Robust CMAC neural network control for LLCC resonant driving linear piezoelectric ceramic motor

Abstract

The authors present a robust cerebellar-model-articulation-computer (CMAC) neural network control system for a linear piezoelectric ceramic motor (LPCM) driven by a two-inductance two-capacitance (LLCC) resonant inverter. The motor structure and the LLCC resonant driving circuit of a LPCM are introduced first. Since the dynamic characteristics and motor parameters of the LPCM are highly nonlinear and time-varying, a robust CMAC neural network control system is therefore designed based on a hypothetical dynamic model to achieve high-precision position control. The LLCC resonant driving circuit is first designed to operate at an optimal switching frequency so that the output voltage will not be affected by the variation of quality factor. Next, the stability of a robust CMAC neural network control system can be ensured without any strict constraint and without much previous knowledge required. It can also be widely applied to other controlling problems. The effectiveness of the proposed driving circuit and control system is verified by the results taken from some experiments in this study under the occurrence of uncertainties. Furthermore, the advantages of the proposed control scheme are indicated in comparison with a traditional proportional integral position control system.