A neural network controller augmented to a high performance linear controller and its application to a HDD-track following servo system
Authors: | Herrmann Guido, University of Leicester, United Kingdom Ge Shuzhi Sam, National University of Singapore, Singapore Guo Guoxiao, A-Star Data Storage Institute, Singapore |
---|
Topic: | 4.2 Mechatronic Systems |
---|
Session: | Data Storage Devices and Micro-Actuation |
---|
Keywords: | hard-disk, servo-control, friction, compensation, neural networks |
---|
Abstract
The performance of a linear, discrete high performance track following controller in a hard disk drive is improved for its disturbance rejection by augmentation of a discrete adaptive neural network (NN) element. The neural network element is deemed to be particularly effective for rejection of bias forces, such as friction. Theoretical and experimental results have been obtained: It is shown theoretically that a NN-element is effective in counteracting a non-linear, model-dependent disturbance. The disturbance is assumed to be unknown, with the exception that the disturbance is known to be matched to the plant actuator input range and the disturbance is an (unknown) continuous function of the plant output measurements. In an experiment for a HDD-servo system, it is shown that the NN-control element improves performance and appears particularly effective for a small number of NN-nodes.