A statistical distribution recalibration method of soft labels to improve domain adaptation for cross-location and cross-machine fault diagnosis

作     者：Zhang, Qing Tang, Lv Sun, Menglin Xuan, Jianping Shi, Tielin 

作者机构：Huazhong Univ Sci & Technol Sch Mech Sci & Engn Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China 

出 版 物：《MEASUREMENT》 (测量)

年 卷 期：2021年第182卷

页      面：109754-109754页

核心收录：

学科分类：08[工学] 080401[工学-精密仪器及机械] 0804[工学-仪器科学与技术] 081102[工学-检测技术与自动化装置] 0811[工学-控制科学与工程] 

基　　金：National Key R&D Program of China [2020YFB20077] Science Challenge Project of China [JDZZ2018006020201] National Natural Science Foundation of China 

主　　题：Intelligent fault diagnosis Cross-location tasks Cross-machine tasks Statistical distribution recalibration Distribution alignment Dynamic distribution adaptation 

摘      要：Unsupervised domain adaptation has achieved certain success in recent cross-domain fault diagnosis research. As a widely used transfer strategy, the distribution alignment often occurs with the problems of too few valid alignment samples, too low confidence of predicted labels, and the inadequate alignment of marginal or conditional distributions. Therefore, this paper proposes a statistical distribution recalibration method of soft labels (SDRS). First, SDRS defines the valid samples and confusion interval in the statistical distribution of per-class predicted probabilities. Then, from the perspective of binary classification, a recalibration space in the confusion interval is further optimized by a center distance metric, to improve predicted confidence and valid distribution alignment. Built on SDRS, a novel cross-domain fault diagnosis approach named SDRSDAN is constructed, where dynamic distribution adaptation is used to match and adjust the marginal and conditional distribution discrepancies adaptively. Extensive experiments prove the effectiveness of SDRS-DAN in cross-location and cross-machine scenarios.