Research on Rotating Machinery Fault Diagnosis Method Based on Energy Spectrum Matrix and Adaptive Convolutional Neural Network | |
Liu YY(刘意杨)1,2,3![]() | |
Department | 工业控制网络与系统研究室 |
Source Publication | PROCESSES
![]() |
ISSN | 2227-9717 |
2021 | |
Volume | 9Issue:1Pages:1-25 |
Indexed By | SCI |
WOS ID | WOS:000610731100001 |
Contribution Rank | 1 |
Funding Organization | Revitalizing Liaoning Outstanding Talents Project [XLYC1907057] ; National Nature Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [U1908212] ; Key Project of Natural Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [61533015] ; National Key R&D Program of China [2018YFB1700200] |
Keyword | hierarchical fault diagnosis energy spectrum matrix dynamic adjustment of the learning rate convolutional neural network rotating machinery |
Abstract | Traditional intelligent fault diagnosis methods focus on distinguishing different fault modes, but ignore the deterioration of fault severity. This paper proposes a new two-stage hierarchical convolutional neural network for fault diagnosis of rotating machinery bearings. The failure mode and failure severity are modeled as a hierarchical structure. First, the original vibration signal is transformed into an energy spectrum matrix containing fault-related information through wavelet packet decomposition. Secondly, in the model training method, an adaptive learning rate dynamic adjustment strategy is further proposed, which adaptively extracts robust features from the spectrum matrix for fault mode and severity diagnosis. To verify the effectiveness of the method, the bearing fault data was collected using a rotating machine test bench. On this basis, the diagnostic accuracy, convergence performance and robustness of the model under different signal-to-noise ratios and variable load environments are evaluated, and the feature learning ability of the method is verified by visual analysis. Experimental results show that this method has achieved satisfactory results in both fault pattern recognition and fault severity evaluation, and is superior to other machine learning and deep learning methods. |
Language | 英语 |
Citation statistics | |
Document Type | 期刊论文 |
Identifier | http://ir.sia.cn/handle/173321/28315 |
Collection | 工业控制网络与系统研究室 |
Corresponding Author | Liu YY(刘意杨) |
Affiliation | 1.Key Laboratory of Networked Control Systems, Chinese Academy of Sciences, Shenyang 110016, China 2.Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China 3.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China 4.College of Information Science and Engineering, Northeastern University, Shenyang 110819, China 5.Industrial Engineering Department, XIOLIFT, Hangzhou 311199, China 6.Information and Control Engineering Department, Shenyang Jianzhu University, Shenyang 110168, China |
Recommended Citation GB/T 7714 | Liu YY,Yang YS,Feng, Tieying,et al. Research on Rotating Machinery Fault Diagnosis Method Based on Energy Spectrum Matrix and Adaptive Convolutional Neural Network[J]. PROCESSES,2021,9(1):1-25. |
APA | Liu YY,Yang YS,Feng, Tieying,Sun Y,&Zhang, Xuejian.(2021).Research on Rotating Machinery Fault Diagnosis Method Based on Energy Spectrum Matrix and Adaptive Convolutional Neural Network.PROCESSES,9(1),1-25. |
MLA | Liu YY,et al."Research on Rotating Machinery Fault Diagnosis Method Based on Energy Spectrum Matrix and Adaptive Convolutional Neural Network".PROCESSES 9.1(2021):1-25. |
Files in This Item: | ||||||
File Name/Size | DocType | Version | Access | License | ||
Research on Rotating(3684KB) | 期刊论文 | 出版稿 | 开放获取 | CC BY-NC-SA | View Application Full Text |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment