Enhanced canonical variate analysis with slow feature for dynamic process status analytics. (November 2020)

• Record Type: Journal Article
• Authors: Zheng, Jiale; Zhao, Chunhui
• Is Part Of: Journal of process control. Volume 95(2020)
• Page Start: 10
• Page End: 31
• Publication Date: 2020-11
• Subjects: Process dynamics -- Slowly varying -- Temporal correlations -- Varying speed -- Process monitoring; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2020.09.005
• Languages: English
• ISSNs: 0959-1524

Abstract

Abstract: Process dynamics is widely presented in industrial processes, which can be perceived as temporal correlations. Negligence of dynamic information may result in misleading monitoring results. Therefore, explicit exploration of dynamic information is crucial to process monitoring. In this paper, a new data-driven algorithm called enhanced canonical variate analysis with slow feature (ECVAS) and corresponding monitoring strategy are proposed for dynamic process monitoring. First, a new objective function is defined with two goals, which attempts to extract slowly varying latent variables in addition to high temporal correlation. Hence, the latent variables called slow canonical variables (SCVs) would capture valuable dynamic information and be isolated from static information and fast-varying noises. Second, the process dynamics has been explored in detail by concurrently monitoring of temporal correlations and varying speed. Therefore, the proposed method achieves in-depth understanding of process dynamics under control actions and helps identify normal changes in operating conditions. Third, process static information and dynamic information have been separately monitored, contributing to a fine-scale identification of process variations. Finally, the validity of the proposed strategy is illustrated with an industrial scale multiphase flow experimental rig and a real thermal power process. Highlights: A new objective is proposed to isolate valuable dynamic information from data by concurrent consideration of temporal correlation and process variation speed. A legible interpretation of process dynamics is provided by concurrently monitoring of temporal correlations and varying speed, which successfully recognizes normal changes in operating conditions. The proposed algorithm provides separately monitoring of process dynamic and static information, which contributes to comprehensive exploration of the process variations. The validity of the proposed method is illustrated with two industrial processes.