnasamy Subramanian, Pravin P. Patil, S. D. Sekar, Y. Sesha Rao, and Melkamu Beyene Bayu. "Optimization of Activated Carbon Fiber Preparation from Hemp Fiber through Dipotassium Hydrogen Phosphate for Application of Thermal Storage System." Adsorption Science & Technology 2023 (April 21, 2023): 1–9. http://dx.doi.org/10.1155/2023/7228408.
Анотація:
With significant benefits over many other commercialised thermal storage methods, activated carbon fiber (ACF) is believed to be among the finest biosorbents for adsorbent purposes. If correctly made, it is an outstanding mesoporous lightweight material with micropores and, in most cases, no micropores. ACF’s higher bulk densities and great dynamic capacity demonstrate its value and are used in adsorbent technologies. The present study’s primary goal is to create active carbon fiber from organic hemp fiber. The following parameters were selected: (i) activating temperatures, (ii) activating timing, (iii) carbonization temperature, (iv) activating ingredient %ages, and (v) speed of activation temperature, all with four levels to achieve the goal. Taguchi optimization techniques were used to optimize the adsorbent characteristics. The current study used an L16 orthogonal array to accomplish that improvement. According to the previous Taguchi, the optimal conditions were 300°C combustions, insemination with 22.5% w / v K2HPO4 solution, and activating at 800°C for 3 hours at 20°C/min. The greatest contribution is 54.75%, followed by the rate of temperature activation at 23.35%, carbonated temperature at 10.14%, duration of stimulation at 8.82%, and H3PO4 concentrations at 2.94%. The results show that the activation temperature and rate of the temperature of activations are the essential elements in the current study’s accomplishment of the best adsorption capacities.
3
Akhmetzhanov, Talgat, Gulmira Danenova, and Andrey Rusanov. "Optimization of Low-Clinker Binder Production Technological Parameters." Key Engineering Materials 683 (February 2016): 243–49. http://dx.doi.org/10.4028/www.scientific.net/kem.683.243.
Анотація:
This paper presents an experimental investigation of the mechanochemical activation the low-clinker binder production systems on the basis of CaO and Ca(OH)2. It is shown that the effects of the mechanochemical interactions of the investigated components of low-clinked binders with the superplasticizer C-3 do not show a significant effect on the binders’- properties. The main influence is observed in the interaction of Portland cement and superplasticizer C-3. This study aimed to optimize the technological parameters of low-clinker binders’ production using different by-products. The expected economic effects of low - clinked binders is associated with the reduced amount of the clinker as one of the expensive components. Taking into account the cost of using the superplasticizer C-3 and various technological wastes the economic impact is expected to be 20-25% decrease of the total cost in the concrete production.
4
Zelentsov, Dmytro, and Shaptala Taras. "Models and methods of learning neural networks with differentiated activation functions." System technologies 6, no. 143 (November 13, 2023): 57–68. http://dx.doi.org/10.34185/1562-9945-6-143-2022-05.
Анотація:
Analysis of the literature made it clear that the problem associated with improving the performance and acceleration of ANN learning is quite actual, as ANNs are used every day in more and more industries. The concepts of finding more profitable activation functions have been outlined a lot, but changing their behavior as a result of learning is a fresh look at the problem. The aim of the study is to find new models of optimization tasks for the formulated prob-lem and effective methods for their implementation, which would improve the quality of ANN training, in particular by overcoming the problem of local minima. A studied of models and methods for training neural networks using an extended vector of varying parameters is conducted. The training problem is formulated as a continuous mul-tidimensional unconditional optimization problem. The extended vector of varying parameters implies that it includes some parameters of activation functions in addition to weight coeffi-cients. The introduction of additional varying parameters does not change the architecture of a neural network, but makes it impossible to use the back propagation method. A number of gradient methods have been used to solve optimization problems. Different formulations of optimization problems and methods for their solution have been investigated according to ac-curacy and efficiency criteria. The analysis of the results of numerical experiments allowed us to conclude that it is expedient to expand the vector of varying parameters in the tasks of training ANNs with con-tinuous and differentiated activation functions. Despite the increase in the dimensionality of the optimization problem, the efficiency of the new formulation is higher than the generalized one. According to the authors, this is due to the fact that a significant share of computational costs in the generalized formulation falls on attempts to leave the neighborhood of local min-ima, while increasing the dimensionality of the solution space allows this to be done with much lower costs.
5
Jiang, Li, Fei Ma, Ai Jun Gu, and Li Jun Zhang. "Production of Activated Carbon from Ligin: Optimization Using Response Surface Methodology." Advanced Materials Research 213 (February 2011): 427–31. http://dx.doi.org/10.4028/www.scientific.net/amr.213.427.
Анотація:
Activated carbon（AC）were prepared from lignin by chemical activation with sodium hydroxide（NaOH）. The influence of activation temperature，activation time and impregnation ration on the BET surface areas were investigated. Based on the central composite design (CCD) and response surface methodology(RSM)，the optimized technological parameters were as follows: temperature 751°C， time 57min and impregnation ration 2.06, BET surface areas was up to 1437.20 m2/g.The adequacy of the model equation for predicting the optimum response values was verified effectively by the validation.
