Wavelet Neural Network Observer Based Adaptive Tracking Control for Two Degree of Freedom Piezo-Electric Actuated Nonlinear Metal Cutting Process Using Reinforcement Learning

Abstract

This paper is concerned with the observer designing problem for the suppression of chatter occurrence due to the existence of hysteresis and time delay in an uncertain two degree of freedom piezo-electric actuated metal cutting is proposed and the novelty is that the Wavelet Neural networks (WNN) observer using reinforcement learning is first incorporated into the controller design for a metal cutting system. An adaptive control strategy is proposed to suppress the undesirable chattering in the turning process. A piezoactuator is introduced for the regulation of the cutting tool displacement as its structure is independent of the tool holder in the machine. Reinforcement learning is used via two Wavelet Neural networks (WNN), critic WNN and action WNN, which are combined to form an adaptive WNN controller. The “strategic” utility function is approximated by the critic WNN and is minimized by the action WNN. Adaptation laws are developed for the online tuning of wavelets parameters. By Lyapunov approach, the uniformly ultimate boundedness of the closed-loop tracking error is verified. Finally, a simulation is performed to verify the effectiveness and performance of the proposed method in eliminating the chattering.