Добірка наукової літератури з теми "620.179.1:004.032.26"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Зміст
Ознайомтеся зі списками актуальних статей, книг, дисертацій, тез та інших наукових джерел на тему "620.179.1:004.032.26".
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.
Дисертації з теми "620.179.1:004.032.26"
Авдєйонок, Ірина Ігорівна. "Фотонна інтегральна схема для систем з штучним інтелектом". Master's thesis, КПІ ім. Ігоря Сікорського, 2021. https://ela.kpi.ua/handle/123456789/41180.
Повний текст джерелаThe dissertation is devoted to the development of a photonic integrated circuit for a neural network. Integrated circuits are an integral part of modern technology. Most of the functional units can be replaced by a photonic component (diodes, waveguides, filters and amplifier) to create a photonic integrated circuit. Photonic integrated circuits have several advantages: they have a higher speed of processing and transmission of information, a larger bandwidth and less energy loss. The most common is the use of hybrid circuits, namely part of the elements of the integrated system is integrated by photonic elements. The first section is devoted to the study of modern development of neural networks. Hardware implementations of neurons and neural networks are considered. A patent search for neuronal modeling was also performed. The second section considers modern architectures of the photon integrated circuit. A new structure of the integrated circuit and its manufacturing technology were proposed. For this purpose, the structure of the lithographic installation was proposed and the technical task was formulated. The third section is devoted to the design of the lithographic system. Dimensional calculations, calculation of structure of optical system were carried out. After the design, the system was analyzed, namely the optimization of the calculated system, energy calculation, and aberration analysis. The fourth section examines the Hopfield neural network, its mathematical model. Based on which a program was developed to model the Hopfield network and calculate weights. The fifth section is devoted to experimental research. A prototype of a photonic integrated system was developed. Experiments were performed: the study of the waveguides of the system for their further implementation and the study of the current prototype. The sixth section is devoted to the development of a startup project.
Момот, Андрій Сергійович. "Удосконалення методу визначення характеристик дефектів багатошарових матеріалів за результатами активного теплового контролю". Doctoral thesis, Київ, 2020. https://ela.kpi.ua/handle/123456789/34952.
Повний текст джерелаГаврілов, Владислав Сергійович. "Система прогнозування музичних композицій методами машинного навчання". Master's thesis, КПІ ім. Ігоря Сікорського, 2021. https://ela.kpi.ua/handle/123456789/46611.
Повний текст джерелаMaster’s thesis explanatory note: 81 p., 35 fig., 20 tables, 1 appendixes, 10 sources. The object of the research is to create a computer tool that allows you to automatically generate realistic music compositions. In the course of the work an analysis of existing methods and approaches to solve this problem was carried out. Out of all analyzed were selected the most realistic results and can be implemented using available computing resources. The subject of the research is a neural network system that allows to generate new music based on submitted compositions, taking into account the duration of the sound of the notes and the pauses between them. The purpose of the work is to generate tunes of a certain genre and style for further use in amateur projects, where developers do not have the ability or finances to create their own or buy existing ones. Several compositions were generated for demonstration purposes. They allow you to evaluate the advantages and disadvantages of the method used. In the course of the work, existing solutions to this problem were analyzed, which allowed us to choose the best method and try to improve it.
Пелещак, Іван Романович. "Система розпізнавання мультиспектральних образів на основі осциляторних нейронних мереж". Diss., Національний університет «Львівська політехніка», 2021. https://ena.lpnu.ua/handle/ntb/56753.
Повний текст джерелаКатюха, Ігор Анатолійович. "Прогнозні моделі електричних навантажень розподільчих мереж в умовах невизначеності вихідної інформації". Thesis, Таврійський державний агротехнологічний університет, 2017. http://repository.kpi.kharkov.ua/handle/KhPI-Press/31033.
