中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 中科院工业视觉智能装备工程实验室
  5. 工业智能技术与系统
Cross-Level fusion for rotating machinery fault diagnosis under compound variable working conditions

文献类型：期刊论文

作者Wang, Sihan4; Wang, Dazhi4; Kong, Deshan4; Li, Wenhui4; Wang, Huanjie1,3; Pecht, Michael2
刊名MEASUREMENT
出版日期2022-08-01
卷号199页码:7
关键词Intelligent fault diagnosis Few-shot learning Anti-noise Compound faults Working condition variation
ISSN号0263-2241
DOI10.1016/j.measurement.2022.111455
通讯作者Wang, Dazhi(wdz_neu2021@163.com)
英文摘要Rotating machinery fault diagnosis based on deep learning has been successfully applied in modern industrial equipment. However, many existing types of research suffer from two significant deficiencies. First, most deep neural networks are based on a single or same kind of similarity measurement method, which cannot fully exploit the data to extract different levels of feature information. Second, most intelligent fault diagnosis methods can only partially solve the data sparsity and domain shift problems caused by small samples, noise, variable working conditions or compound faults. The model's performance will degenerate rapidly when the above problems occur simultaneously. To address this problem, this paper develops a cross-level fusion neural network method that extracts abundant information on features by calculating spatial-level, channel-level, and second-order statistical information and adaptively fusing the three levels to obtain the final relationship score. First, the signal is input into the embedding module through a Fast Fourier Transform to obtain the feature embedding of the onedimensional sequence signal. Then, the cross-level metrics learning module calculates the similarity of query sets and support sets at different levels. Finally, the similarities of different levels are fused through the adaptive fusion module to output the final relationship score. The bearing fault diagnosis experiments in the compound variable condition scenario show that the proposed method improves at least 78.53% compared to the traditional deep learning method, at least 3.22% and at most 35.52% compared to multiple few-shot learning methods. In addition, the ablation test analyzes the contribution of different level measurement methods to the model, and the maximum difference between them will reach 32.49%. In summary, the cross-level fusion method can effectively alleviate the data sparsity and domain shift problems.
WOS关键词NEURAL-NETWORK ; BEARINGS
资助项目National Natural Science Foundation of China[52077027] ; Department of Science and Technology of Liaoning province[2020020304-JH1/101]
WOS研究方向Engineering ; Instruments & Instrumentation
语种英语
WOS记录号WOS:000817179900005
出版者ELSEVIER SCI LTD
资助机构National Natural Science Foundation of China ; Department of Science and Technology of Liaoning province
源URL[http://ir.ia.ac.cn/handle/173211/49149]  
专题综合信息系统研究中心_工业智能技术与系统
通讯作者Wang, Dazhi
作者单位1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
2.Univ Maryland, Ctr Adv Life Cycle Engn, College Pk, MD 20742 USA
3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China
4.Northeastern Univ, Sch Informat Sci & Engn, Shenyang 110819, Peoples R China
推荐引用方式
GB/T 7714		 Wang, Sihan,Wang, Dazhi,Kong, Deshan,et al. Cross-Level fusion for rotating machinery fault diagnosis under compound variable working conditions[J]. MEASUREMENT,2022,199:7.
APA Wang, Sihan,Wang, Dazhi,Kong, Deshan,Li, Wenhui,Wang, Huanjie,&Pecht, Michael.(2022).Cross-Level fusion for rotating machinery fault diagnosis under compound variable working conditions.MEASUREMENT,199,7.
MLA Wang, Sihan,et al."Cross-Level fusion for rotating machinery fault diagnosis under compound variable working conditions".MEASUREMENT 199(2022):7.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。