Intelligent High Speed Control of Piezoelectric Actuators for Precision Manufacturing

A major limitation of piezoelectric actuators is their lack of accuracy due to hysteresis, drift, and creep nonlinearities. The maximum error due to these nonlinearities can be as much as 10-15% of the path covered if the actuators are not under closed-loop control. In this proposal, we present a novel closed-loop control approach to compensate for the hysteresis and creep nonlinearities. The controller consists of a feedforward loop and a feedback loop. In the feedforward controller, a novel neural network called Fuzzy CMAC (Cerebellar Model Arithmetic Computer) will be used to generate certain desired voltages to the piezoelectric actuator to compensate for the nonlinearities in the actuator. The Fuzzy CMAC inherits preferred features of arbitrary function approximation, self learning, and parallel processing from the original CMAC neural network, and the capability of acquiring and incorporating human knowledge into a system and the capability of processing information based on fuzzy inference rules from the fuzzy logic. Our learning rates are at least an order of magnitude faster than conventional neural nets. The inputs to the Fuzzy CMAC are the desired trajectories that the actuator wants to follow. Since the cancellation of nonlinearities by the feedforward controller may not be perfect, a feedback loop is then used to reduce the tracking error even further. The feedback controller will be a simple PID controller. One major advantage of our proposed scheme is that, once the Fuzzy CMAC neural network controller has learned the nonlinear dynamics of the actuator, any arbitrary type of desired trajectory can be tracked.