摘要：AbstractAdvanced model-based control strategies like Model Predictive Control can offer superior control of key process variables for multiple-input multiple-output systems. The quality of the system model is critical to controller performance and should adequately describe the process dynamics across its operating range while remaining amenable to fast optimization. Mechanistic models might be difficult to construct or might evaluate too slowly for fast-sampling purposes, while System Identification methods that yield linear models might only offer effective control within a limited range. This work thus articulates an integrated System Identification procedure for deriving black-box nonlinear continuous-time multiple-input multiple-output system models for Nonlinear Model Predictive Control. In this piece, seven candidate models were trained on data sets generated from two different methods and integrated into a Nonlinear Model Predictive Controller for a highly nonlinear Continuous Stirred Tank Reactor system. This procedure successfully identified system models that enabled effective control in both servo and regulator problems across wider operating ranges, given that the data set is sufficiently uniform across the operating range. These results were subsequently built upon in a follow-up work. This demonstration of how such system models could be identified for Nonlinear Model Predictive Control without prior knowledge of system dynamics opens further possibilities for direct data-driven methodologies for model-based control which, in the face of process uncertainties or modeling limitations, allow rapid and stable control over wider operating ranges.
关键词：KeywordsNonlinear model predictive controlblack-box modelingsystem identificationmachine learningindustrial applications of process control
