Extended Prediction Error Approach for MPC Performance Monitoring and Industrial Applications

Performance monitoring and diagnosis of model predictive control systems (MPC) has been a great interest for both academia and industry. In recent years some novel approaches for multivariate control performance monitoring have been developed without the requirement of process models or interactor matrices. Among them the prediction error approach has shown to be a promising one, but it has certain limitations in applications. This paper further develops the prediction error approach for performance monitoring of model predictive control systems, and demonstrates its applications in two industrial MPC performance monitoring and diagnosis problems.