Abstract
A new self-tuning neuro-proportional+integral+derivative (PID) controller is proposed and applied to position control of the magnetic head in a hard disk drive. The proportional, integral, and derivative gains are tuned using two types of neural network, which reduces the burden of trial and error by human operators. Simulation results show the effectiveness of the proposed method over several conventional control methods.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Miller WT III, Sutton RS, Werbos PJ (1990) Neural networks for control. MIT Press, Cambridge
White DA, Sofge DA (eds) (1992) Handbook of intelligent control: neural, fuzzy, and adaptive approaches. Van Nostrand Reinhold, New York
Omatu S, Marzuki K, Rubiyah Y (1995) Neuro-control and its applications. Springer, London.
Mita T (1994)H ∞ control (in Japanese), Shokodo, Tokyo
Tomizuka M, Chin T, Kia C (1989) Analysis and synthesis of discrete-time repetitive, controllers. ASME J Dyn Syst Meas Control 111:353–358
Kobayashi M, Yamaguchi T, Hirai H, et al. (1996) Adaptive control of a hybrid servo system for magnetic disk drives. JSME Int J Ser C 39:772–780
Author information
Authors and Affiliations
Corresponding author
About this article
Cite this article
Fujinaka, T., Yoshioka, M. & Omatu, S. An intelligent approach to position control of a hard disk drive. Artif Life Robotics 5, 15–19 (2001). https://doi.org/10.1007/BF02481315
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF02481315