Вы здесь ▸ Обсуждение ▸
Мои публикации
Публикации: статьи в журналах и сборниках конференций, доклады, презентации, отчеты, авторские свидетельства.
Иванов В.К.
Прогнозирование диагностических данных с использованием нечетких нейронных сетей Proceedings Article
In: Современные технологии и инновации, pp. 169-179, ТвГТУ, 2023, ISBN: 9785799513023.
Abstract | Links | BibTeX | Метки: diagnostic variable, forecast, fuzzy neural network, membership function, production rule, status-4, technology, time series, training dataset, временной ряд, диагностическая переменная, нечеткая нейронная сеть, обучающий набор данных, прогноз, продукционное правило, технологический процесс, функция принадлежности
@inproceedings{nokey,
title = {Прогнозирование диагностических данных с использованием нечетких нейронных сетей},
author = {Иванов В.К.},
url = {https://disk.yandex.ru/i/gsIW0s0vQKW6xg},
isbn = {9785799513023},
year = {2023},
date = {2023-07-31},
urldate = {2023-07-31},
booktitle = {Современные технологии и инновации},
pages = {169-179},
publisher = {ТвГТУ},
abstract = {В статье описан подход к решению задач анализа диагностической информации о функционировании сложного технологического процесса на примере прогнозирования трендов и временного ряда значений диагностических переменных. Цель проведённого исследования – показать возможность применения нечёткого сглаживания временного ряда и нечётких нейронных сетей для смягчения последствий неопределённости факторов, влияющих на функционирование технологического процесса, и неполноты информации о них. Предлагается модель прогнозирования, основанная на использовании нечётких временных рядов. Эта модель используется для формализации системы нечётких продукционных правил. Обосновывается применение нейронной сети с архитектурой ANFIS. Описывается методика подготовки обучающих и проверочных наборов реальных данных, настройки и обучения нейронной сети. Представлены некоторые результаты оценки качества обучения нейронной сети. Отмечается достаточная точность прогноза, достигаемая без использования затратных вычислительных ресурсов. Делается вывод о применимости предложенного подхода к данной и подобным задачам.
V.K. Ivanov. Prediction diagnostic data using fuzzy neural networks
The paper describes an approach to solving the problems of analyzing diagnostic information about the complex technological process functioning by the example of forecasting diagnostic variables values trends and their a time series. The study purpose is to show the possibility of using time series fuzzy smoothing and fuzzy neural networks to mitigate the factors uncertainty effects affecting the technological process functioning and incompleteness of information about such factors. A sales forecasting model based on the fuzzy time series use is proposed. This model is used to formalize fuzzy production rules system. The application of a neural network with ANFIS architecture is justified. The methodology of preparing training and verification real data sets, setting up and training a neural network is described. Some results of the neural network training quality evaluation are presented. There is a sufficient accuracy of the forecast, achieved without the expensive computing resources use. The conclusion is made about the proposed approach applicability to this and similar tasks.},
keywords = {diagnostic variable, forecast, fuzzy neural network, membership function, production rule, status-4, technology, time series, training dataset, временной ряд, диагностическая переменная, нечеткая нейронная сеть, обучающий набор данных, прогноз, продукционное правило, технологический процесс, функция принадлежности},
pubstate = {published},
tppubtype = {inproceedings}
}
В статье описан подход к решению задач анализа диагностической информации о функционировании сложного технологического процесса на примере прогнозирования трендов и временного ряда значений диагностических переменных. Цель проведённого исследования – показать возможность применения нечёткого сглаживания временного ряда и нечётких нейронных сетей для смягчения последствий неопределённости факторов, влияющих на функционирование технологического процесса, и неполноты информации о них. Предлагается модель прогнозирования, основанная на использовании нечётких временных рядов. Эта модель используется для формализации системы нечётких продукционных правил. Обосновывается применение нейронной сети с архитектурой ANFIS. Описывается методика подготовки обучающих и проверочных наборов реальных данных, настройки и обучения нейронной сети. Представлены некоторые результаты оценки качества обучения нейронной сети. Отмечается достаточная точность прогноза, достигаемая без использования затратных вычислительных ресурсов. Делается вывод о применимости предложенного подхода к данной и подобным задачам.
V.K. Ivanov. Prediction diagnostic data using fuzzy neural networks
The paper describes an approach to solving the problems of analyzing diagnostic information about the complex technological process functioning by the example of forecasting diagnostic variables values trends and their a time series. The study purpose is to show the possibility of using time series fuzzy smoothing and fuzzy neural networks to mitigate the factors uncertainty effects affecting the technological process functioning and incompleteness of information about such factors. A sales forecasting model based on the fuzzy time series use is proposed. This model is used to formalize fuzzy production rules system. The application of a neural network with ANFIS architecture is justified. The methodology of preparing training and verification real data sets, setting up and training a neural network is described. Some results of the neural network training quality evaluation are presented. There is a sufficient accuracy of the forecast, achieved without the expensive computing resources use. The conclusion is made about the proposed approach applicability to this and similar tasks.
