Slow feature analysis for monitoring and diagnosis of control performance. (March 2016)

• Record Type: Journal Article
• Authors: Shang, Chao; Huang, Biao; Yang, Fan; Huang, Dexian
• Is Part Of: Journal of process control. Volume 39(2016:Mar.)
• Page Start: 21
• Page End: 34
• Publication Date: 2016-03
• Subjects: Data-driven modeling -- Control performance monitoring -- Contribution plot -- Fault diagnosis -- Industrial alarm system; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2015.12.004
• Languages: English
• ISSNs: 0959-1524

Abstract

Abstract : Highlights: A data-driven approach to control performance monitoring and diagnosis is proposed. Temporal variations of processes implicitly reveal control performance. Nominal temporal dynamics is statistically modeled by slow feature analysis. Control charts are established based on temporal variations of slow features. Contribution plots are adopted for diagnosis of control performance. Abstract: Recently, slow feature analysis (SFA), a novel dimensionality reduction technique, has been adopted for integrated monitoring of operating condition and process dynamics. By isolating temporal behaviors from steady-state information, the SFA-based monitoring scheme enables improved discrimination of nominal operating point changes from real faults. In this study, we demonstrate that the temporal dynamics is an additional indicator of control performance changes, and further exploit its unique efficacy in control performance monitoring. Because of its data-driven nature and ease from first-principle knowledge, the SFA-based monitoring scheme allows an overall assessment of the plant-wide control performance and is compatible with different control strategies. An attractive feature of the SFA-based approach compared to existing ones is that generic process monitoring indices are used, which renders contribution plots naturally applicable to real-time diagnosis of control performance. As a result, potential fault variables as root causes of control performance changes can be identified, including not only controlled variables (CV) but also manipulated variables (MV) and disturbance variables (DV). Simulated and experimental studies demonstrate the effectiveness of the proposed method.