Adaptive neural network control of hard disk drives with hysteresis friction nonlinearity

Phyo Phyo San, Beibei Ren, Shuzhi Sam Ge, Tong Heng Lee, Jin Kun Liu

Research output: Contribution to journalArticlepeer-review

43 Scopus citations

Abstract

In this brief, an adaptive neural network (NN) friction compensator is presented for servo control of hard disk drives (HDDs). The existence of the hysteresis friction nonlinearity from pivot bearing, which is represented as the LuGre hysteresis friction model here, increases the position error signal of read-write head and deteriorates the performance of HDD servo systems. To compensate for the effect of the hysteresis friction nonlinearity, NN is adopted to approximate its unknown bounding function. With the proposed control, all the closed-loop signals are ensured to be bounded while the tracking error converges into a neighborhood of zero. Comprehensive comparisons between the conventional proportional-integral-derivative control (without friction compensator) and the proposed adaptive NN control (with friction compensator) are provided in experiment results. It is shown that the proposed control can mitigate the effect of the hysteresis friction nonlinearity and improve the track seeking performance.

Original languageEnglish
Article number5415528
Pages (from-to)351-358
Number of pages8
JournalIEEE Transactions on Control Systems Technology
Volume19
Issue number2
DOIs
StatePublished - Mar 2011

Keywords

  • Adaptive control
  • Hard disk drive (HDD)
  • Hysteresis friction compensation
  • Neural networks (NNs)
  • Pivot

Fingerprint

Dive into the research topics of 'Adaptive neural network control of hard disk drives with hysteresis friction nonlinearity'. Together they form a unique fingerprint.

Cite this