6
Gao, Feng, Ying Xin Ge, Jia Zhao, and Hai Xia Yang. "Technology Optimization Study on Preparation of Activated Carbon from Rice Husk Cracking." Advanced Materials Research 197-198 (February 2011): 931–34. http://dx.doi.org/10.4028/www.scientific.net/amr.197-198.931.
Анотація:
Response surface methodology (RSM) was adopted to study the key parameters such as activation temperature, activation time, and active agent amount in order to increase activated carbon iodine adsorption value from rice husk. A second order quadratic equation was established and the applicability of model and interaction involved factors on predicting the iodine adsorption value was verified. The results indicated that the effect on the iodine adsorption value was as follows: activation temperature, activation ratio, activation time. The optimal levels for achieving the highest iodine adsorption value were obtained, including activation temperature of 550°C, activation time of 48min and activation ratio of 1.25. The iodine adsorption value reached 1464.793mg/g under optimized conditions. Iodine adsorption value was conducted under the optimum condition and the results showed the average relative error 0.58%, it proved that the models fitted well, the experimental data and the model were feasible.
7
Zhao, W., M. Fan, H. Gao, and H. Wang. "Central composite design approach towards optimization of super activated carbons from bamboo for hydrogen storage." RSC Advances 6, no. 52 (2016): 46977–83. http://dx.doi.org/10.1039/c6ra06326h.
Анотація:
Super activated carbons were developed from moso bamboo and central composite design was used to determine optimum responses by investigating the influence of activation parameters, weight ratio of KOH/precursor (W) and activation temperature (T).
8
Chen, Liqing, Wanjun Li, Yang Yang, and Wei Miao. "Evaluation and optimization of vehicle pedal comfort based on biomechanics." Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering 234, no. 5 (September 27, 2019): 1402–12. http://dx.doi.org/10.1177/0954407019878355.
Анотація:
Existing research on the manipulation comfort of the cab pedal generally focuses on the completion of the pedal movement when a vehicle is at rest, with certain data collected for analysis. This paper, by taking passenger vehicles in China as the study object and in view of the actual road conditions in China and the Chinese body size, attempts to solve the problem of muscle redundancy through the maximum/minimum optimization model of muscle activation. The road test was carried out on a typical pavement in a Chinese city. The parameters of pedal stroke, pedal force, and typical Electromyography signal (EMG) signal of drivers’ lower limbs during driving were obtained, from which muscle activation degree was calculated. The obtained experimental data were used as external driving one to simulate and analyze the pedal comfort under the layout of different human percentile and different pedal parameters in an aim to obtain the optimal value. The results indicate that the difference in pedal strokes, pedal preload, pedal resistance coefficients, seat heights, and H-point distances can have a noticeable effect on muscle activation. Taking a 95th-percentile accelerator pedal as an example, with the optimal values of each parameter selected (pedal preload: 8.2 N, pedal resistance coefficient: 2.55, seat height: 0.45 m and H-point distance: 0.86 m), as the pedal strokes increase, muscle activation shows a trend of increase after initial decrease. In the common stroke of a pedal after optimization, the degree of muscle activation is significantly lower than that before optimization, indicating a decrease in muscle fatigue.
9
Chen, Guo, Kun Xiong, Jinhui Peng, and Jin Chen. "Optimization of combined mechanical activation-roasting parameters of titania slag using response surface methodology." Advanced Powder Technology 21, no. 3 (May 2010): 331–35. http://dx.doi.org/10.1016/j.apt.2009.12.017.
10
Rožić, Ljiljana, Tatjana Novaković, and Srđan Petrović. "Modeling and optimization process parameters of acid activation of bentonite by response surface methodology." Applied Clay Science 48, no. 1-2 (March 2010): 154–58. http://dx.doi.org/10.1016/j.clay.2009.11.043.
Дисертації з теми "Activation parameters optimization":
1
Lopes, Leal Junior Marcos. "Méthode de conception et de dimensionnement en fatigue d'actionneurs à base d'Alliage à Mémoire de Forme pour des applications automobiles." Electronic Thesis or Diss., École nationale d'ingénieurs de Brest, 2024. http://www.theses.fr/2024ENIB0001.
Анотація:
Dans le contexte actuel de l’industrie automobile, de nombreux actionneurs sont indispensables, ce qui nécessite des solutions optimisées. Les actionneurs en Alliage à Mémoire de Forme (AMF) sont bien adaptés à cette fin. Cependant, la mise en œuvre de cette technologie dans le secteur automobile se heurte à des difficultés liées à la complexité du comportement et au manque d’outils de conception. Cette thèse vise à établir une approche multidisciplinaire pour concevoir des actionneurs SMA répondant aux exigences de l’industrie automobile. La méthode comprend trois parties principales : caractériser le comportement thermomécanique et électrique des fils NiTi, proposer un modèle numérique basé sur des expériences pour simuler le comportement des actionneurs SMA sous activation électrique via l’effet Joule, et déterminer le comportement à la fatigue pour estimer la durée de vie et l’impact de la dégradation sur les performances. Enfin, une méthode de conception validée pour les actionneurs à base de fils SMA est présentéeIn the current automotive industry context, numerous actuators are essential, necessitating optimized solutions. Shape memory alloy (SMA) actuators are well-suited for this purpose. However, implementing this technology in the automotive sector faces challenges due to complex behavior and a lack of design tools. This thesis aims to establish a multidisciplinary approach to designing SMA actuators to meet automotive industry requirements. The method comprises three main parts: characterizing NiTi wires’ thermomechanical and electrical behavior, proposing a numerical model based on experiments to simulate SMA actuator behavior under electrical activation via the Joule effect, and determining fatigue behavior for estimating lifespan and degradation impact on performance. Finally, a validated design method for SMA wire-based actuators is presented
2
Aldemir, Basak. "Parameter Optimization Of Chemically Activated Mortars Containing High Volumes Of Pozzolan By Statistical Design And Analysis Of Experiments." Master's thesis, METU, 2006. http://etd.lib.metu.edu.tr/upload/12607106/index.pdf.
