Adaptive hybrid control for linear piezoelectric ceramic motor using recurrent CMAC network

In this study, an adaptive hybrid control system using a new cerebellar model articulation controller (CMAC) network paradigm called recurrent CMAC (RCMAC) network, which is proposed to control the moving table of the linear piezoelectric ceramic motor (LPCM) drive system to achieve high-precision position control with robustness. The architecture of RCMAC network is a modified model of the CMAC network to attain a small number of receptive fields. In the proposed controller, the Lyapunov stability theorem and the gradient descent method are adopted to train the RCMAC network on-line using the proposed adaptive update laws. Moreover, to relax the requirement for the bounds of minimum approximation error and Taylor high-order terms, a simple adaptive bound algorithm is utilized to estimate the mentioned bound. The effectiveness of the control system is verified by experimental results in the presence of uncertainties.