Continual learning fault diagnosis:A dual-branch adaptive aggregation residual network for fault diagnosis with machine increments  

作　　者：Bojian CHEN Changqing SHEN Juanjuan SHI Lin KONG Luyang TAN Dong WANG Zhongkui ZHU 

机构地区：[1]School of Rail Transportation,Soochow University,Suzhou 215131,China [2]China Chang Guang Satellite Technology CO.LTD,Changchun 130102,China [3]Department of Industrial Engineering and Management and in the State Key Laboratory of Mechanical System and Vibration,Shanghai Jiao Tong University,Shanghai 200030,China

出　　处：《Chinese Journal of Aeronautics》2023年第6期361-377,共17页中国航空学报（英文版）

基　　金：supported by the National Natural Science Foundation of China(Nos.52272440,51875375);the China Postdoctoral Science Foundation Funded Project(No.2021M701503).

摘　　要：As a data-driven approach, Deep Learning(DL)-based fault diagnosis methods need to collect the relatively comprehensive data on machine fault types to achieve satisfactory performance. A mechanical system may include multiple submachines in the real-world. During condition monitoring of a mechanical system, fault data are distributed in a continuous flow of constantly generated information and new faults will inevitably occur in unconsidered submachines, which are also called machine increments. Therefore, adequately collecting fault data in advance is difficult. Limited by the characteristics of DL, training existing models directly with new fault data of new submachines leads to catastrophic forgetting of old tasks, while the cost of collecting all known data to retrain the models is excessively high. DL-based fault diagnosis methods cannot learn continually and adaptively in dynamic environments. A new Continual Learning Fault Diagnosis method(CLFD) is proposed in this paper to solve a series of fault diagnosis tasks with machine increments. The stability–plasticity dilemma is an intrinsic issue in continual learning. The core of CLFD is the proposed Dual-branch Adaptive Aggregation Residual Network(DAARN).Two types of residual blocks are created in each block layer of DAARN: steady and dynamic blocks. The stability–plasticity dilemma is solved by assigning them with adaptive aggregation weights to balance stability and plasticity, and a bi-level optimization program is used to optimize adaptive aggregation weights and model parameters. In addition, a feature-level knowledge distillation loss function is proposed to further overcome catastrophic forgetting. CLFD is then applied to the fault diagnosis case with machine increments. Results demonstrate that CLFD outperforms other continual learning methods and has satisfactory robustness.

关 键 词：Catastrophic forgetting Continual learning Fault diagnosis Knowledge distillation Machine increments Stability-plasticity dilemma 

分 类 号：V267[航空宇航科学与技术—航空宇航制造工程] V467