Анотація:
ABSTRACT
PARAMETER OPTIMIZATION OF CHEMICALLY ACTIVATED MORTARS CONTAINING HIGH VOLUMES OF POZZOLAN BY STATISTICAL DESIGN AND ANALYSIS OF EXPERIMENTS
Aldemir, BaSak
M.S., Department of Industrial Engineering
Supervisor: Prof. Dr. Ömer Saatç
ioglu Co-Supervisor: Assoc. Prof. Dr. Lutfullah Turanli January 2006, 167 pages This thesis illustrates parameter optimization of early and late compressive strengths of chemically activated mortars containing high volumes of pozzolan by statistical design and analysis of experiments. Four dominant parameters in chemical activation of natural pozzolans are chosen for the research, which are natural pozzolan replacement, amount of pozzolan passing 45 &
#956
m sieve, activator dosage and activator type. Response surface methodology has been employed in statistical design and analysis of experiments. Based on various second-order response surface designs
experimental data has been collected, best regression models have been chosen and optimized. In addition to the optimization of early and late strength responses separately, simultaneous optimization of compressive strength with several other responses such as cost, and standard deviation estimate has also been performed. Research highlight is the uniqueness of the statistical optimization approach to chemical activation of natural pozzolans.
3
Kanneganti, Aswini. "Optimization of reconstruction parameters in brain activation studies." 2008. http://hdl.handle.net/10106/1871.
Частини книг з теми "Activation parameters optimization":
1
Law, D. W., C. Gunasekara, and S. Setunge. "Use of Brown Coal Ash as a Replacement of Cement in Concrete Masonry Bricks." In Lecture Notes in Civil Engineering, 23–25. Singapore: Springer Nature Singapore, 2023. http://dx.doi.org/10.1007/978-981-99-3330-3_4.
Анотація:
AbstractPortland cement production is not regarded as environmentally friendly, because of its associated high carbon emissions, which are responsible for 5% of global emissions. An alternative is to substitute fly ash for Portland cement. Australia has an abundance of brown coal fly ash, as it is the main source of primary energy in the State of Victoria. Currently, the majority of this material is stored in landfills and currently there is no commercial use for it in the cement industry because brown coal fly ash cannot be used as a direct replacement material for Portland cement due to the high sulfur and calcium content and low aluminosilicate content. However, the potential exists to use brown coal fly ash as a geopolymeric material, but there remains a significant amount of research needed to be conducted. One possible application is the production of geopolymer concrete bricks. A research project was undertaken to investigate the use of brown coal fly ash from Latrobe Valley power stations in the manufacture of geopolymer masonry bricks. The research developed a detailed understanding of the fundamental chemistry behind the activation of the brown coal fly ash and the reaction mechanisms involved to enable the development of brown coal fly ash geopolymer concrete bricks. The research identified suitable manufacturing techniques to investigate relationships between compressive strength and processing parameters and to understand the reaction kinetics and microstructural developments. The first phase of the research determined the physical, chemical, and mineralogical properties of the Loy Yang and Yallourn fly ash samples to produce a 100% fly ash-based geopolymer mortar. Optimization of the Loy Yang and Yallourn geopolymer mortars was conducted to identify the chemical properties that were influential in the production of satisfactory geopolymer strength. The Loy Yang mortars were able to produce characteristic compressive strengths acceptable in load-bearing bricks (15 MPa), whereas the Yallourn mortars produced characteristic compressive strengths only acceptable as non-load-bearing bricks (5 MPa). The second phase of the research transposed the optimal geopolymer mortar mix designs into optimal geopolymer concrete mix designs while merging the mix design with the optimal Adbri Masonry (commercial partner) concrete brick mix design. The reference mix designs allowed for optimization of both the Loy Yang and Yallourn geopolymer concrete mix designs, with the Loy Yang mix requiring increased water content because the original mix design was deemed to be too dry. The key factors that influenced the compressive strength of the geopolymer mortars and concrete were identified. The amorphous content was considered a vital aspect during the initial reaction process of the fly ash geopolymers. The amount of unburnt carbon content contained in the fly ash can hinder the reactive process, and ultimately, the compressive strength because unburnt carbon can absorb the activating solution, thus reducing the particle to liquid interaction ratio in conjunction with lowering workability. Also, fly ash with a higher surface area showed lower flowability than fly ash with a smaller surface area. It was identified that higher quantity of fly ash particles <45 microns increased reactivity whereas primarily angular-shaped fly ash suffered from reduced workability. The optimal range of workability lay between the 110–150 mm slump, which corresponded with higher strength displayed for each respective precursor fly ash. Higher quantities of aluminum incorporated into the silicate matrix during the reaction process led to improved compressive strengths, illustrated by the formation of reactive aluminosilicate bonds in the range of 800–1000 cm–1 after geopolymerization, which is evidence of a high degree of reaction. In addition, a more negative fly ash zeta potential of the ash was