Повний текст джерелаThe thesis for getting scientific degree of the Candidate of technical science on the specialty 05.14.02 «Electric power stations, network and system» (141 Electrical energetics, electrical engineering and electromechanics). – Tavricheskiy State Agrotechnology University, Melitopol, Ukraine National Technical University «Kharkiv Polytechnic Institute» MES of Ukraine, Kharkiv, 2017. The dissertation devoted to solving actual scientific and technical problem of development of modern science and analytical tools forecast electricity consumption in the face of uncertainty, taking into account the possibility of information support automated systems of commercial accounting of electric power and features of individual consumers and aims to increase efficiency and save electricity. Improved method of fuzzy regression analysis to build long–term forecasting models of electric loads in distribution networks. Included balanced participation of two performance criteria fuzzy models: the degree of combination and degree of fuzziness when building predictive models. The method of correction term predictive models for short–term forecast. An approach to building the type of predictive models in any type of stress. Analytical contacted fuzzy indicators forecast accuracy Mean absolute percentage error. The technique was tested in the development of predictive models of electric load number of consumers with different types of load charts. The main results of the dissertation found practical application in the form of hardware and software to automate the process of long–term and operational forecasting electricity consumers of electrical loads that can integrate information into an automated accounting system of electricity, as well as operational management mode of distribution networks. VII As a result of the research on the theme of the thesis, the following scientific results were obtained: - the method for obtaining predictive models of electrical loads is improved, which is distinguished by constructing a fuzzy regression compatibility criterion based on the intersection of fuzzy numbers, which makes it possible to uncover the uncertainty of the output data and improve the quality of the prediction of electrical loads. - for the first time the method of unification of the type of forecasting models is proposed, which differs in the fact that in the daily schedule of electricity consumption allocated functional areas, with the separate use for them of fuzzy regression analysis, which allows you to get the kind of forecast models at all loads. - for the first time the method of increasing the adequacy of models obtained on the basis of fuzzy regression analysis, which differs from the parity considering the degree of compatibility and the degree of fuzzy description, which will make prediction of electrical loads more qualitative. - for the first time an analytical method for determining the efficiency of the forecast of electricity consumption in electric networks is determined, which allows to perform a comparative analysis of fuzzy regression models of the forecast with models obtained by other methods. The practical significance of the obtained results of work for the electric power industrylies in the developed method of forecasting electricity consumption based on fuzzy regression analysis, which includes the principles of constructing predictive models, algorithmic support, as well as software implemented in a convenient for integration in AMSCA form. The research results are implemented and confirmed by the relevant acts: - PE "Molokozavod-OLKOM" for the analysis of electricity consumption and operational control in order to reduce energy losses in the network of intra-electric power supply. VIII - in the educational process, the main results of the work are included in the relevant disciplines - "Practical engineering training" and "Engineering activities" in the specialty: 8.10010101 - Power engineering of agricultural production. - Azov REM OJSC "Zaporizhiaoblenergo" used a hardware and software complex for the process of long-term and short-term prediction of electrical loads and operational control of the modes of distribution networks. The basic scientific positions on the materials of the dissertation work are published in 15 printed works, including 9 articles in the scientific professional editions of Ukraine (5 in the publications included in the international science-computer bases, 1 ¬ in the edition with the index SCORUS), 6 in the materials of the conferences and workshops. Thesis consists of introduction, abstract, four sections, conclusions, list of used sources and applications. The total volume of the dissertation is 190 pages, among them: 18 figures in the text, 20 tables in the text, the list of used sources contains 115 titles in 12 pages, applications in 19 pages.
Катюха, Ігор Анатолійович. "Прогнозні моделі електричних навантажень розподільчих мереж в умовах невизначеності вихідної інформації". Thesis, НТУ "ХПІ", 2017. http://repository.kpi.kharkov.ua/handle/KhPI-Press/31032.
