Skip to main navigation Skip to search Skip to main content

An active vibration isolation method based on CMAC network

  • Naval University of Engineering Wuhan

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Considering the nonlinearities in active vibration isolation system and the deficiencies of existing control methods, a novel method based on CMAC neural network is proposed. In the control structure, the CMAC network is adopted as controller, and the filtered-X concept is extended for use with the controller parameters update; a MLP network with taped line input is used to model the secondary path off line, thus parameters of the MLP network are combined with the error signal to jointly update the controller weights based on the stochastic gradient descent algorithm. Simulation results show the proposed method has good isolation performance for system with some nonlinearities.

Original languageEnglish
Title of host publicationProceedings of the 6th International Conference on Fluid Power Transmission and Control, ICFP 2005
EditorsYongxiang Lu, Qingfeng Wang, Li Wei
PublisherInernational Academic Publishers
Pages700-703
Number of pages4
ISBN (Electronic)7506274027, 9787506274029
StatePublished - 2005
Event6th International Conference on Fluid Power Transmission and Control, ICFP 2005 - Hangzhou, China
Duration: 5 Apr 20058 Apr 2005

Publication series

NameProceedings of the 6th International Conference on Fluid Power Transmission and Control, ICFP 2005

Conference

Conference6th International Conference on Fluid Power Transmission and Control, ICFP 2005
Country/TerritoryChina
CityHangzhou
Period5/04/058/04/05

Keywords

  • Active vibration isolation
  • CMAC network
  • Secondary path modelling

Fingerprint

Dive into the research topics of 'An active vibration isolation method based on CMAC network'. Together they form a unique fingerprint.

Cite this