identified as improving the initial deprotonation and overall reactivity of the geopolymer, whereas a less negative zeta potential of the mortar led to increased agglomeration and improved gel development. Following geopolymerization, increases in the quantity of quartz and decreases in moganite correlated with improved compressive strength of the geopolymers. Overall, Loy Yang geopolymers performed better, primarily due to the higher aluminosilicate content than its Yallourn counterpart. The final step was to transition the optimal geopolymer concrete mix designs to producing commercially acceptable bricks. The results showed that the structural integrity of the specimens was reduced in larger batches, indicating that reactivity was reduced, as was compressive strength. It was identified that there was a relationship between heat transfer, curing regimen and structural integrity in a large-volume geopolymer brick application. Geopolymer bricks were successfully produced from the Loy Yang fly ash, which achieved 15 MPa, suitable for application as a structural brick. Further research is required to understand the relationship between the properties of the fly ash, mixing parameters, curing procedures and the overall process of brown coal geopolymer concrete brick application. In particular, optimizing the production process with regard to reducing the curing temperature to ≤80 °C from the current 120 °C and the use of a one-part solid activator to replace the current liquid activator combination of sodium hydroxide and sodium silicate.
2
Aburasain, R. Y., E. A. Edirisinghe, and M. Y. Zamim. "A Coarse-to-Fine Multi-class Object Detection in Drone Images Using Convolutional Neural Networks." In Digital Interaction and Machine Intelligence, 12–33. Cham: Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-031-11432-8_2.
Анотація:
AbstractMulti-class object detection has a rapid evolution in the last few years with the rise of deep Convolutional Neural Networks (CNNs) learning based, in particular. However, the success approaches are based on high resolution ground level images and extremely large volume of data as in COCO and VOC datasets. On the other hand, the availability of the drones has been increased in the last few years and hence several new applications have been established. One of such is understanding drone footage by analysing, detecting, recognizing different objects in the covered area. In this study conducted, a collection of large images captured by a drone flying at a fixed altitude in a desert area located within the United Arab Emirates (UAE) is given and it is utilised for training and evaluating the CNN networks to be investigated. Three state-of-the-art CNN architectures, namely SSD-500 with VGGNet-16 meta-architecture, SSD-500 with ResNet meta-architecture and YOLO-V3 with Darknet-53 are optimally configured, re-trained, tested and evaluated for the detection of three different classes of objects in the captured footage, namely, palm trees, group-of-animals/cattle and animal sheds in farms. Our preliminary experiments revealed that YOLO-V3 outperformed SSD-500 with VGGNet-16 by a large margin and has a considerable improvement as compared to using SSD-500 with ResNet. Therefore, it has been selected for further investigation, aiming to propose an efficient coarse-to-fine object detection model for multi-class object detection in drone images. To this end, the impact of changing the activation function of the hidden units and the pooling type in the pooling layer has been investigated in detail. In addition, the impact of tuning the learning rate and the selection of the most effective optimization method for general hyper-parameters tuning is also investigated. The result demonstrated that the multi-class object detector developed has precision of 0.99, a recall of 0.94 and an F-score of 0.96, proving the efficiency of the multi-class object detection network developed.
3
Duy Sang, Nguyen. "The Genetic Algorithm and its Application in Calculating the Kinetic Parameters of the Thermoluminescence Curve." In Genetic Algorithms - Theory, Design and Programming. IntechOpen, 2024. http://dx.doi.org/10.5772/intechopen.112198.
Анотація:
This chapter explores the use of genetic algorithms as a tool for calculating the kinetic parameters of the thermoluminescence curve. Genetic algorithm is a search algorithm inspired by the process of natural selection, and it has proven to be effective in solving optimization problems in various fields. Author used genetic algorithm to estimate the activation energy and frequency factor of the thermoluminescence curve, which are important parameters in determining the dosimetric properties of materials. The results showed that genetic algorithm could accurately estimate the kinetic parameters of the thermoluminescence curve with high precision and efficiency compared to conventional methods. This approach can also handle noisy data and reduce the impact of outliers on the estimation process. Furthermore, author demonstrated that genetic algorithm can be generalized to different types of the thermoluminescence curves, such as those generated by different materials or under different experimental conditions. The proposed method is fast, accurate, and robust, making it useful for researchers in the field of dosimetry who require precise estimations of these parameters.
4
Oliveira, Ádamo Henrique Rocha de, Yrlles Araujo Moraes, Rayssa Pereira Moraes Rego Sobrinho, Jorleanderson Moraes Maia, and Marcos Silva Chaves. "Automatic parameterization of neural networks using evolutionary algorithms." In Multidisciplinary Perspectives: Integrating Knowledge. Seven Editora, 2024. http://dx.doi.org/10.56238/sevened2024.007-089.
