Feedforward control based on neural networks for disturbance rejection in hard disk drives

Abstract

A feedforward control based on neural networks to attenuate the effect of external vibrations on the positioning accuracy of hard disk drives (HDDs) is presented. The adaptive neural network compensator utilises accelerometer signals to detect external vibrations. No information on the plant, sensor and disturbance dynamics is needed in the design of the adaptive neural network compensator. The stability of the proposed scheme is analysed by the Lyapunov criterion. Experimental results show that the tracking performance of HDDs can be improved significantly by using the feedforward controller when compared with the case without compensation. © The Institution of Engineering and Technology 2009.