文献类型：期刊文献

英文题名：Concurrent Monitoring Strategy for Static and Dynamic Deviations Based on Selective Ensemble Learning Using Slow Feature Analysis

作者：Hong, Huifen[1];Jiang, Chao[1,4];Peng, Xin[1,2];Zhong, Weimin[1,3]

机构：[1]East China Univ Sci & Technol, Key Lab Adv Control & Optimizat Chem Proc, Minist Educ, Shanghai 200237, Peoples R China;[2]Univ Duisburg Essen, Inst Automat Control & Complex Syst, D-47057 Duisburg, Germany;[3]Tongji Univ, Shanghai Inst Intelligent Sci & Technol, Shanghai 200092, Peoples R China;[4]Univ Alberta, Dept Chem & Mat Engn, Edmonton, AB T6G 2V4, Canada

年份：2020

卷号：59

期号：10

起止页码：4620

外文期刊名：INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH

收录：;EI(收录号：20201308360772);WOS:【SCI-EXPANDED(收录号:WOS:000526415600045)】；

基金：The work was supported by the National Natural Science Foundation of China under Grants 61890930-3, 61925305, and 61803157, the Shanghai Sailing Program under Grant 18YF1405200, the Programme of Introducing Talents of Discipline to Universities (the 111 Project) under Grant B17017, and Fundamental Research Funds for the Central Universities under Grant 222201917006.

语种：英文

外文关键词：Principal component analysis - Learning systems - Process control - Bayesian networks - Clustering algorithms - Fault detection - Inference engines

摘要：Slow feature analysis (SFA) has been extensively adopted for process monitoring. Since the prominent ability of exploring dynamic information of the industrial process, SFA could monitor the process static and dynamic deviations concurrently. However, for complex and large-scale processes, it is difficult for a single SFA model to monitor the whole process well because of the complex relationship within massive volumes of variables. To address this issue and get a better monitoring performance, a novel ensemble process monitoring method based on slow feature analysis models is proposed as ensemble SFA (ESFA) in this paper. The proposed method develops a set of SFA models based on different combinations of variables, and the divisive hierarchical clustering algorithm (DHCA) is performed to pick out some models with great diversity as the base learners. Then, the fault detection results of base models would be combined into a comprehensive indicator through Bayesian inference. Furthermore, the ESFA method also provides an ES2 statistic for monitoring process dynamics to differentiate the deviations of normal operating condition changes from dynamic anomalies incurred by real faults. Finally, compared with basic SFA and several principal component analysis (PCA)-based methods, the validity of the proposed method is demonstrated through the case studies of the Tennessee Eastman (TE) benchmark process and the BSM1 process.