Анотація:
Artificial Intelligence consists of an area where methods or systems are developed that act intelligently, approaching human behavior, in situations involving problem solving, acquisition and representation of knowledge, pattern recognition, etc. Within this context, a type of computational model that has gained prominence are the Artificial Neural Networks (ANNs), which are formed by basic blocks inspired by the biological neuron. An ANN has the ability to act in various applications, such as universal approximation of functions, process control, pattern recognition and classification, and data grouping. To meet a wide range of applications, an ANN requires the determination of a series of parameters, among them: topology, number of layers, number of neurons, activation function, training method, etc. In other words, the design of an ANN with the most appropriate configuration for each type of problem requires a series of choices, preliminary tests and experience from the designer. However, in order to avoid such choices being made empirically, it is possible to treat this parameterization as an optimization problem, allowing its resolution through the use of evolutionary algorithms, which are optimization tools developed to simulate several natural evolutionary processes. In this work, the Genetic Algorithm and Differential Evolution with binary coding were applied to automatically parameterize single-layer hidden neural networks applied in the modeling of a buck converter and in the prediction of compressive strength of self-compacting concrete (SCC) with the addition of fibers. The neural networks used were trained with the Extreme Learning Machine algorithm and the results of the simulations show that the Genetic Algorithm was the technique that presented the best performance when parameterizing the network in the modeling process of the buck converter, while the Differential Evolution combined with the binary coding GVP was the best strategy to parameterize the neural network in the process of predicting compressive strength of SCC.
5
Honcharova, Olena. "EFFICIENCY OF COMPLEX TECHNOLOGICAL SOLUTIONS FOR GROWING FISH TO INCREASE RESISTANCE TO THE INFLUENCE OF ABIOTIC AND BIOTIC FACTORS UNDER THE INFLUENCE OF CLIMATE TRANSFORMATIONS." In Traditional and innovative approaches to scientific research: theory, methodology, practice. Publishing House “Baltija Publishing”, 2022. http://dx.doi.org/10.30525/978-9934-26-241-8-10.
Анотація:
The purpose. To substantiate the effectiveness of using the method of rearing fish at the early stages of ontogenesis before stocking water bodies using a scientific-experimental method. Methodology of the study is based on the functional status of the fish organism. The experimental part of the work was performed on the basis of the Department of Aquatic Bioresources and Aquaculture of the Kherson State Agrarian and Economic University (Ukraine), laboratory of the "Kherson Production and Experimental Plant for Breeding of the Ordinary Fish" State Institution and "Aquaculture Perspectives" Scientific Research Laboratory, "Scientific Research Laboratory of Physiological and Biochemical Research of S. Pentelyuk", Scientific Research Laboratory on ecological and chemical analysis and water monitoring of Public higher education institution Kherson State Agrarian and Economic University (KSAEU, Ukraine). For studies of the main parameters that were studied, standard methods were used [1–4]. The blood from heart and tail vein was obtained using Pasteur needle and heparinized syringe. For biochemical studies, apart from blood plasma, the muscle part was also collected. They were also frozen in ThermoMix and stored for further research. Using a digital camera and Micromed microscope. Muscle protein content was determined by the Lowry method. Biochemical studies of biological material were performed using ULAB 102 spectrophotometer. Catalase activity was determined by 219Chapter «Agricultural sciences»the spectrophotometric method, based on the ability of hydrogen peroxide to form a stable color with the reagent. Biochemical analysis of samples to study the level of activity of alanine aminotransferase (ALT), aspartate aminotransferase (AST), total protein content, and glucose concentration was carried out in the laboratory of the Department of Aquatic Bioresources and Aquaculture of KSAEU on a Humalyzer 3000 analyzer using standardized Human GmbH kits. Against the background of the outlined parameters, observations of the ethology of hydrobionts were carried out during the day, with the recording of certain details as necessary. All manipulations of the object of scientific research were carried out in accordance with the rules of the "European Convention for the Protection of Vertebrate Animals Used for Experimental and Other Scientific Purposes" (Strasbourg, 1986). Results. The results of the research work on the comprehensive study of the leading parameters of the growth efficiency with the use of optimization elements are presented. Positive results were obtained on the speed of development of young carp in polyculture with carp against the background of activation of metabolic processes in the body. The implementation of technological elements for optimizing the growth of hydrobionts in the early stages of ontogenesis helps to increase the viability of young and ensures the efficiency of stocking reservoirs with such young carp. The proposed biologically active substances in the composition of the ration reasonably provide the functionality of a micro-additive against the background of elements of resource-saving technology in the scheme of a modular fish farming system. Practical implications. The method of growing carp presented in the article before stocking with fish helps to increase growth parameters, increase resistance to the influence of abiotic and biotic factors. Value/originality. The use of resource-saving elements in the technology of growing fish. The uniqueness provides innovative solutions for optimizing the technology of growing carp and silver carp.
6
Dağlarli, Evren. "Explainable Artificial Intelligence (xAI) Approaches and Deep Meta-Learning Models." In Advances and Applications in Deep Learning. IntechOpen, 2020. http://dx.doi.org/10.5772/intechopen.92172.
