A neural network approach to the design of a vehicle's non-linear hybrid suspension system

K. N. Spentzas, S. A. Kanarachos

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

In the following, a design method is presented for non-linear hybrid suspension systems of vehicles based on neural networks. A hybrid suspension system is one that behaves as an active suspension system only when the road excitation amplitude is above a prescribed value. Discontinuous operation of the controller helps to minimize the energy consumed by the actuator. The design targets of our method are the minimization of the vertical acceleration imposed on the passengers as well as the respect of all the design and construction constraints. The neural network used is obtained by a Taylor approximation of the unknown non-linear control function. Because of the existence of numerous local minima of the neural network, an evolutionary algorithm is used to solve the resulting neural network problem.

Original languageEnglish
Pages (from-to)833-838
Number of pages6
JournalProceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture
Volume216
Issue number5
DOIs
Publication statusPublished - 1 May 2002
Externally publishedYes

Fingerprint

Neural networks
Active suspension systems
Evolutionary algorithms
Actuators
Controllers

Keywords

  • Neural networks
  • Semistochastic optimization
  • Vehicles' hybrid suspension
  • Vehicles' suspension

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering
  • Mechanical Engineering

Cite this

@article{c7fe07ca14344ba9a34128167f3daab6,
title = "A neural network approach to the design of a vehicle's non-linear hybrid suspension system",
abstract = "In the following, a design method is presented for non-linear hybrid suspension systems of vehicles based on neural networks. A hybrid suspension system is one that behaves as an active suspension system only when the road excitation amplitude is above a prescribed value. Discontinuous operation of the controller helps to minimize the energy consumed by the actuator. The design targets of our method are the minimization of the vertical acceleration imposed on the passengers as well as the respect of all the design and construction constraints. The neural network used is obtained by a Taylor approximation of the unknown non-linear control function. Because of the existence of numerous local minima of the neural network, an evolutionary algorithm is used to solve the resulting neural network problem.",
keywords = "Neural networks, Semistochastic optimization, Vehicles' hybrid suspension, Vehicles' suspension",
author = "Spentzas, {K. N.} and Kanarachos, {S. A.}",
year = "2002",
month = "5",
day = "1",
doi = "10.1243/0954405021520364",
language = "English",
volume = "216",
pages = "833--838",
journal = "Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture",
issn = "0954-4054",
publisher = "SAGE Publications",
number = "5",

}

TY - JOUR

T1 - A neural network approach to the design of a vehicle's non-linear hybrid suspension system

AU - Spentzas, K. N.

AU - Kanarachos, S. A.

PY - 2002/5/1

Y1 - 2002/5/1

N2 - In the following, a design method is presented for non-linear hybrid suspension systems of vehicles based on neural networks. A hybrid suspension system is one that behaves as an active suspension system only when the road excitation amplitude is above a prescribed value. Discontinuous operation of the controller helps to minimize the energy consumed by the actuator. The design targets of our method are the minimization of the vertical acceleration imposed on the passengers as well as the respect of all the design and construction constraints. The neural network used is obtained by a Taylor approximation of the unknown non-linear control function. Because of the existence of numerous local minima of the neural network, an evolutionary algorithm is used to solve the resulting neural network problem.

AB - In the following, a design method is presented for non-linear hybrid suspension systems of vehicles based on neural networks. A hybrid suspension system is one that behaves as an active suspension system only when the road excitation amplitude is above a prescribed value. Discontinuous operation of the controller helps to minimize the energy consumed by the actuator. The design targets of our method are the minimization of the vertical acceleration imposed on the passengers as well as the respect of all the design and construction constraints. The neural network used is obtained by a Taylor approximation of the unknown non-linear control function. Because of the existence of numerous local minima of the neural network, an evolutionary algorithm is used to solve the resulting neural network problem.

KW - Neural networks

KW - Semistochastic optimization

KW - Vehicles' hybrid suspension

KW - Vehicles' suspension

UR - http://www.scopus.com/inward/record.url?scp=0036275689&partnerID=8YFLogxK

U2 - 10.1243/0954405021520364

DO - 10.1243/0954405021520364

M3 - Article

VL - 216

SP - 833

EP - 838

JO - Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture

JF - Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture

SN - 0954-4054

IS - 5

ER -