Fuzzy Broad Learning Adaptive Control for Voice Coil Motor Drivers

Chun Fei Hsu*, Bo Rui Chen, Bing Fei Wu

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

The position of a voice coil motor (VCM) driver is difficult to control in a stable and highly precise manner. To address these challenges, this study proposes a fuzzy broad learning adaptive control (FBLAC) system consisting of a fuzzy broad controller and a robust controller. The fuzzy broad controller uses a fuzzy broad-learning system (FBLS) to approximate an ideal controller online, and the robust controller is designed to keep the system stable. The gradient descent method and the chain rule are applied to adjust all the FBLS parameters online to increase its approximation and learning capacities. Furthermore, the experimental results demonstrate that the proposed FBLAC system has good tracking performance and uncertainty rejection properties. The main contributions of this study are as follows: (1) An FBLS with a simple structure and full-tuned parameter learning laws to improve its learning ability was investigated. (2) Stability analysis of the closed-loop FBLAC system was proved based on the gradient descent method and the Lyapunov stability theorem. (3) Several experimental evaluations and analyses were conducted to demonstrate the effectiveness of the proposed FBLAC method.

Original languageEnglish
JournalInternational Journal of Fuzzy Systems
DOIs
StateAccepted/In press - 2022

Keywords

  • Broad-learning system
  • Online parameter learning
  • Stability analysis
  • VCM driver

Fingerprint

Dive into the research topics of 'Fuzzy Broad Learning Adaptive Control for Voice Coil Motor Drivers'. Together they form a unique fingerprint.

Cite this