A Model Predictive Control Performance Monitoring and Grading Strategy Based on Improved Slow Feature Analysis

Abstract

Slow feature analysis (SFA) has been adopted for control performance monitoring (CPM) recently. However, due to the selection criterion of the dominant slow features (SFs) and the performance monitoring statistics, the traditional SFA-based CPM method has certain limitations in monitoring model predictive control (MPC) performance and fails to distinguish the direction of performance change, i.e., whether the performance becomes better or worse. In order to solve the above problems, an MPC performance monitoring and grading strategy based on improved SFA is proposed in this paper. First, a new criterion for selecting dominant SFs is proposed. On this basis, two combined monitoring indices are built to monitor steady-state and dynamic characteristics of MPC systems, respectively. Besides, an SFA-based predictable performance assessment index is proposed to indicate the direction of performance change. Finally, a performance grading strategy based on improved SFA is established to classify current MPC performance to four levels. Two simulation examples demonstrate the effectiveness and superiority of the proposed method.