Повний текст джерелаDissertation for scientific degree of candidate of technical sciences, specialty 05.14.02 – electric power stations, networks and systems. – Tavricheskiy State Agrotechnology University, Melitopol, 2017. The dissertation devoted to solving actual scientific and technical problem of development of modern science and analytical tools forecast electricity consumption in the face of uncertainty, taking into account the possibility of information support automated systems of commercial accounting of electric power and features of individual consumers and aims to increase efficiency and save electricity. Improved method of fuzzy regression analysis to build long–term forecasting models of electric loads in distribution networks. Included balanced participation of two performance criteria fuzzy models: the degree of combination and degree of fuzziness when building predictive models. The method of correction term predictive models for short–term forecast. An approach to building the type of predictive models in any type of stress. Analytical contacted fuzzy indicators forecast accuracy Mean absolute percentage error. The technique was tested in the development of predictive models of electric load number of consumers with different types of load charts. The main results of the dissertation found practical application in the form of hardware and software to automate the process of long–term and operational forecasting electricity consumers of electrical loads that can integrate information into an automated accounting system of electricity, as well as operational management mode of distribution networks.
Коржов, Ігор Михайлович. "Пристрій контролю та діагностування стану промислових динамічних об’єктів". Thesis, Національний технічний університет "Харківський політехнічний інститут", 2019. http://repository.kpi.kharkov.ua/handle/KhPI-Press/43360.
Повний текст джерелаThe thesis is submitted to obtain a scientific degree of Doctor of Philosophy, specialty 152 – Metrology and information-measuring technique (15 – Automation and instrument-making). – National Technical University “Kharkiv Polytechnic Institute”, Kharkiv, 2019. The object of research is the process of conducting analysis in primary and secondary system transformations of information, which creates a problem situation with the improvement of hardware, algorithmic and software devices for control and diagnostics of complex industrial objects. The subject of research is a device for control and diagnostics of the state industrial dynamic objects. The scientific and practical task of increasing the efficiency of devices for control and diagnostics of the state of complex industrial objects with uncertain dynamic properties is solved in the dissertation. The solution is found using both classical and fundamentally new modern methods of probability theory, random processes, multivariate statistical analysis, information theory of measurement and control. The introduction substantiates the relevance of research tasks showing connection between the work and scientific programs, plans, themes, the scientific novelty is stated and practical value of the obtained results is formulated. The first chapter deals with analytical review and evaluation of questions in the field of control and diagnostics of the state of industrial objects. The object of diagnostics is selected; its structure, technical characteristics and area of use are considered. The analysis of methodical, algorithmic and equipment-specific devices for measuring temperature and mechanical vibration is carried out. A review of the existing devices for control and diagnostics of the state of complex industrial objects is made, their technical and economic characteristics are analyzed, and the optimal structure of the control and diagnostic system is selected. Some aspects of hardware, software and algorithmic programming when creating devices for control and diagnostics of the state of complex industrial objects are emphasized. The areas of research are selected; the main tasks of the dissertation are stated. The second chapter studies probabilistic models of parametrization of spectral changes of stationary measurement signals. The formalization of the probabilistic properties of non-stationary random signals is made, the correlation models of the spectral non-stationary of these signals are investigated, the dispersion analysis of frequency and time models of auto-coherence is carried out, the sensitivity of the correlation spectral model for the auto-coherence indicator of the multidimensional thermodynamic process is estimated, the discriminating properties of the indicators of auto-coherence are assessed regarding the classification of vibrational processes, diagnostic properties of components of the auto-coherence index are investigated, the choice of indicators for non-stationary control of dynamic processes is conducted. The research results have allowed obtaining a number of scientific results: - the theory of auto-coherence for spectrally non-stationary measurement signals has been developed. The conditions of the choice of the number of scales and displacements are determined regarding the estimation of the auto-coherence coefficients for monitoring the stationary disturbances of the measuring signal; - the conditions of calibration of auto-coherence index, which correspond to the absence of stationary violation, are obtained. A probabilistic model of the autocoherence index taking into account the minimum value (scale) of the spectral wavelet transform is developed; - the possibility of dispersion expansion of the basic auto-coherence index in paired independent components is shown, allowing to receive independent information on stationary violation, taking into account functional and random changes of the spectrum; - the example of thermal dynamic processes shows the efficiency of the developed autocorrelation index for controlling the dynamic properties of inertial multidimensional industrial