Simultaneous online model identification and production optimization using modifier adaptation. (February 2022)

• Record Type: Journal Article
• Authors: Matias, José; Kungurtsev, Vyacheslav; Egan, Malcolm
• Is Part Of: Journal of process control. Volume 110(2022)
• Page Start: 110
• Page End: 120
• Publication Date: 2022-02
• Subjects: Real-time optimization -- Modifier adaptation -- Reinforcement learning -- Process monitoring; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2021.12.009
• Languages: English
• ISSNs: 0959-1524

Abstract

Abstract: A key problem for many industrial processes is to limit exposure to system malfunction. The system health state can be represented by different models. However, it is often the case that control cost minimization is prioritized over model identification. Indeed, model identification is typically not considered in production optimization, which can lead to delayed awareness and alerting of malfunction. In this paper, we address the problem of simultaneous production optimization and system identification. We develop new algorithms based on modifier adaptation and reinforcement learning, which efficiently manage the tradeoff between cost minimization and identification. For two case studies based on a chemical reactor and subsea oil and gas exploration, we show that our algorithms yield control costs comparable to existing methods while yielding rapid identification of system degradation. Highlights: Connection between modifier adaptation (MA) and reinforcement learning. Identify model based on available set while selecting best-performing inputs. Two algorithms for efficiently managing exploration and exploitation tradeoff. Algorithm 1: extending MA with a Bayesian belief update rule to address the tradeoff. Algorithm 2: address the tradeoff by regularization with Jensen–Shannon divergence.