Intelligent semi-active vehicle suspension systems using neural networks

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

A methodology is proposed for designing intelligent vehicle suspension systems which implement the magneto-rheological damper as an active element. The adaptive control law is constructed based on the neural network methodology and Taylor series approximation. The controller commands the current of the magneto-rheological damper and controls directly the damper force. The neural network is trained with respect to a developed road disturbance scenario and its parameters are obtained using a global numerical optimisation technique. The proposed control law has a novel structure capable of sensing the interactions between the variables and thus can adjust the feedback gains with respect to the existing conditions. It takes into consideration the actuator's dynamics and avoids limit cycling which is caused by the hysteretic behaviour of the MR dampers. The performance of the intelligent system is evaluated by means of simulations in MATLAB for quarter and half car models.

Original languageEnglish
Pages (from-to)135-158
Number of pages24
JournalInternational Journal of Vehicle Systems Modelling and Testing
Volume7
Issue number2
DOIs
Publication statusPublished - 2012
Externally publishedYes

Fingerprint

Magnetorheological Damper
Vehicle suspensions
Neural Networks
Neural networks
Intelligent Vehicle
Intelligent vehicle highway systems
Taylor series
Methodology
Numerical Optimization
Damper
Cycling
Intelligent systems
Intelligent Systems
Numerical Techniques
Adaptive Control
Global Optimization
Optimization Techniques
MATLAB
Actuator
Sensing

Keywords

  • Intelligent semi-active vibration control
  • Magneto-rheological damper
  • Neural networks
  • NNs

ASJC Scopus subject areas

  • Modelling and Simulation
  • Automotive Engineering

Cite this

@article{23d2c0e5ba014010a04eb8a6572a795d,
title = "Intelligent semi-active vehicle suspension systems using neural networks",
abstract = "A methodology is proposed for designing intelligent vehicle suspension systems which implement the magneto-rheological damper as an active element. The adaptive control law is constructed based on the neural network methodology and Taylor series approximation. The controller commands the current of the magneto-rheological damper and controls directly the damper force. The neural network is trained with respect to a developed road disturbance scenario and its parameters are obtained using a global numerical optimisation technique. The proposed control law has a novel structure capable of sensing the interactions between the variables and thus can adjust the feedback gains with respect to the existing conditions. It takes into consideration the actuator's dynamics and avoids limit cycling which is caused by the hysteretic behaviour of the MR dampers. The performance of the intelligent system is evaluated by means of simulations in MATLAB for quarter and half car models.",
keywords = "Intelligent semi-active vibration control, Magneto-rheological damper, Neural networks, NNs",
author = "Kanarachos, {Stratis A.}",
year = "2012",
doi = "10.1504/IJVSMT.2012.048444",
language = "English",
volume = "7",
pages = "135--158",
journal = "International Journal of Vehicle Systems Modelling and Testing",
issn = "1745-6436",
publisher = "Inderscience",
number = "2",

}

TY - JOUR

T1 - Intelligent semi-active vehicle suspension systems using neural networks

AU - Kanarachos, Stratis A.

PY - 2012

Y1 - 2012

N2 - A methodology is proposed for designing intelligent vehicle suspension systems which implement the magneto-rheological damper as an active element. The adaptive control law is constructed based on the neural network methodology and Taylor series approximation. The controller commands the current of the magneto-rheological damper and controls directly the damper force. The neural network is trained with respect to a developed road disturbance scenario and its parameters are obtained using a global numerical optimisation technique. The proposed control law has a novel structure capable of sensing the interactions between the variables and thus can adjust the feedback gains with respect to the existing conditions. It takes into consideration the actuator's dynamics and avoids limit cycling which is caused by the hysteretic behaviour of the MR dampers. The performance of the intelligent system is evaluated by means of simulations in MATLAB for quarter and half car models.

AB - A methodology is proposed for designing intelligent vehicle suspension systems which implement the magneto-rheological damper as an active element. The adaptive control law is constructed based on the neural network methodology and Taylor series approximation. The controller commands the current of the magneto-rheological damper and controls directly the damper force. The neural network is trained with respect to a developed road disturbance scenario and its parameters are obtained using a global numerical optimisation technique. The proposed control law has a novel structure capable of sensing the interactions between the variables and thus can adjust the feedback gains with respect to the existing conditions. It takes into consideration the actuator's dynamics and avoids limit cycling which is caused by the hysteretic behaviour of the MR dampers. The performance of the intelligent system is evaluated by means of simulations in MATLAB for quarter and half car models.

KW - Intelligent semi-active vibration control

KW - Magneto-rheological damper

KW - Neural networks

KW - NNs

U2 - 10.1504/IJVSMT.2012.048444

DO - 10.1504/IJVSMT.2012.048444

M3 - Article

VL - 7

SP - 135

EP - 158

JO - International Journal of Vehicle Systems Modelling and Testing

JF - International Journal of Vehicle Systems Modelling and Testing

SN - 1745-6436

IS - 2

ER -