The Fuzzy CMAC Based on RLS Algorithm

Abstract

In this paper, the structure of the fuzzy crebellar model articulation controller (FCMAC) neural network was discussed. The FCMAC can improve the accuracy of the CMAC. It also has excellent generalization ability and fault-tolerance ability. The recursive least squares (RLS) algorithm was introduced into the FCMAC. The FCMAC based on RLS algorithm has potential application prospect in the research of modeling and emulation on the complex systems.

Adaptive control over non­linear objects using the robust neural network FCMAC

“…A traditional CMAC network is trained using an error back propagation algorithm, minimizing quadratic functional from error ( ) e k based on the presentation of training pairs ( ) ( ), ( ) , x k y k 1,2,... k = [2,3,9]. The LSM solution, obtained in this case, which is asymptotically optimal with a minimum variance in the class of unbiased estimates, is based on the assumption that interference x is not correlated and follows a normal distribution law.…”