A comparison between CMAC neural network control and two traditional adaptive control systems

A comparison is made of a neural-network-based controller similar to the cerebellar model articulation controller (CMAC) and two traditional adaptive controllers, a self-tuning regulator (STR) and a Lyapunov-based model reference adaptive controller (MRAC). The three systems are compared conceptually and through simulation studies on the same low-order control problem. Results are obtained for the case where the system is linear and noise-free, for the case where noise is added to the system, and for the case where a nonlinear system is controlled. Comparisons are made with respect to closed-loop system stability, speed of adaptation, noise rejection, the number of required calculations, system tracking performance, and the degree of theoretical development. The results indicate that the neural network approach functions well in noise, works for linear and nonlinear systems, and can be implemented very efficiently for large-scale systems.<>