Design of artificial neural network using particle swarm optimisation for automotive spring durability

Y. S. Kong, S. Abdullah, D. Schramm, M. Z. Omar, S. M. Haris

Research output: Contribution to journalArticle

Abstract

This paper presents the optimisation of spring fatigue life based on an artificial neural network (ANN) architecture and particle swarm optimisation algorithm (PSO) using ISO 2631 vertical vibration as input. The road-induced vibration of a ground vehicle caused the spring to fail due to fatigue and human discomfort. Hence, there is a need to model the relationship between these two parameters for spring design assistance. Vibration and force signals were extracted from a quarter car model simulation for fatigue life and ISO 2631 vertical vibration estimations. PSO was applied to the datasets for ANN weights and biases adjustments while the mean squared error (MSE) was set as the objective function. For validation purposes, a set of independent datasets was applied to the ANN. The residuals were analysed using Lilliefors normality and error histogram. For prediction accuracy, the predicted fatigue lives were analysed using scatter band approach and compared with traditional trained ANN. The results have shown that most of the PSO-based ANN predicted fatigue lives were in the acceptable region and the root mean square error (RMSE) value of 0.6391 life cycles in natural logarithm was obtained. The PSO-based ANN has shown improved performance compared to the conventional ANN approach in predicting fatigue life.

Original languageEnglish
Pages (from-to)5137-5145
Number of pages9
JournalJournal of Mechanical Science and Technology
Volume33
Issue number11
DOIs
Publication statusPublished - 1 Nov 2019

Fingerprint

Particle swarm optimization (PSO)
Durability
Neural networks
Fatigue of materials
Ground vehicles
Network architecture
Mean square error
Life cycle
Railroad cars

Keywords

  • Artificial neural network
  • Fatigue life
  • Particle swarm optimization
  • Vertical vibration

ASJC Scopus subject areas

  • Mechanics of Materials
  • Mechanical Engineering

Cite this

Design of artificial neural network using particle swarm optimisation for automotive spring durability. / Kong, Y. S.; Abdullah, S.; Schramm, D.; Omar, M. Z.; Haris, S. M.

In: Journal of Mechanical Science and Technology, Vol. 33, No. 11, 01.11.2019, p. 5137-5145.

Research output: Contribution to journalArticle

@article{27406056ee7445b98f20d8174def58a4,
title = "Design of artificial neural network using particle swarm optimisation for automotive spring durability",
abstract = "This paper presents the optimisation of spring fatigue life based on an artificial neural network (ANN) architecture and particle swarm optimisation algorithm (PSO) using ISO 2631 vertical vibration as input. The road-induced vibration of a ground vehicle caused the spring to fail due to fatigue and human discomfort. Hence, there is a need to model the relationship between these two parameters for spring design assistance. Vibration and force signals were extracted from a quarter car model simulation for fatigue life and ISO 2631 vertical vibration estimations. PSO was applied to the datasets for ANN weights and biases adjustments while the mean squared error (MSE) was set as the objective function. For validation purposes, a set of independent datasets was applied to the ANN. The residuals were analysed using Lilliefors normality and error histogram. For prediction accuracy, the predicted fatigue lives were analysed using scatter band approach and compared with traditional trained ANN. The results have shown that most of the PSO-based ANN predicted fatigue lives were in the acceptable region and the root mean square error (RMSE) value of 0.6391 life cycles in natural logarithm was obtained. The PSO-based ANN has shown improved performance compared to the conventional ANN approach in predicting fatigue life.",
keywords = "Artificial neural network, Fatigue life, Particle swarm optimization, Vertical vibration",
author = "Kong, {Y. S.} and S. Abdullah and D. Schramm and Omar, {M. Z.} and Haris, {S. M.}",
year = "2019",
month = "11",
day = "1",
doi = "10.1007/s12206-019-1003-9",
language = "English",
volume = "33",
pages = "5137--5145",
journal = "Journal of Mechanical Science and Technology",
issn = "1738-494X",
publisher = "Korean Society of Mechanical Engineers",
number = "11",

}

TY - JOUR

T1 - Design of artificial neural network using particle swarm optimisation for automotive spring durability

AU - Kong, Y. S.

AU - Abdullah, S.

AU - Schramm, D.

AU - Omar, M. Z.

AU - Haris, S. M.

PY - 2019/11/1

Y1 - 2019/11/1

N2 - This paper presents the optimisation of spring fatigue life based on an artificial neural network (ANN) architecture and particle swarm optimisation algorithm (PSO) using ISO 2631 vertical vibration as input. The road-induced vibration of a ground vehicle caused the spring to fail due to fatigue and human discomfort. Hence, there is a need to model the relationship between these two parameters for spring design assistance. Vibration and force signals were extracted from a quarter car model simulation for fatigue life and ISO 2631 vertical vibration estimations. PSO was applied to the datasets for ANN weights and biases adjustments while the mean squared error (MSE) was set as the objective function. For validation purposes, a set of independent datasets was applied to the ANN. The residuals were analysed using Lilliefors normality and error histogram. For prediction accuracy, the predicted fatigue lives were analysed using scatter band approach and compared with traditional trained ANN. The results have shown that most of the PSO-based ANN predicted fatigue lives were in the acceptable region and the root mean square error (RMSE) value of 0.6391 life cycles in natural logarithm was obtained. The PSO-based ANN has shown improved performance compared to the conventional ANN approach in predicting fatigue life.

AB - This paper presents the optimisation of spring fatigue life based on an artificial neural network (ANN) architecture and particle swarm optimisation algorithm (PSO) using ISO 2631 vertical vibration as input. The road-induced vibration of a ground vehicle caused the spring to fail due to fatigue and human discomfort. Hence, there is a need to model the relationship between these two parameters for spring design assistance. Vibration and force signals were extracted from a quarter car model simulation for fatigue life and ISO 2631 vertical vibration estimations. PSO was applied to the datasets for ANN weights and biases adjustments while the mean squared error (MSE) was set as the objective function. For validation purposes, a set of independent datasets was applied to the ANN. The residuals were analysed using Lilliefors normality and error histogram. For prediction accuracy, the predicted fatigue lives were analysed using scatter band approach and compared with traditional trained ANN. The results have shown that most of the PSO-based ANN predicted fatigue lives were in the acceptable region and the root mean square error (RMSE) value of 0.6391 life cycles in natural logarithm was obtained. The PSO-based ANN has shown improved performance compared to the conventional ANN approach in predicting fatigue life.

KW - Artificial neural network

KW - Fatigue life

KW - Particle swarm optimization

KW - Vertical vibration

UR - http://www.scopus.com/inward/record.url?scp=85074829483&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074829483&partnerID=8YFLogxK

U2 - 10.1007/s12206-019-1003-9

DO - 10.1007/s12206-019-1003-9

M3 - Article

AN - SCOPUS:85074829483

VL - 33

SP - 5137

EP - 5145

JO - Journal of Mechanical Science and Technology

JF - Journal of Mechanical Science and Technology

SN - 1738-494X

IS - 11

ER -