Design of a non-linear hybrid car suspension system using neural networks

Konstantinos Spentzas, Stratis A. Kanarachos

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

A methodology for the design of active/hybrid car suspension systems with the goal to maximize passenger comfort (minimization of passenger acceleration) is presented. For this reason, a neural network (NN) controller is proposed, who corresponds to a Taylor series approximation of the (unknown) non-linear control function and the NN is due to the numerous local minima trained using a semi-stochastic parameter optimization method. Two cases A and B (continuous and discontinuous operation) are investigated and numerical examples illustrate the design methodology.

Original languageEnglish
Pages (from-to)369-378
Number of pages10
JournalMathematics and Computers in Simulation
Volume60
Issue number3-5
Early online date20 Mar 2002
DOIs
Publication statusPublished - 30 Sep 2002
Externally publishedYes

Fingerprint

Railroad cars
Neural Networks
Neural networks
Taylor series
Control Function
Stochastic Optimization
Parameter Optimization
Nonlinear Control
Local Minima
Nonlinear Function
Design Methodology
Optimization Methods
Maximise
Controller
Unknown
Numerical Examples
Controllers
Methodology
Approximation
Design

Keywords

  • Hybrid car suspension
  • Neural networks
  • Semi-stochastic optimization

ASJC Scopus subject areas

  • Information Systems and Management
  • Control and Systems Engineering
  • Applied Mathematics
  • Computational Mathematics
  • Modelling and Simulation

Cite this

Design of a non-linear hybrid car suspension system using neural networks. / Spentzas, Konstantinos; Kanarachos, Stratis A.

In: Mathematics and Computers in Simulation, Vol. 60, No. 3-5, 30.09.2002, p. 369-378.

Research output: Contribution to journalArticle

@article{fd4a767749b24bcda5fa1e1e7a676a15,
title = "Design of a non-linear hybrid car suspension system using neural networks",
abstract = "A methodology for the design of active/hybrid car suspension systems with the goal to maximize passenger comfort (minimization of passenger acceleration) is presented. For this reason, a neural network (NN) controller is proposed, who corresponds to a Taylor series approximation of the (unknown) non-linear control function and the NN is due to the numerous local minima trained using a semi-stochastic parameter optimization method. Two cases A and B (continuous and discontinuous operation) are investigated and numerical examples illustrate the design methodology.",
keywords = "Hybrid car suspension, Neural networks, Semi-stochastic optimization",
author = "Konstantinos Spentzas and Kanarachos, {Stratis A.}",
year = "2002",
month = "9",
day = "30",
doi = "10.1016/S0378-4754(02)00029-0",
language = "English",
volume = "60",
pages = "369--378",
journal = "Mathematics and Computers in Simulation",
issn = "0378-4754",
publisher = "Elsevier",
number = "3-5",

}

TY - JOUR

T1 - Design of a non-linear hybrid car suspension system using neural networks

AU - Spentzas, Konstantinos

AU - Kanarachos, Stratis A.

PY - 2002/9/30

Y1 - 2002/9/30

N2 - A methodology for the design of active/hybrid car suspension systems with the goal to maximize passenger comfort (minimization of passenger acceleration) is presented. For this reason, a neural network (NN) controller is proposed, who corresponds to a Taylor series approximation of the (unknown) non-linear control function and the NN is due to the numerous local minima trained using a semi-stochastic parameter optimization method. Two cases A and B (continuous and discontinuous operation) are investigated and numerical examples illustrate the design methodology.

AB - A methodology for the design of active/hybrid car suspension systems with the goal to maximize passenger comfort (minimization of passenger acceleration) is presented. For this reason, a neural network (NN) controller is proposed, who corresponds to a Taylor series approximation of the (unknown) non-linear control function and the NN is due to the numerous local minima trained using a semi-stochastic parameter optimization method. Two cases A and B (continuous and discontinuous operation) are investigated and numerical examples illustrate the design methodology.

KW - Hybrid car suspension

KW - Neural networks

KW - Semi-stochastic optimization

UR - http://www.scopus.com/inward/record.url?scp=0037201108&partnerID=8YFLogxK

U2 - 10.1016/S0378-4754(02)00029-0

DO - 10.1016/S0378-4754(02)00029-0

M3 - Article

VL - 60

SP - 369

EP - 378

JO - Mathematics and Computers in Simulation

JF - Mathematics and Computers in Simulation

SN - 0378-4754

IS - 3-5

ER -