文献类型：期刊文献

英文题名：Temporal Attention Source-Free Adaptation for Chemical Processes Fault Diagnosis

作者：Xiao, Yutang[1];Shi, Hongbo[1];Song, Bing[1];Tao, Yang[1];Tan, Shuai[1];Wang, Boyu[2,3]

机构：[1]East China Univ Sci & Technol, Key Lab Smart Mfg Energy Chem Proc, Minist Educ, Shanghai 200237, Peoples R China;[2]Univ Western Ontario, Dept Comp Sci, London, ON N6A 5B7, Canada;[3]Univ Western Ontario, Brain Mind Inst, London, ON N6A 5B7, Canada

年份：2024

卷号：20

期号：3

起止页码：4773

外文期刊名：IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS

收录：;EI(收录号：20234715088524);WOS:【SCI-EXPANDED(收录号:WOS:001106577700001)】；

基金：The work of Boyu Wang was supported by NSERC Discovery Grants Program. This work was supported in part by the National Natural Science Foundation of China under Grant 62073141, Grant 62073140, and Grant 62103149, in part by the National Key Research and Development Program of China under Grant 2020YFC1522502,and Grant 2020YFC1522505, in part by Shanghai Rising-Star Program under Grant 21QA1401800

语种：英文

外文关键词：Adaptation models; Data models; Feature extraction; Fault diagnosis; Time series analysis; Chemical processes; Chemicals; Chemical process fault diagnosis; privacy-preserving; source-free domain adaptation (SFDA); temporal attention

摘要：Recently, domain adaptation (DA)-based fault diagnosis approaches have been actively studied in chemical processes to build a reliable fault diagnosis model for a new operating mode (i.e., target domain) by making use of labeled data from a historical mode (i.e., source domain). However, this raises privacy concerns, such as data leakage, since industrial data contains sensitive production information. Moreover, preprocessed source and target data used to train an effective target model will result in additional computational costs. Therefore, it is crucial to develop a novel privacy preserving DA-based fault diagnosis approach that can improve the diagnosis performance for a new mode and protect the privacy of a historical mode simultaneously. To this end, fault diagnosis is formulated as the source-free DA problem and proposes a temporal attention source-free adaptation (TASFA) algorithm, which only utilizes the pretrained source model and unlabeled target data to learn a diagnosis model. Specifically, for the time-series process, an attention mechanism is designed to capture and leverage the temporal correlations between source and target domains by extracting the most transferable information from the target time series. Empirical results on both the Tennessee Eastman process and the continuous stirred tank reactor demonstrate the effectiveness and efficiency of TASFA.