V.K. Ivanov. Prediction diagnostic data using fuzzy neural networks
The paper describes an approach to solving the problems of analyzing diagnostic information about the complex technological process functioning by the example of forecasting diagnostic variables values trends and their a time series. The study purpose is to show the possibility of using time series fuzzy smoothing and fuzzy neural networks to mitigate the factors uncertainty effects affecting the technological process functioning and incompleteness of information about such factors. A sales forecasting model based on the fuzzy time series use is proposed. This model is used to formalize fuzzy production rules system. The application of a neural network with ANFIS architecture is justified. The methodology of preparing training and verification real data sets, setting up and training a neural network is described. Some results of the neural network training quality evaluation are presented. There is a sufficient accuracy of the forecast, achieved without the expensive computing resources use. The conclusion is made about the proposed approach applicability to this and similar tasks.
Ivanov V.K., Palyukh B.V., Sotnikov A.N.
Generation of Production Rules with Belief Functions to Train Fuzzy Neural Network in Diagnostic System Journal Article
In: Lobachevskii Journal of Mathematics, vol. 43, no. 10, pp. 2853–2862, 2022, ISSN: 1995-0802.
Abstract | Links | BibTeX | Altmetric | Метки: belief function, diagnostic system, diagnostic variable, evidence theory, fuzzy system, incident, membership function, multistage production process, neural network, process chain, production rule, status-4
@article{nokey,
title = {Generation of Production Rules with Belief Functions to Train Fuzzy Neural Network in Diagnostic System},
author = {Ivanov V.K. and Palyukh B.V. and Sotnikov A.N. },
url = {https://trebuchet.public.springernature.app/get_content/2642e052-2f35-4c6e-94ec-91c7565d5eda
https://disk.yandex.ru/i/CX5OUwIb2PKGRg},
doi = {10.1134/S1995080222130169},
issn = {1995-0802},
year = {2022},
date = {2022-10-31},
urldate = {2022-10-31},
journal = {Lobachevskii Journal of Mathematics},
volume = {43},
number = {10},
pages = {2853–2862},
abstract = {The article examines some algorithms for joint processing of raw data on the state of a complex multistage continuous production process to obtain probabilistic characteristics of abnormal critical events that can potentially lead to single failures or even emergencies. The article, thus, proposes and substantiates an approach to developing a technology to detect and predict malfunctions and determine their causes. The sequence of operations to process and convert diagnostic process data is considered essential. As a result, the article presents a general diagnostic model of a multistage production process. The model can formalize the main objects and processes in terms of the problem being solved. An incident is defined as an abnormal critical event described by non-normative values of diagnostic variables. Incidents are shown to be indicated by the corresponding membership functions. The hypotheses on potential incident causes are discussed to be built with belief functions being the basis of evidence theory or Dempster−Shafer theory. The hypotheses are characterized by an interval of malfunction probability in some process chain. The authors propose a procedure of converting these hypotheses into fuzzy production rules automatically. The automatical procedure is a prerequisite to using fuzzy neural networks to obtain a reliable estimate of the degree of belief in the incident cause. As a summary, the generated database of the production rules to train a neural network is substantiated to be used with the TSK architecture that makes possible to estimate a malfunction probability in the process chain quickly without resource-intensive computations.},
keywords = {belief function, diagnostic system, diagnostic variable, evidence theory, fuzzy system, incident, membership function, multistage production process, neural network, process chain, production rule, status-4},
pubstate = {published},
tppubtype = {article}
}
The article examines some algorithms for joint processing of raw data on the state of a complex multistage continuous production process to obtain probabilistic characteristics of abnormal critical events that can potentially lead to single failures or even emergencies. The article, thus, proposes and substantiates an approach to developing a technology to detect and predict malfunctions and determine their causes. The sequence of operations to process and convert diagnostic process data is considered essential. As a result, the article presents a general diagnostic model of a multistage production process. The model can formalize the main objects and processes in terms of the problem being solved. An incident is defined as an abnormal critical event described by non-normative values of diagnostic variables. Incidents are shown to be indicated by the corresponding membership functions. The hypotheses on potential incident causes are discussed to be built with belief functions being the basis of evidence theory or Dempster−Shafer theory. The hypotheses are characterized by an interval of malfunction probability in some process chain. The authors propose a procedure of converting these hypotheses into fuzzy production rules automatically. The automatical procedure is a prerequisite to using fuzzy neural networks to obtain a reliable estimate of the degree of belief in the incident cause. As a summary, the generated database of the production rules to train a neural network is substantiated to be used with the TSK architecture that makes possible to estimate a malfunction probability in the process chain quickly without resource-intensive computations.