A KPI-based process monitoring and fault detection framework for large-scale processes. (May 2017)

• Record Type: Journal Article
• Authors: Zhang, Kai; Shardt, Yuri A.W.; Chen, Zhiwen; Yang, Xu; Ding, Steven X.; Peng, Kaixiang
• Is Part Of: ISA transactions. Volume 68(2017:May)
• Page Start: 276
• Page End: 286
• Publication Date: 2017-05
• Subjects: KPI -- Large-scale -- Process monitoring -- Least square -- Data-driven subspace; Engineering instruments -- Periodicals; Engineering instruments; Periodicals; Electronic journals; 629.805
• DOI: 10.1016/j.isatra.2017.01.029
• Languages: English
• ISSNs: 0019-0578

Abstract

Abstract: Large-scale processes, consisting of multiple interconnected subprocesses, are commonly encountered in industrial systems, whose performance needs to be determined. A common approach to this problem is to use a key performance indicator (KPI)-based approach. However, the different KPI-based approaches are not developed with a coherent and consistent framework. Thus, this paper proposes a framework for KPI-based process monitoring and fault detection (PM-FD) for large-scale industrial processes, which considers the static and dynamic relationships between process and KPI variables. For the static case, a least squares-based approach is developed that provides an explicit link with least-squares regression, which gives better performance than partial least squares. For the dynamic case, using the kernel representation of each subprocess, an instrument variable is used to reduce the dynamic case to the static case. This framework is applied to the TE benchmark process and the hot strip mill rolling process. The results show that the proposed method can detect faults better than previous methods. Abstract : Highlights: Key performance indicators (KPIs) form an important component for process monitoring of industrial systems. Both partial least-squares (PLS) and traditional, least-squares can be used to build the data-driven models. This paper shows that for static KPI systems traditional, least-squares approach is better than PLS. For the dynamic case, an instrument variable can be used to reduce this case to the static situation. Simulations on the TE and hot-strip, rolling mill process show that the faults are detected faster and better using the proposed method.