Neural-Fuzzy Control of Chemical Technological Processes

By continuous improvement of the intelligent control systems achieves more accurate values of the controlled parameters which lead to the more effective control, entirely. This paper presents the intelligent control system design via the combination of the predictive and the neural-fuzzy controller type of ANFIS. The neural-fuzzy controller works in parallel with the predictive controller. This controller adjusts the output of the predictive controller, in order to enhance the predicted inputs. The performance of our proposal is demonstrated on the chemical reactor control problem. Experimental results confirmed control quality improvement in the combined controller over the original predictive and PID controller.