A Study of Adaptive Control Based on CMAC Neural Network

Over the last few years, the study in adaptive
intelligent control utilizing Fuzzy, Neural Network
for a class of unknown nonlinear systems has
attracted considerable attention. In this book, a
new hybrid adaptive cerebeller model articulation
controller (CMAC) sliding mode control system is
developed. The hybrid adaptive CMAC sliding mode
controller (HACSMC) uses the direct and indirect
adaptive CMAC controllers to perform the equivalent
control of sliding mode control (SMC). Two types of
methods, sign function switching controller and CMAC
switching controller are proposed to design the
switching control law of SMC. In addition, the
adaptive laws of the control system are derived in
the sense of Lyapunov theorem, so that the stability
of the system can be guaranteed. Finally, the
proposed control system is applied to inverted
pendulum system and Chua s chaotic circuit. The
simulation results show that the HACSMC can not only
make control system have good tracking performance
and strong robustness but also have more flexibility
during the design process.

Autorentext
Cheng Ching-Lung was born in Taiwan, on October 12, 1980. He
received the B. S. degree from Tungnan University and the M.S.
degree from Tatung University, Taiwan, both in electrical
engineering. Since 2006, he has been an electronic engineer at
Shuttle.Inc. His research interests include adaptive control
system and artificial intelligence.