Dual-input anomaly detection method based on deep reinforcement learning

作     者：Kang, Yuxiang Chen, Guo Wang, Hao Pan, Wenping Wei, Xunkai 

作者机构：Nanjing Univ Aeronaut & Astronaut Coll Civil Aviat Nanjing Peoples R China Nanjing Univ Aeronaut & Astronaut Coll Gen Aviat & Flight Nanjing Peoples R China Beijing Aeronaut Engn Tech Res Ctr Beijing Peoples R China Nanjing Univ Aeronaut & Astronaut 29Jiangjun Ave Nanjing Jiangsu Peoples R China 

出 版 物：《STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL》 (结构安全监测)

年 卷 期：2024年第23卷第3期

页      面：1578-1591页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 08[工学] 0804[工学-仪器科学与技术] 

基　　金：National Science and Technology Major Project [J2019-IV-004-0071] National Natural Science Foundation of China 

主　　题：Deep reinforcement learning anomaly detection dual-input deep neural network unsupervised learning rolling bearings 

摘      要：Aiming at the problem of low accuracy of unsupervised learning anomaly detection algorithm, a dual-input anomaly detection method based on deep reinforcement learning was proposed. The proposed model mainly consists of a feature extractor and anomaly detector. Based on the deep reinforcement learning framework, the feature extractor uses a dual-input deep neural network to form the current value network and the target value network, which are used to extract the low-dimensional feature vectors. Based on the 3 principle, the reward function of reinforcement learning is designed to reward and punish the output results of the model during training. The model was trained only with the normal data, and the extracted feature vector of the normal class was used as the input of the anomaly detector to complete the learning of the detector. During the test, the input anomaly detection was realized based on the dual-input convolutional neural network, and the anomaly detector was completed by learning. To illustrate the generality and generalization performance of the proposed method, four sets of image data and two sets of rolling bearing fault data in different fields were verified respectively. At the same time, the proposed method is applied to the fault detection of a real aero-engine rolling *** results show that the proposed model has high anomaly detection accuracy, which is superior to the current optimal method.