Анотація:
The explainable artificial intelligence (xAI) is one of the interesting issues that has emerged recently. Many researchers are trying to deal with the subject with different dimensions and interesting results that have come out. However, we are still at the beginning of the way to understand these types of models. The forthcoming years are expected to be years in which the openness of deep learning models is discussed. In classical artificial intelligence approaches, we frequently encounter deep learning methods available today. These deep learning methods can yield highly effective results according to the data set size, data set quality, the methods used in feature extraction, the hyper parameter set used in deep learning models, the activation functions, and the optimization algorithms. However, there are important shortcomings that current deep learning models are currently inadequate. These artificial neural network-based models are black box models that generalize the data transmitted to it and learn from the data. Therefore, the relational link between input and output is not observable. This is an important open point in artificial neural networks and deep learning models. For these reasons, it is necessary to make serious efforts on the explainability and interpretability of black box models.
Тези доповідей конференцій з теми "Activation parameters optimization":
1
Ali, Taalimi, and Fatemizadeh Emad. "fMRI activation detection by obtaining BOLD response of extracted balloon parameters with Particle Swarm Optimization." In IEEE EUROCON 2009 (EUROCON). IEEE, 2009. http://dx.doi.org/10.1109/eurcon.2009.5167829.
2
Huang, Cunjun, Pradip N. Sheth, and Kevin P. Granata. "Multibody Dynamics Integrated With Muscle Models and Space-Time Constraints for Optimization of Lifting Movements." In ASME 2005 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference. ASMEDC, 2005. http://dx.doi.org/10.1115/detc2005-85385.
Анотація:
A multibody dynamics model integrated with space-time constraints based optimization is presented in this paper for generating optimal trajectories of human lifting movements. “Space-time constraints” is a two-point boundary value dynamic optimization technique developed for animation of computer graphics characters and has a significant potential for biomechanics and other mechanical movement based dynamic optimization problems. Optimization results demonstrate the ability to consider different preferences for minimizing the loading of specific joints such as an ankle, or a knee, or a shoulder during the lifting motion and the resulting lifting trajectories are shown to be different. Lumped muscle models to generate the joint torques are incorporated at five joints to model the actuation effects of the muscular system during the dynamic movement. The dynamic optimization is then based on the muscle activation parameters instead of the traditionally used joint torques. The muscle activation model optimization is shown to correlate better with the actual motion tests conducted by the VICON video capture and test data analysis system.
3
Kuo, Peter S., and Charles C. Blatchley. "Turbine Blade Tip-Shroud Wear Characteristics Monitored by Surface Layer Activation." In ASME 1989 International Gas Turbine and Aeroengine Congress and Exposition. American Society of Mechanical Engineers, 1989. http://dx.doi.org/10.1115/89-gt-300.
Анотація:
An on-line investigation into turbine shroud gap control and optimization was recently conducted at Textron Lycoming Division. The Surface Layer Activation (SLA) technique was used (for the first time in turbine blades) to determine shroud wear rates during operation and to detect related blade motions in the shrouded assembly. Surface losses from shroud tip faces, which were activated by a particle accelerator, were detected by gamma spectrometry. Engine testing deliberately used “tight” and “loose” shroud assemblies to evaluate the effect of total gap on wear. Tests were run at speed ranges known to include blade-disc system modes, with over 30 hours of running time for each shroud configuration. On-line wear monitoring and total accumulated wear for each blade both indicated a faster wear rate in the “loose” shroud wheel than in the “tight” assembly, with most wear occurring in the high engine speed range. The experimental measurements provide a further understanding of design parameters for the optimization of turbine blade tip shrouds.
4
Wang, Shuang, and John C. Brigham. "An Adjoint Based Approach for Optimal Design of Morphing SMP." In ASME 2013 Conference on Smart Materials, Adaptive Structures and Intelligent Systems. American Society of Mechanical Engineers, 2013. http://dx.doi.org/10.1115/smasis2013-3250.
Анотація:
This work presents a strategy to identify the optimal localized activation and actuation for a morphing thermally activated SMP structure or structural component to obtain a targeted shape change or set of shape features, subject to design objectives such as minimal total required energy and time. This strategy combines numerical representations of the SMP structure’s thermo-mechanical behavior subject to activation and actuation with gradient-based nonlinear optimization methods to solve the morphing inverse problem that includes minimizing cost functions which address thermal and mechanical energy, morphing time, and damage. In particular, the optimization strategy utilizes the adjoint method to efficiently compute the gradient of the objective functional(s) with respect to the design parameters for this coupled thermo-mechanical problem.
5
Wang, Xiaowei, and YeongAe Heo. "Neural Network Optimization for Lifetime Structural Adaptation to Evolving Natural Events." In ASME 2021 40th International Conference on Ocean, Offshore and Arctic Engineering. American Society of Mechanical Engineers, 2021. http://dx.doi.org/10.1115/omae2021-62401.
Анотація:
Abstract Recent advances in data analytics, numerical modeling, and structural health monitoring (SHM) boost the application of machine learning methods in the field of structural engineering. Among them, the multi-layer neural network (MLNN) is one of the most popular ones. However, mathematical details of MLNN have yet to be well understood for structural problems. This study aims to identify optimal MLNN parameters for regression modeling of structural response estimates. SHM data-validated finite element models considering stochastic uncertainties in the natural events and structural properties are used to prepare a large dataset for regression modeling. The efficacy and accuracy of regression modeling are optimized by extensive sensitivity analyses for key MLNN parameters (e.g., numbers of hidden layers and neurons, activation functions and learning rates) via a k-fold cross-validation process. The optimized regression modeling is incorporated into a conceptual smart framework for lifetime structural performance assessment adapting to evolving natural events. The presented optimization process and smart framework is applicable to marine and offshore structures by characterizing the offshore hazards and structural responses.
