Fuzzy Domain Adaptation Approach for Source-free Domain Rotary Machinery Fault Diagnosis

doi:10.3901/JME.2024.18.043

Abstract

Abstract: Existing domain adaptation methods require access to raw data, increasing the risk of data leakage. Fuzzy domain adaptation generates fuzzy rules and relationships without accessing source data. Leveraging knowledge from the source, this research proposes a novel method for source-free domain rotary machinery fault diagnosis using fuzzy domain adaptation. Specifically, during source domain training, a joint training strategy simultaneously trains all source models by sharing model parameters. This approach significantly enhances the multi-domain performance of each private source model. Additionally, a model with a fused fuzzy strategy is constructed to derive fuzzy rules from source samples and anchor points corresponding to various categories. In the target domain adaptation phase, the proposed method retrains the source feature extractor using target data while keeping the fuzzy rules fixed. Subsequently, an anchor point alignment strategy is introduced to transfer diagnostic knowledge. Finally, a filtering strategy is designed to obtain high-confidence target pseudo-labels, combining a self-supervised learning strategy for the ultimate optimization of the target model. After verification by rolling bearing cross-domain diagnosis cases and gear cross-domain diagnosis cases, the framework is an efficient and secure solution for fault diagnosis.

Key words: rotary machinery fault diagnosis, data privacy leakage, source-free domain, fuzzy domain adaptation, self-supervised learning strategy

CLC Number:

TH17

ZHAO Ke, YE Min, WANG Ruixin, LU Hai, LIU Mengmeng, SHAO Haidong. Fuzzy Domain Adaptation Approach for Source-free Domain Rotary Machinery Fault Diagnosis[J]. Journal of Mechanical Engineering, 2024, 60(18): 43-52.

References

[1] ZHAO K，LIU Z，ZHAO B，et al. Class-aware adversarial multiwavelet convolutional neural network for cross-domain fault diagnosis[J]. IEEE Transactions on Industrial Informatics，2024，20(3)：4492-4503.
[2] 江星星，彭德民，沈长青，等. 快速固有成分滤波特征融合的轴承故障诊断方法[J]. 机械工程学报，2022，58(22)：129-139. JIANG Xingxing，PENG Demin，SHEN Changqing，et al. Feature fusion of fast intrinsic component filtering for bearing fault diagnosis[J]. Journal of Mechanical Engineering，2022，58(22)：129-139.
[3] 郑近德，应万明，潘海洋，等. 基于改进全息希尔伯特谱分析的旋转机械故障诊断方法[J]. 机械工程学报，2023，59(1)：162-174. ZHENG Jinde, YING Wanming, PAN Haiyang, et al. Improved Holo-Hilbert spectrum analysis-based fault diagnosis method for rotating machines[J]. Journal of Mechanical Engineering, 2023, 59(1)：162-174.
[4] 李响，付春霖，雷亚国，等. 保证数据隐私的装备协同智能故障诊断联邦迁移学习方法[J]. 机械工程学报，2023，59(6)：1-9. LI Xiang，FU Chunlin，LEI Yaguo，et al. Federated transfer learning method for privacy-preserving collaborative intelligent machinery fault diagnostics[J]. Journal of Mechanical Engineering，2023，59(6)：1-9.
[5] 陈祝云，钟琪，黄如意，等. 基于增强迁移卷积神经网络的机械智能故障诊断[J]. 机械工程学报，2021，57(21)：96-105. CHEN Zhuyun，ZHONG Qi，HUANG Ruyi，et al. Intelligent fault diagnosis for machinery based on enhanced transfer convolutional neural network[J]. Journal of Mechanical Engineering，2021，57(21)：96-105.
[6] KANG G，JIANG L，YANG Y，et al. Contrastive adaptation network for unsupervised domain adaptation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2019：4893-4902.
[7] ZHAO K，LIU Z，LI J，et al. Self-paced decentralized federated transfer framework for rotating machinery fault diagnosis with multiple domains[J]. Mechanical Systems and Signal Processing，2024，211：111258.
[8] QIAN W，LI S，JIANG X. Deep transfer network for rotating machine fault analysis[J]. Pattern Recognition，2019，96：106993.
[9] FERRACUTI F，FREDDI A，MONTERIU A，et al. Fault diagnosis of rotating machinery based on wasserstein distance and feature selection[J]. IEEE Transactions on Automation Science and Engineering，2021，19(3)：1997-2007.
[10] KUANG J，XU G，TAO T，et al. Self-supervised bi-classifier adversarial transfer network for cross-domain fault diagnosis of rotating machinery[J]. ISA transactions，2022，130：433-448.
[11] ZHANG Z，GUAN C，CHEN H，et al. Adaptive privacy-preserving federated learning for fault diagnosis in internet of ships[J]. IEEE Internet of Things Journal，2021，9(9)：6844-6854.
[12] ZHANG W，LI X，MA H，et al. Federated learning for machinery fault diagnosis with dynamic validation and self-supervision[J]. Knowledge-Based Systems，2021，213：106679.
[13] ZHAO K，HU J，SHAO H，et al. Federated multi-source domain adversarial adaptation framework for machinery fault diagnosis with data privacy[J]. Reliability Engineering & System Safety，2023，236：109246.
[14] TIAN J，ZHANG J，JIANG Y，et al. A novel generalized source-free domain adaptation approach for cross-domain industrial fault diagnosis[J]. Reliability Engineering & System Safety，2024，243：109891.
[15] WANG J，ZHANG H，MIAO Q. Source free unsupervised domain adaptation for electro-mechanical actuator fault diagnosis[J]. Chinese Journal of Aeronautics，2023，36(4)：252-267.
[16] LIU F，ZHANG G，LU J. Multisource heterogeneous unsupervised domain adaptation via fuzzy relation neural networks[J]. IEEE Transactions on Fuzzy Systems，2020，29(11)：3308-3322.
[17] LESSMEIER C. KIMOTHO J，ZIMMER D. et al. Condition monitoring of bearing damage in electromechanical drive systems by using motor current signals of electric motors：A benchmark data set for data-driven classification[C/CD]// European Conference of the Prognostics and Health Management Society，Bilbao (Spain)，2016.
[18] 张宗振，王金瑞，韩宝坤，等. 非线性稀疏盲解卷积的轴承早期故障诊断方法[J]. 机械工程学报，2023(16)：1-10. ZHANG Zongzhen，WANG Jinrui，HAN Baokun，et al. Early stage fault diagnosis method of bearings based on nonlinear sparse blind deconvolution[J]. Journal of Mechanical Engineering，2023(16)：1-10.
[19] LIANG J，HU D，FENG J. Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation[C]//International Conference on Machine Learning，PMLR，2020：6028-6039.
[20] GAO Q，HUANG T，ZHAO K，et al. Multi-source weighted source-free domain transfer method for rotating machinery fault diagnosis[J]. Expert Systems with Applications，2024，237：121585.