Physically Consistent Machine Learning Models Using Artificial Data for MISO Systems and Model Predictive Control

Abstract This work presents a novel artificial data assisted machine learning modelling approach to guarantee the correct physical gain signs between manipulated variables (MV)/controlled variable (CV) in a multi-input-single-output (MISO) model predictive control system (MPC). These industrial systems, such as polymerization reacting systems, are basically controlled based on the operators’ experiences due the lack of the trustworthy models. The purpose of this work is to provide an implementable machine learning model for MPC purposed by the aid of artificial data. This approach is shown valid through a numerical problem, real plant test data and plant test.