A novel auto-regressive dynamic slow feature analysis method for dynamic chemical process monitoring. (2nd February 2022)

• Record Type: Journal Article
• Authors: Xu, Yuemei; Jia, Mingxing; Mao, Zhizhong
• Is Part Of: Chemical engineering science. Volume 248:Part B(2022)
• Publication Date: 2022-02-02
• Subjects: Dynamic process monitoring -- Slow feature analysis -- Dynamic latent variable -- Temporal correlation; Chemical engineering -- Periodicals; Génie chimique -- Périodiques; Chemical engineering; Periodicals; Electronic journals; 660
• DOI: 10.1016/j.ces.2021.117236
• Languages: English
• ISSNs: 0009-2509

Abstract

Highlights: The temporal correlation is considered by introduce a dynamic latent model. A novel dynamic process modeling method (RDSFA) is proposed. The proposed RDSFA extract a group latent features with slow varying speed and explicit dynamic autoregressive representation. Two statistics which only contain unpredictable variability information are formed. The superiority and effectiveness of the proposed RDSFA based dynamic process monitoring is demonstrated by compare with other methods. Abstract: A novel dynamic data modeling method called autoregressive dynamic slow feature analysis (RDSFA) is proposed for dynamic process concurrent monitoring of operating condition deviations and process dynamics anomalies. In this method, a multi-goal optimization question is formulized with constraints of the extract latent variable catch some variation information and mutually orthogonal to extract a group of latent features which change slowly over time and whose autoregressive model are built explicitly. When the proposed method is applied to the process monitoring, in addition to the statistics about slow feature and whose first derivatives with respect to time which have existed in SFA based monitoring frame, we add other two statistics which only contain unpredictable variability information to provide more sensitive monitoring results. Case studies on simulation data, data from a CSTR process are presented to reveal the efficiency and the superiority of the proposed method as compared to other related methods.