6
Kinser, Robert Eric, Deborah A. Furey, and Othon K. Rediniotis. "Calibration Neural Network for a Novel Omni-Directional Velocity Probe: PROBENET." In ASME 1996 International Mechanical Engineering Congress and Exposition. American Society of Mechanical Engineers, 1996. http://dx.doi.org/10.1115/imece1996-0948.
Анотація:
Abstract In this paper, the development of an adaptive neural network for the calibration of novel velocity measurement instrumentation is presented. The backpropagation-based algorithm, PROBENET, was initially developed for the calibration of multi-hole pressure probes, although at this point it has evolved to a generic-application code. The code offers distinct advantages over commercial packages (such as the Matlab Neural Network Toolkit, Demuth and Beale, 1994) in terms of maximum allowable network size, training convergence rates, flexibility in network architecture design and network optimization capabilities. PROBENET incorporates multiple activation functions per layer, as well as heuristics-based procedures for network-architecture optimization. Techniques for local minima avoidance and convergence rate improvement, incorporated into the algorithm, are: momentum, variable learning rate and Levenberg-Marquardt optimization methods. The present study documents the performance of PROBENET when applied to the calibration of a novel 18-hole probe developed to overcome the flow angularity measurement limitations of traditional 5- and 7-hole probes. The study compared the performance of two types of network architectures: single activation function per layer and multiple activation functions per layer, and showed that the latter consistently produced a better solution in terms of convergence rate and accuracy. The use of multi-function layers and network optimization resulted in very good prediction accuracy of the flow parameters.
7
Zhang, Yang, Yan Qiao, Fujian Zhou, Dengfeng Ren, Yuzhang Liu, and Jie Bai. "Study On Shear & Tensile Activation Of Hydraulic Fracturing In Natural Fractured Reservoirs." In SPE/IATMI Asia Pacific Oil & Gas Conference and Exhibition. SPE, 2023. http://dx.doi.org/10.2118/215378-ms.
Анотація:
Abstract The most fundamental purpose of reservoir stimulation is to maximize stimulation volume. For reservoirs developed with natural fractures, the maximization of fracture activation (tensile & shear activation) area should be pursued. Many scholars have studied the mechanical conditions of natural fractures activation, and used stress shadow to optimize cluster spacing. However, there is a lack of in-depth research on fracture propagation law, relationship between fracture activation and stress shadow, and factors affecting natural fracture activation. In this paper, numerical simulation methods are used to establish a true three-dimensional hydraulic fracturing model for reservoirs with natural fractures, and the quantitative evaluation indicators of stress shadow area and activation degree of natural fractures are formed. By studying the effects of different natural fracture properties, mechanical and engineering parameters on fracture propagation, stress shadow and natural fracture activation, the main controlling factors affecting fracture propagation and turning, the relationship between fracture activation and stress shadow, and changing rules of fracture activation are clarified. Finally, the fracture turning and accuracy of model are verified by microseismic monitoring data. Studies have shown that large-scale, high-density natural fractures, high net pressure, low in-situ stress difference, and moderate stress-fracture angle (30°~60°) can easily divert the propagation of hydraulic fractures instead of expanding in the horizontal maximum principal stress (Shmax) direction. Fracture tensile activation has a strong positive correlation with stress shadow area, that is, tensile activation leads to the increase of stress shadow area, while fracture shear activation has almost no correlation. Fracture tensile & shear activation area is in a competitive relationship, and shear fractures are dominant when the stressfracture angle is 45-60°, the in-situ stress difference and pore pressure are high. The main controlling factors affecting activated fractures total area are geological factors and mechanical parameters, which are positively correlated with natural fracture density, dip angle, in-situ stress difference, pumping volume, pore pressure, negatively correlated with friction angle and cohesion, and have optimal values with fracture size (60m), stress-fracture angle (45°) and net pressure. Micro-seismic data show that when natural fractures density is high, the hydraulic fractures propagation direction deflects and doesn't expand in the horizontal maximum principal stress direction, which further verifies the accuracy of the method and conclusions. There is no obvious correlation between natural fracture activation area and stress shadow. It is not applicable to optimize cluster spacing of reservoirs with natural fractures only by stress shadow. The natural fracture activation area should be used as an indicator for measure optimization. In addition, this paper provides a reference for the selection of reservoir stimulation horizons, the formulation of working systems, and the realization of large hydraulic fracture diversion.
8
Ku¨hnel, Janpeter, and Reza S. Abhari. "Part Load Behavior Optimization of Hybrid Coal and Gas Fired Combined Cycles Including Deactivation of Components." In ASME Turbo Expo 2002: Power for Land, Sea, and Air. ASMEDC, 2002. http://dx.doi.org/10.1115/gt2002-30136.
