Adaptive-Predictive Control with Intelligent Virtual Sensor

This paper is concerned with a development of an alternative intelligent control strategy, which is an integration between adaptive-predictive based controller and intelligent virtual sensing system. This allows an immeasurable variable to be inferred and used for control. The neuro-fuzzy approach is used for modelling the process as it has learning capability from the numerical data obtained from the measurements and subsequently used as process model in the predictive control scheme. The intelligent virtual sensor is composed of the Diagonal Recurrent Neural Network (DRNN) and the Extended Kalman Filter (EKF) as the estimator with inputs from DRNN. This integration enables the development of an on-line control scheme involving the immeasurable variable. Experimental results show some potential benefits on applying the proposed technique to the real-world process plant