A Reinforcement Learning System for Fault Detection and Diagnosis in Mechatronic Systems

作     者：Wanxin Zhang Jihong Zhu 

作者机构：School of Electronics and Information TechnologySun Yat-sen UniversityGuangzhou510006China Department of Computer Science and TechnologyTsinghua UniversityBeijing100084China 

出 版 物：《Computer Modeling in Engineering & Sciences》 (工程与科学中的计算机建模（英文）)

年 卷 期：2020年第124卷第9期

页      面：1119-1130页

核心收录：

学科分类：070801[理学-固体地球物理学] 07[理学] 0708[理学-地球物理学] 

基　　金：This work was supported by the Soft Science Research Program of Guangdong Province under Grant 2020A1010020013 the National Defense Innovation Special Zone of Science and Technology Project under Grant 18-163-00-TS-006-038-01 the National Natural Science Foundation of China under Grant 61673240 

主　　题：Classification reinforcement learning neural network feature exaction and selection fault detection and diagnosis 

摘      要：With the increasing demand for the automation of operations and processes in mechatronic systems,fault detection and diagnosis has become a major topic to guarantee the process *** exist numerous studies on the topic of applying artificial intelligence methods for fault detection and ***,much of the focus has been given on the detection of *** terms of the diagnosis of faults,on one hand,assumptions are required,which restricts the diagnosis *** the other hand,different faults with similar symptoms cannot be distinguished,especially when the model is not trained by plenty of *** this work,we proposed a reinforcement learning system for fault detection and *** assumption is *** exaction is first *** with the features as the states of the environment,the agent directly interacts with the *** policy,which determines the exact category,size and location of the fault,is obtained by updating Q *** method takes advantage of expert *** the features are unclear,action will be made to get more information from the new state for further *** create recurrent neural network with the long short-term memory architecture to approximate Q *** application on a motor is *** experimental results validate that the proposed method demonstrates a significant improvement compared with existing state-of-the-art methods of fault detection and diagnosis.