Two-Degree-of-Freedom Control of a Self-Sensing Micro-Actuator for HDD using Neural Networks

Abstract

The present paper describes a two-degree-of-freedom control of a self-sensing micro-actuator for a dual-stage hard disk drive using neural networks. The two-degree-of-freedom control system is comprised of a feedforward controller and a feedback controller. Two neural networks are developed for the two-degree-of-freedom control system, one for the inverse dynamic model for the feedforward controller and one for system identification for the generation of the desired self-sensing signal. The feedback controller can realize the identified self-sensing signal. The micro-actuator uses a PZT actuator pair, installed on the assembly of the suspension. The self-sensing micro-actuator can be used to form a combined actuation and sensing mechanism. Experimental results show that the neural network approach can be used effectively for the control and identification of the self-sensing micro-actuator system