objects. Also the possibility of automatic correction of the measurement error of temperature, if you control the whole heat process, and not its individual values, is shown; - the example of vibration signals shows the possibility of a qualitative classification of technical states, as well as quantitative classification of individual frequency-time components of the auto-coherence index is shown. It is proved that the best diagnostic properties are characterized by random (noise) components of the auto-coherence index. The third chapter presents studies on the diagnostic properties of autocoherence indices with restrictions on the measurement information volume. The general task of functional diagnostics of dynamic industrial objects is formulated, the model of parametric discrimination is chosen, the influence of the study sample size on the average risk of diagnosing is investigated, and mathematical and computer models of optimization of the space of informative signs by the criterion of maximum likelihood were created and their research was conducted. The researches in this chapter have allowed obtaining the following results: - experimental studies of the auto-coherence indices of vibration signals show that it is possible to use a linear solving function for controlling and diagnosing the technical state of vibrational objects, for which it is possible to use dispersion tables of auto-coherence indices and a normalized covariance matrix, which allow to generate, by multiplication, a total covariance matrix; - equations for the average risk and diagnostics probability are obtained allowing to model the influence of the training sample volume and informative features number on the performance indicators of the technical condition; - the existence of minimal extreme values of average risk for thermal and vibrational objects has been proved, allowing to use average risk as a target function for optimizing informative features space; - the complex influence of three parameters (geometric distance between diagnosed states, number of informative parameters, training sample volume) on the probability of control and diagnostics of the technical state of both thermal and vibration objects is studied. Such research has proven the ability to form an optimal, maximum control probability, system of informational features. The fourth chapter is devoted to the development of algorithmic and software device for monitoring and diagnosing the state of industrial objects. The methods of primary and secondary statistical transformations based on regression, spectral, dispersion and covariance analyses of the control and diagnostic device, have allowed to form the structure and the principle of algorithmic support functioning while limiting the volumes of measuring information by the diagnosed functional states. In this chapter the software aimed at implementation of the developed algorithms is chosen, programs fragments of devices for control and diagnostics of the state of industrial objects on the platform LabView are developed. According to researches of this chapter the following results are obtained: - the algorithmic structure of control devices and diagnostics of dynamic objects is developed, which consists of primary and secondary statistical transformation and contains the implementation of sampling processes of measurement signals, discrete analog wavelet transformation, differentiation and integration procedures; - an adaptive wavelet transform process with a flexible choice of the Gaussian parent wavelet is implemented, which minimizes the errors of control and diagnostics. - computer components of algorithmic and software procedures of primary and secondary statistical transformation in the synthesis of computerized diagnostic systems are formed, simulation modeling is conducted, the effects of destabilizing factors when controlling parameters of dynamic objects nodes are analyzed and their states are diagnosed; - the device software for controlling and diagnosing the state of industrial objects on the LabView platform with the use of object-oriented programming language, which allows to carry out the necessary control procedures in batch mode and in real-time, is developed.The fifth chapter presents engineering applications for the control and diagnostics of complex industrial objects. The research is provided for the development and patenting of primary transformers, selecting and patenting the structure of measuring channels of primary transformers, the development and creation of electronic blocks of primary and secondary transformation of information. The method of calibration of vibration test stands for metrological provision of primary vibration transducers is proposed, the verification of qualification of calibration laboratories in Ukraine and the influence of metrological support on the creation of systems of control and diagnosis of complex industrial objects are considered. According to researches of this chapter the following results are obtained: - primary temperature transducers for monitoring infra-low frequency processes in the investigated industrial object when evaluating thermal regimes, as well as primary transducers of mechanical vibration for monitoring high-frequency processes when evaluating rolling bearings condition of gear reducers are developed and patented; - on the basis of the Arduino microcontroller, a device for monitoring and diagnosing the condition of the extruder heating zones for manufacturing thermoplastics and the rolling bearings condition of gear reducers is created; - metrological researches of devices for measurement of infra-low frequency and high-frequency measuring signals are conducted, the vibration testing devices are implemented, and calibration methods of these devices are developed. - prospects for development of the theory and practice of control and diagnostics of processes characterized by different frequency indices in the specialized metrological laboratories are presented.
