Stabilizing model predictive control using parameter-dependent dynamic policy for nonlinear systems modeled with neural networks. (December 2015)

• Record Type: Journal Article
• Authors: Gautam, Ajay; Soh, Yeng Chai
• Is Part Of: Journal of process control. Volume 36(2015:Dec.)
• Page Start: 11
• Page End: 21
• Publication Date: 2015-12
• Subjects: Model predictive control (MPC) -- Nonlinear MPC -- Neural-network-based MPC -- Gain-scheduled MPC -- Optimized dynamic policy -- Tubular reactor; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2015.09.003
• Languages: English
• ISSNs: 0959-1524

Abstract

Abstract : Highlights: Computationally efficient MPC for neural-network-modeled nonlinear systems. Proposed MPC design applicable for a family of operating points. Offline-optimized dynamic controller based on a LPV model used for terminalcontrol. Terminal controller parameterized quadratically in terms of time-varying parameter. Applicability illustrated for CSTR and distributed-parameter tubular reactor system. Abstract: A class of parameter-dependent dynamic control policies is explored for its use in a model predictive control (MPC) algorithm for a nonlinear system modeled with a feedforward neural network (NN). The NN-modeled system is expressed as a polytopic quasi-linear-parameter-varying (quasi-LPV) system over a region of the state-input space for a range of operating points, and the dynamics of the proposed policy, which are optimized off-line to enlarge the region of attraction, are allowed to depend on a time-varying parameter of the polytopic quasi-LPV system model such that the resulting control involves a continuous gain-scheduling that leads to reduced conservativeness. A complete MPC algorithm using the dynamic policy as the terminal policy ensures stabilization and improved control performance over a larger domain of attraction without a larger horizon length. Simulation examples with tank and tubular reactor systems illustrate the effective performance of the proposed approach in practical applications.