Анотація:
This paper presents a methodology to optimize the part load behavior of complex power plant cycles. As free optimization parameters the traditional continuous control parameter and the activation/deactivation of defined plant components are considered resulting in a mixed integer non-linear programming problems (MINLP). The procedure starts with a continuous process on either side of the non-linearity in part load, while refining the steps as it approaches the discontinuity. It is shown that good convergence around the non-linearity can be found with the present scheme. For part load operation a number of continuous and binary free optimization parameters are available creating a challenging optimization problem. The developed procedure is applied to a conventional steam cycle power plant, which is parallel repowered with a modern gas turbine. The resulting power plant layout is a hybrid coal and gas fired combined cycle. As objective function the maximized overall thermal efficiency and the minimized fuel costs are two examples chosen. Investigating the minimized fuel costs as the objective function the optimized operation strategy is found to be an unique function of the fuel price ratio between coal and gas for the chosen layout. Finally we show, that the operation strategy can be notably improved by considering the deactivation of cycle components for minimizing the fuel costs and for maximizing the cycle efficiency. For example the cycle efficiency can be improved up to 2% by deactivating the high pressure feed water preheating. The fuel costs are reduced by 20% for a particular load point by deactivating the gas turbine.
9
Wang, Zhuo, Pengwei Liu, Zhen Hu, and Lei Chen. "Simulation-Based Process Optimization of Metallic Additive Manufacturing Under Uncertainty." In ASME 2019 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference. American Society of Mechanical Engineers, 2019. http://dx.doi.org/10.1115/detc2019-97492.
Анотація:
Abstract The presence of various uncertainty sources in metal-based additive manufacturing (AM) process prevents producing AM products with consistently high quality. Using electron beam melting (EBM) of Ti-6A1-4V as an example, this paper presents a data-driven framework for process parameters optimization using physics-informed computer simulation models. The goal is to identify a robust manufacturing condition that allows us to constantly obtain equiaxed materials microstructures under uncertainty. To overcome the computational challenge in the robust design optimization under uncertainty, a two-level data-driven surrogate model is constructed based on the simulation data of a validated high-fidelity multi-physics AM simulation model. The robust design result, indicating a combination of low preheating temperature, low beam power and intermediate scanning speed, was acquired enabling the repetitive production of equiaxed-structure products as demonstrated by physics-based simulations. Global sensitivity analysis at the optimal design point indicates that among the studied six noise factors, specific heat capacity and grain growth activation energy have largest impact on the microstructure variation.
10
Yusuf, N., C. Cavalleri, W. A. Tolioe, L. H. How, S. H. Daud, D. Johare, M. S. Hendrawati, and A. G. A. Halim. "Optimization of Pulsed Neutron Logging for Real-Time Water Management Through Oxygen Activation and Water Flow Logs." In International Petroleum Technology Conference. IPTC, 2024. http://dx.doi.org/10.2523/iptc-23368-ms.
Анотація:
Abstract Pulsed neutron logging (PNL) is often part of production enhancement strategies to evaluate remaining potential and water flow, guiding intervention plans and de-risking water shutoff opportunities. The qualitative assessment of the oxygen activation (OA) curves response can accurately pinpoint zones potentially affected by water flow and can be used on real-time to optimize the selection of representative depths for water flow logging (WFL) station survey. Both OA and WFL operate under the assumption that oxygen nuclei represent the borehole water phase. The OA continuous measurement of the oxygen activation is made during a window when the burst is off and only the activation background from the formation and the borehole is recorded. Depending on the toolstring configuration, the OA curves are sensitive to up or down flow of water, while the signal amplitude varies with velocity and water holdup. Regions where the OA curve amplitude and separations are more pronounced indicate possible crossflow or movement where the water velocity is faster than the tool. The OA curves are recorded during standard depth logging passes performed for petrophysical parameters and saturation monitoring, without the need of separate passes; these curves help in highlighting changes in the borehole conditions, detecting unexpected flow, and indicating where to do WFL stations. In some logging programs where WFL stations were not planned, the real-time findings from the OA curves have enabled the extension of the log data acquisition to further investigate potential water movement with WFL mode, confirming the presence of fluid movement or recirculation at the wellbore. A good qualitative match between the OA curves behavior and the WFL stations’ result is observed in most cases. As indicated by the physics of the measurement, the pulsed neutron tool can only be configured to detect one flow direction per descent; reconfiguration for inverted positioning of transmitter and detectors is required for sensitivity to flow in the opposite direction. However, in a recent example, the intelligent combination of the pulsed neutron and gamma ray sensors made it possible to detect flow in both up and down directions in one single pass. The examples in this paper demonstrate the usage of the OA continuous logs and WFL stations where pulsed neutron logging (PNL) have been run in a few wells in Malaysia. These logs have been recorded in wells with variation/complex completions ranging from single completion with gravel pack assembly to openhole completions with screens. As demonstrated in these case studies, real-time evaluation of the pulsed neutron data and logging program optimization and updates are instrumental to enable a comprehensive interpretation, from petrophysical analysis to water management, facilitating fast, informed decision making. The novel OA curves from advanced PNL technology, complemented by other pulsed neutron borehole indicators and temperature profile, have been able to help indicate potential water movement in the borehole affecting the reservoir performance. This information successfully assisted the interpretation of remaining hydrocarbon potential and current fluid dynamics at the wellbore.