Adaptive neuro-fuzzy control system by RBF and GRNN neural networks

Recently, adaptive control systems utilizing artificial intelligent techniq ues are being actively investigated in many applications. Neural networks w ith their powerful learning capability are being sought as the basis for ma ny adaptive control systems where on-line adaptation can be implemented. Fu zzy logic, on the other hand, has proved to be rather popular in many contr ol system applications due to providing a rule-base like structure. In this paper, an adaptive neuro-fuzzy control system is proposed in which the Rad ial Basis Function neural network (RBF) is implemented as a neuro-fuzzy con troller (NFC) and the General Regression neural network (GRNN) as a predict or. The adaptation of the system involves the following three procedures: ( 1) tuning of the control actions or rules, (2) trimming of the control acti ons, and (3) adjustment of the controller output gain. The tuning method is a non-gradient descent method based on the predicted system response which is able to self-organize the control actions from the initial stage. The t rimming scheme can help to reduce the aggressiveness of the particular cont rol rules such that the response is stabilized to the set-points more effec tively, while the controller gain adjustment scheme can be applied in the c ases where the appropriate controller output gain is difficult to determine heuristically. To show the effectiveness of this methodology its performan ce is compared with the well known Generalized Predictive Control (GPC) tec hnique which is a combination of both adaptive and predictive control schem es. Comparisons are made with respect to the transient response, disturbanc e rejection and changes in plant dynamics. The proposed control system is a lso applied in controlling a single link manipulator. The results show that it exhibits robustness and good adaptation capability which can be practic ally implemented.