A comparative case study between shallow and deep neural networks in induction motor's fault diagnosis

IF 1.4 4区 工程技术 Q3 ENGINEERING, ELECTRICAL & ELECTRONIC
Azadeh Gholaminejad, Saeid Jorkesh, Javad Poshtan
{"title":"A comparative case study between shallow and deep neural networks in induction motor's fault diagnosis","authors":"Azadeh Gholaminejad,&nbsp;Saeid Jorkesh,&nbsp;Javad Poshtan","doi":"10.1049/smt2.12143","DOIUrl":null,"url":null,"abstract":"<p>Here, performance of auto-encoder deep neural networks in detection and isolation of induction motor states (healthy, bearing outer race fault, stator winding short circuit and broken rotor bar) in the presence of unbalanced power supply and electro-pump dry running disturbances is investigated. Easily available three-phase electrical current signals are denoised using independent component analysis, and then the frequency-domain signal is used to train a neural network. A comparison is made between shallow and deep neural networks and also between the conventional structure of deep methods and the encoder–decoder structure in terms of training and test accuracy and robustness. In fact, the depth is increased and the effectiveness is investigated. At the end, it is shown that an encoder–decoder structure leads to the best result in terms of accuracy and robustness. The algorithms are examined experimentally, and the results show that the auto-encoder deep neural network can detect the aforementioned faults with a high reliability in the presence of disturbances.</p>","PeriodicalId":54999,"journal":{"name":"Iet Science Measurement & Technology","volume":null,"pages":null},"PeriodicalIF":1.4000,"publicationDate":"2023-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/smt2.12143","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Iet Science Measurement & Technology","FirstCategoryId":"5","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1049/smt2.12143","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 2

Abstract

Here, performance of auto-encoder deep neural networks in detection and isolation of induction motor states (healthy, bearing outer race fault, stator winding short circuit and broken rotor bar) in the presence of unbalanced power supply and electro-pump dry running disturbances is investigated. Easily available three-phase electrical current signals are denoised using independent component analysis, and then the frequency-domain signal is used to train a neural network. A comparison is made between shallow and deep neural networks and also between the conventional structure of deep methods and the encoder–decoder structure in terms of training and test accuracy and robustness. In fact, the depth is increased and the effectiveness is investigated. At the end, it is shown that an encoder–decoder structure leads to the best result in terms of accuracy and robustness. The algorithms are examined experimentally, and the results show that the auto-encoder deep neural network can detect the aforementioned faults with a high reliability in the presence of disturbances.

Abstract Image

浅层和深层神经网络在感应电机故障诊断中的比较案例研究
本文研究了在存在不平衡电源和电泵干运行扰动的情况下,自动编码器深度神经网络在检测和隔离感应电机状态(健康、轴承外圈故障、定子绕组短路和转子棒断裂)方面的性能。使用独立分量分析对容易获得的三相电流信号进行去噪,然后使用频域信号来训练神经网络。在训练、测试准确性和稳健性方面,对浅层和深层神经网络以及深层方法的传统结构和编码器-解码器结构进行了比较。事实上,深度增加了,有效性也得到了研究。最后,结果表明,编码器-解码器结构在准确性和鲁棒性方面取得了最佳结果。对算法进行了实验验证,结果表明,在存在扰动的情况下,自动编码器深度神经网络可以高可靠性地检测上述故障。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Iet Science Measurement & Technology
Iet Science Measurement & Technology 工程技术-工程:电子与电气
CiteScore
4.30
自引率
7.10%
发文量
41
审稿时长
7.5 months
期刊介绍: IET Science, Measurement & Technology publishes papers in science, engineering and technology underpinning electronic and electrical engineering, nanotechnology and medical instrumentation.The emphasis of the journal is on theory, simulation methodologies and measurement techniques. The major themes of the journal are: - electromagnetism including electromagnetic theory, computational electromagnetics and EMC - properties and applications of dielectric, magnetic, magneto-optic, piezoelectric materials down to the nanometre scale - measurement and instrumentation including sensors, actuators, medical instrumentation, fundamentals of measurement including measurement standards, uncertainty, dissemination and calibration Applications are welcome for illustrative purposes but the novelty and originality should focus on the proposed new methods.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信