Unsupervised fault diagnosis method based on domain adaptive neural network and joint distributed adaptive

被引：0
|
作者：
Zhang Z. [1 ]
Li X. [1 ]
Gao L. [1 ]
机构：
[1] School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan
来源：
Jisuanji Jicheng Zhizao Xitong/Computer Integrated Manufacturing Systems, CIMS | 2022年 / 28卷 / 08期
基金：
中国国家自然科学基金;
关键词：
domain adaptation neural network; fault diagnosis; joint distribution adaptive method; transfer learning; unsupervised learning;
D O I：
10.13196/j.cims.2022.08.008
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Fault diagnosis is very important for the health management of mechanical equipment. At present, data-driven fault diagnosis methods have become a research hotspot in this field. However, the working status and conditions of mechanical equipment are constantly changing, which leads to different distributions of fault data and brings challenges to fault diagnosis. To solve this problem, an unsupervised fault diagnosis method was proposed based on domain adaptive neural network and joint distributed adaptive. The fault diagnosis data of different data distributions were preprocessed by the method of signal to image. Then, the domain adaptive neural network was used to generate features with similar data distribution, and finally the joint distribution adaptive method was used to process the generated features. The proposed method could effectively solve the problem of different data distribution caused by changes in working status and conditions. The generated model could more accurately diagnose the fault data sampled in another working state without a label. Using a classic case in Case Western Reserve University bearing data set, the method was tested and verified, and the experimental results proved the feasibility and effectiveness of the method. © 2022 CIMS. All rights reserved.
引用
收藏
页码：2365 / 2374
页数：9
相关论文
共 36 条
  • [1] GAO Z, CECATI C, DING S X., A survey of fault diagnosis and fault-tolerant techniques Part I: Fault diagnosis with model-based and signal-based approaches, IEEE Transactions on Industrial Electronics, 62, 6, pp. 3757-3767, (2015)
  • [2] SHEPPARD J W, KAUFMAN M A., A Bayesian approach to diagnosis and prognosis using built-in test, IEEE Transactions on Instrumentation and Measurement, 5 4, 3, pp. 1003-1018, (2005)
  • [3] GENG Sujie, WANG Xiuli, Fault diagnosis and state estimation of power equipment based on fuzzy Bayesian network[J], Computer Integrated Manufacturing Systems, 2 7, 1, pp. 64-72, (2021)
  • [4] SOUALHI A, MEDJAHER K, ZERHOUNI N., Bearing-health monitoring based on Hilbert-Huang transform, support vector machine, and regression, IEEE Transactions on Instrumentation and Measurement, 64, 1, pp. 52-62, (2014)
  • [5] WEI Yonghua, WANG Minghua, Degradation state recognition of rolling bearing based on EEMD and SVM, Computer Integrated Manufacturing Systems, 2 1, 9, pp. 2475-2483, (2015)
  • [6] WEN L, LI X, GAO L., A new two-level hierarchical diagnosis network based on convolutional neural network, IEEE Transactions on Instrumentation and Measurement, 69, 2, pp. 330-338, (2019)
  • [7] LIU Xiuqing, MA Hongzhan, CHU Xuening, Performance assessment and anomaly detection of wind turbine based on long short time memory-auto encoder neural network, Computer Integrated Manufacturing Systems, 25, 12, pp. 3209-3219, (2019)
  • [8] SONG Ya, XIA Tangbin, ZHENG Yu, Remaining useful life prediction of turbofan engine based on Autoencoder-BLSTM [J], Computer Integrated Manufacturing Systems, 25, 7, pp. 1611-1619, (2019)
  • [9] CHEN Delei, WANG Cheng, ZENG Yu, Uncorrelated multisource load identification in frequency domain based on neural network and model transfer learning, Computer Integrated Manufacturing Systems, 27, 10, pp. 2961-2969, (2021)
  • [10] CAI B, HUANG L, XIE M., Bayesian networks in fault diagnosis, IEEE Transactions on Industrial Informatics, 13, 5, pp. 2227-2240, (2017)
1234