Abstract
Model reference adaptive control (MRAC) is widely used in linear system control areas, and Neural Networks (NN) is often used to extend MRAC to nonlinear areas. However, this kind of solution inherits some drawbacks of NN, including slow learning speed, weak generalization ability, local minima tendency, etc. Given these drawbacks, this paper attempts to use support vector regression (SVR) as a substitute of NN. In this approach, SVR is employed to compensate the nonlinear part of the plant. A stable controller-parameter adjustment mechanism is constructed by using the practical stability theory. Simulation results show that the proposed approach could reach desired performance.
Publisher
Trans Tech Publications, Ltd.
Reference18 articles.
1. Hang C C, Parks P C. Comparative Studies of Mode Reference Adaptive Control System[J]. IEEE Trans, Automatic Control, 1973, 18 (5): 419-428.
2. Lu J, Phuah J, Yahagi T. A Method of Mode Reference Adaptive Control for MIMO Nonlinear System Using Neural Networks[J]. IEICE Trans, Fundamentals, 2001, 84(8): 1933-(1941).
3. Rossomando F G, Soria C, Patino D, Carelli R. Model Reference Adaptive Control for Mobile Robots in Trajectory Tracking using Radial Basis Function Neural Networks[J]. Latin American Applied Research, 2011, 41(8 ): 177-182.
4. Elbuluk M E, Tong L, Husain I. Neural Network based Model Reference Adaptive Systems for High Performance Motor Drives and Motion Controls[J]. IEEE Trans, Industry Applications, 2000, 38(3): 879-886.
5. Tanaka Kanya, Yoshimura Yoshie. MRAC Combined Neural Networks for Ultra-Sonic Motor[J]. JSME International Journal Series-C, 2006, 49(4): 1084-1090.