A Constrained Recursive Adaptive Predictive Control Method With Lagrange Polynomials

This paper proposes a constrained recursive adaptive predictive control (CRAPC) method to address the nonlinear, time‐varying, and constrained nature of industrial processes. It is considered that the system model, which is the online identification algorithm, is used to get the state‐space model. The state‐space model is obtained through the recursive method and SVD decomposition. The system model update strategy is determined by comparing the prediction errors and forgetting factor before and after updating the model. The model is subsequently applied to design the adaptive predictive controller. This process entails solving constraints via a quadratic program that employs Lagrange polynomials, thereby minimizing computational time. The proposed control method is applied to a continuous stirred tank heater (CSTH) system and a constrained model predictive control (CMPC) method regarding as a comparison. The advantages of the proposed approach are demonstrated by the simulation outcomes.