Assessment of process operating performance with supervised probabilistic slow feature analysis. (April 2023)

• Record Type: Journal Article
• Authors: Chu, Fei; Hao, Li-li; Shang, Chao; Liu, Yan; Wang, Fu-li
• Is Part Of: Journal of process control. Volume 124(2023)
• Page Start: 152
• Page End: 165
• Publication Date: 2023-04
• Subjects: Operation performance assessment -- Slow feature analysis -- Complex industrial process -- Sparse learning; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2023.02.015
• Languages: English
• ISSNs: 0959-1524

Abstract

Abstract: Assessment of operating performance, which is adopted to assess optimal degree for complex industrial process, has been increasing concerned in the last few years. In this study, a supervised probabilistic slow feature analysis (SPSFA) is proposed to assess the optimal degree of process performance by deep mining process variables information on the basis of the probability distribution model. First, the slow features (SFs) are modeled in state–space form as a serial correlation feature to effectively represent the potential variation of performance, and the serial correlation hiding in the performance features reveals the potential changes of performance, which helps improve cognitive depth and assessment accuracy of performance. Then, multi-order dynamic information of SFs is further combined to design the multi-order dynamic index, which accurately and timely depict the dynamic changes of the process. Hence, the proposed method provides an explicit representation of underlying driving forces of performance variations and meaningful physical interpretation of each stage from optimal to non-optimal. In addition, a sparse learning-based non-optimal factor identification method is proposed, which identifies non-optimal factor variables by reconstructing the online estimation of the Kalman filter and using Group Lasso. The feasibility and effectiveness of the proposed method is validated by an actual dense medium coal preparation process and a typical Tennessee Eastman process. Highlights: It is the first time to establish the operation performance assessment model based on probability graph model. Multi-order dynamic information of SFs is further explored to design a multi-order dynamic index to provide an explicit representations of underlying driving forces of performance variations. A new non-optimal factor recognition method based on sparse learning is proposed to identification of non-optimal factor variables by reconstructing Kalman filter online estimation and using Group Lasso.