Transfer reinforcement learning method with multi-label learning for compound fault recognition. (January 2023)

• Record Type: Journal Article
• Authors: Wang, Zisheng; Zhang, Qing; Tang, Lv; Shi, Tielin; Xuan, Jianping
• Is Part Of: Advanced engineering informatics. Volume 55(2023)
• Publication Date: 2023-01
• Subjects: Compound fault recognition -- Deep reinforcement learning -- Multi-label learning -- Transfer learning -- Trust region policy optimization; Computer-aided engineering -- Periodicals; Engineering -- Data processing -- Periodicals; 620.00285
• DOI: 10.1016/j.aei.2022.101818
• Languages: English
• ISSNs: 1474-0346

Abstract

Abstract: In complex working site, bearings used as the important part of machine, could simultaneously have faults on several positions. Consequently, multi-label learning approach considering fully the correlation between different faulted positions of bearings becomes the popular learning pattern. Deep reinforcement learning (DRL) combining the perception ability of deep learning and the decision-making ability of reinforcement learning, could be adapted to the compound fault diagnosis while having a strong ability extracting the fault feature from the raw data. However, DRL is difficult to converge and easily falls into the unstable training problem. Therefore, this paper integrates the feature extraction ability of DRL and the knowledge transfer ability of transfer learning (TL), and proposes the multi-label transfer reinforcement learning (ML-TRL). In detail, the proposed method utilizes the improved trust region policy optimization (TRPO) as the basic DRL framework and pre-trains the fixed convolutional networks of ML-TRL using the multi-label convolutional neural network method. In compound fault experiment, the final results demonstrate powerfully that the proposed method could have the higher accuracy than other multi-label learning methods. Hence, the proposed method is a remarkable alternative when recognizing the compound fault of bearings. Highlights: The proposed method is based on the DRL and the TL. A pre-trained ML-CNN is designed to enhance the ability of ML-TRL. An end-to-end mode is developed by training directly the 1D signal.