A novel non-linear model predictive controller based on minimal resource allocation network and its application in CSTR PH process

In this paper, a novel predictive controller based on minimal resource allocation network for non-linear system is presented. The controller combines the advantages of MRAN and neural predictor. The implemented neural predictive controller not only effectively eliminates the most significant obstacles but also be very robustness. At last, the algorithm is applied in a high non-linear Continuous Stirred Tank Reactor (CSTR) pH process model and presents a better real-time control effect.