Каран, Евгений Валентинович. "Прогнозирование ресурса авиационных конструкций с многоочаговым повреждением". Thesis, 2016. http://er.nau.edu.ua/handle/NAU/17702.
Повний текст джерелаКаран Е.В. «Прогнозирование ресурса авиационных конструкций с многоочаговым повреждением» – Рукопись. Диссертация на соискание учёной степени кандидата технических наук по специальности 05.07.02 – проектирование, конструкция и производство летательных аппаратов. – Национальный авиационный университет, г. Киев, 2016. Диссертация посвящена разработке метода прогнозирования ресурса авиационных конструкций с многоочаговым повреждением на основе численного моделирования методом Монте-Карло. Многоочаговое повреждение авиационных конструкций проявляется, как правило, в рядах заклёпочных соединений и характеризуется образованием усталостных трещин у отверстий под заклёпки, их распространением вдоль соединения, а также объединением трещин, растущих навстречу друг другу из соседних отверстий. Проблема многоочагового повреждения особенно актуальна при оценке работоспособности, назначении периодичности осмотров и прогнозировании остаточной прочности стареющего парка самолётов. Случайная природа многоочагового повреждения обусловлена стохастическим рассеянием времени до образования трещин в заклёпочном соединении, случайным характером их распространения и объединения. Большинство из этих факторов учитывается при численном моделировании данного вида повреждения методом Монте-Карло. Для реализации численного эксперимента необходимо располагать математическими моделями процессов образования и роста усталостных трещин, числовые характеристики которых можно получить только экспериментальным путём. Результатом численного эксперимента являются статистические оценки ресурсных показателей конструкции. Разработана методика циклических испытаний плоских образцов с множественными концентраторами напряжения в виде отверстий и методика непрерывной регистрации и измерения размеров усталостных трещин на образце в процессе его нагружения. Проведены экспериментальные исследования на усталость образцов с множественными концентраторами и модельных образцов с заклёпочным соединением внахлёст, получено данные о сопротивлении алюминиевого сплава Д16АТ многоочаговому повреждению. На основании экспериментальных исследований определены статистическое распределение и числовые характеристики циклической наработки до образования усталостных трещин в испытуемых образцах в зависимости от действующего напряжения. Определено влияние заклёпочных соединения на усталостную прочность образцов с множественными концентраторами. На основании экспериментальных исследований получены обобщённые кинетические диаграммы усталостного разрушения алюминиевого сплава Д16АТ для образцов с отверстиями и с заклёпочным соединением. Определены коэффициенты С и m уравнения Пэриса для усталостных трещин в испытуемых образцах и установлена взаимосвязь между данными коэффициентами. Определены статистические показатели для распределения значений коэффициента m. Разработана эмпирическая модель кинетики роста усталостных трещин, которая базируется на модифицированном уравнении Пэриса и с использованием которой можно моделировать случайный рост трещины в алюминиевых сплавах. На основании полученных экспериментальных данных разработано соответствующее алгоритмическое и программное обеспечение для численного моделирования многоочагового повреждения заклёпочных соединений авиационных конструкций из алюминиевых сплавов. Проведена проверка работоспособности и оценка точности разработанного метода прогнозирования ресурса при многоочаговом повреждении авиационных конструкций.