Please use this identifier to cite or link to this item:
Full metadata record
DC FieldValueLanguage
dc.contributor.authorФедоров, Євген Євгенович-
dc.contributor.authorЯрош, Ирина Викторовна-
dc.contributor.authorЧерняк, Татьяна Александровна-
dc.description.abstractВ статье рассмотрены и проанализированы существующие методы диагностики шахтного вентилятора. Исходя из выделенных основных преимуществ и недостатков указанных методов, разработан и реализован нейросетевой метод диагностики состояния вентиляторной установки главного проветривания. В основу данного метода заложена предложенная нейронная сеть TDNN, архитектура которой определена на основе проведенных экспериментальных исследований. Для ускорения процесса обучения авторской нейронной сети предложен пакетный режим обучения. Для оценки эффективности предложенного метода диагностики состояния вентиляторной установки главного проветривания была проведена серия численных исследований, результаты которых доказывают эффективность предложенной авторами нейронной сети и ее архитектуры.uk_UA
dc.description.abstractCurrently, the increasing of operational safety is one of the major problems that exist in the mining industry. The problem of emergency equipment for mining industry is caused by the rapid increase in the share of depletion of its physical resources. Among the existing mine equipment, one of the most important roles is played by fan installations of the main airing, which ensure normal vital activity of the mine personnel. Therefore, an important task is to develop a software component, designed to diagnose the state of it and to be used in computer systems. At the heart of this objective lies the problem of building effective methods, providing high speed of diagnostics model training, as well as a high probability, adequacy and speed of signals recognition, which contain the vibrational information. At present, as a tool for vibration diagnostics, the following calculation methods are most commonly used: kurtosis, crest factor, RMS value, envelope spectrum. However, when using these markers separately for diagnosis of fan installations of the main airing condition, the probability of error is no less than 0.05. On the other hand, the processing speed of vibrational information is poor. Therefore, the development of methods for intelligent integrated diagnostics of fan installations of the main airing is relevant. As the use of artificial neural networks in the diagnosis gives tangible advantages, which are the following: the interaction between the factors is studied on finished models; it does not require any assumptions regarding the distribution of factors; a priori information about the factors can be omitted; the initial data can be highly correlated, incomplete or noisy; it is possible to conduct the analysis of systems with a high degree of nonlinearity; fast model development; high adaptability; the analysis of systems with a large number of factors; it does not require a complete enumeration of all possible models; the analysis of systems with non-uniform factors, neural network method of diagnosis is used in the article. The aim of the study consists in the development of a method for analysis of the process of changing the condition of fan installations of the main airing. The article defines the structure of the artificial neural network model, which is a TDNN neural network, that allows to explore the spectrum envelope at certain points of time. The minimum root-mean-square error has been chosen as a criterion for evaluating the effectiveness of the neural network diagnostic model. As a result of a numerical study, it is found that in the presence of 16 modules in the input layer, the value of RMS error does not change significantly, the proposed network provides diagnostic results with a minimum deviationuk_UA
dc.publisherВісник Черкаського державного технологічного університету. Технічні наукиuk_UA
dc.subjectвентиляторная установка главного проветриванияuk_UA
dc.subjectнейронная сетьuk_UA
dc.subjectпроизводственная безопасностьuk_UA
dc.subjectпакетный режим обученияuk_UA
dc.subjectfan installation of the main airinguk_UA
dc.subjectneural networkuk_UA
dc.subjectoperational safetyuk_UA
dc.subjectbatch training modeuk_UA
dc.titleНейросеть TDNN для диагностики состояния вентиляторной установки главного проветриванияuk_UA
dc.title.alternativeTDNN neural network for diagnosing the state of the fan installation of the main airinguk_UA
Appears in Collections:№4/2019

Files in This Item:
File Description SizeFormat 
5.pdfФедоров512.72 kBAdobe PDFThumbnail
зміст.pdf367.83 kBAdobe PDFThumbnail
титул.pdf336.59 kBAdobe PDFThumbnail

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.