Reinforcement learning-based cost-sensitive classifier for imbalanced fault classification
作者机构:State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University
出 版 物:《Science China(Information Sciences)》 (中国科学:信息科学(英文版))
年 卷 期:2023年第66卷第11期
页 面:113-126页
核心收录:
学科分类:12[管理学] 08[工学] 0831[工学-生物医学工程(可授工学、理学、医学学位)] 0710[理学-生物学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 1002[医学-临床医学] 081104[工学-模式识别与智能系统] 080401[工学-精密仪器及机械] 0804[工学-仪器科学与技术] 080402[工学-测试计量技术及仪器] 0805[工学-材料科学与工程(可授工学、理学学位)] 0838[工学-公安技术] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术(可授工学、理学学位)]
基 金:supported in part by National Natural Science Foundation of China (Grant Nos. 62003301, 61833014) Natural Science Foundation of Zhejiang Province (Grant No. LQ21F030018)
主 题:imbalanced fault classification fault diagnosis industrial process monitoring deep reinforcement learning cost-sensitive learning policy gradient sample weights
摘 要:Fault classification plays a crucial role in the industrial process monitoring domain. In the datasets collected from real-life industrial processes, the data distribution is usually imbalanced. The datasets contain a large amount of normal data(majority) and only a small amount of faulty data(minority); this phenomenon is also known as the imbalanced fault classification problem. To solve the imbalanced fault classification problem, a novel reinforcement learning(RL)-based cost-sensitive classifier(RLCC) based on policy gradient is proposed in this paper. In RLCC, a novel cost-sensitive learning strategy based on policy gradient and the actor-critic of RL is developed. The novel cost-sensitive learning strategy can adaptively learn the cost matrix and dynamically yield the sample weights. In addition, RLCC uses a newly designed reward to train the sample weight learner and classifier using an alternating iterative approach. The alternating iterative approach makes RLCC highly flexible and effective in solving the imbalanced fault classification *** effectiveness and practicability of the proposed RLCC method are verified through its application in a real-world dataset and an industrial process benchmark.