Learning of model-plant mismatch map via neural network modeling and its application to offset-free model predictive control. (July 2022)

• Record Type: Journal Article
• Authors: Son, Sang Hwan; Kim, Jong Woo; Oh, Tae Hoon; Jeong, Dong Hwi; Lee, Jong Min
• Is Part Of: Journal of process control. Volume 115(2022)
• Page Start: 112
• Page End: 122
• Publication Date: 2022-07
• Subjects: Model predictive control -- Artificial neural network -- Model-plant mismatch -- Offset-free tracking; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2022.04.014
• Languages: English
• ISSNs: 0959-1524

Abstract

Abstract: We propose an improved offset-free model predictive control (MPC) framework, which learns and utilizes the intrinsic model-plant mismatch map, to effectively exploit the advantages of model-based and data-driven control strategies and overcome the limitation of each approach. In this study, the model-plant mismatch map on steady-state manifold is approximated via artificial neural network (ANN) modeling based on steady-state data from the process. Though the learned model-plant mismatch map can provide the information at the equilibrium point (i.e., setpoint), it cannot provide model-plant mismatch information during transient state. To handle this, we additionally apply a supplementary disturbance variable which is updated from a revised disturbance estimator considering the disturbance value obtained from the learned model-plant mismatch map. Then, the learned and supplementary disturbance variables are applied to the target problem and finite-horizon optimal control problem of the offset-free MPC framework. By this, the control system can utilize both the learned model-plant mismatch information and the stabilizing property of the nominal disturbance estimator. The closed-loop simulation results demonstrate that the proposed offset-free MPC scheme utilizing the model-plant mismatch map learned via ANN modeling efficiently improves the closed-loop reference tracking performance of the control system. Additionally, the zero-offset tracking condition of the developed framework is mathematically examined. Highlights: An improved offset-free model predictive control framework is proposed. Intrinsic model-plant mismatch map is approximated via neural network modeling. Learned model-plant mismatch map is utilized in an offset-free control framework. Proposed scheme efficiently improved the closed-loop reference-tracking performance. Zero-offset tracking condition of the developed framework is mathematically examined.