A Dual-Mode Control with a RBF Network

[摘要] In this paper, a RBF network with Gaussians is adapted through a combination of switching and integral laws. The idea is taking the best features of each method. The hyperbolic tangent is used instead of signal function which reduces the chattering phenomenon. A hyperbolic secant is used to regulate the integral law, increasing its effects on steady state and reducing on transient. This method produces a smooth control signal with a significant chattering reduction or even its elimination, and a fast and less oscillatory system output. The process is in real time, and the error between the reference model and system outputs is the controlled variable. This strategy needs only measurements of input and output of the plant. Knowledge about parameters and disturbances is unnecessary too. A Lyapunov proof is presented for dual-mode method and comparisons through simulations.

[学科分类] 自动化工程

[关键词] Adaptive control ;Dual mode ;Neural network ;Radial basis functions