Recognizing vehicle lubricant oil quality via neural network

Siti Norul Huda Sheikh Abdullah, Khairuddin Omar, Siti Rozaimah Sheikh Abdullah, Norsalina Harun, Mohd Syarif Afriansyah Lubis, Che Hassan Che Haron, Kamsuriah Ahmad, Mohd Zakree Ahmad Nazri, Mohammad Faidzul Nasrudin, Chin Sin Lee, Abdul Sahli Fakhrudin, Mohd Esa Baruji

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Currently, measuring either vehicle's mileage or duration or either one does maintain lubricant viscosity. However, these judgments are inaccurate because there are many other factors like conductivity, humidity and viscosity that may affect the oil quality. This paper proposed one theory of monitoring viscosity quality with Neural Network (NN) modelling by introducing factors like temperature, shear stress and pressure. One deterministic objective will be highlighted that is to develop NN modelling based on those three factors. This research also introduces normalization approach called Along Channel and logarithmic function due to various range of data input. NN modelling, an off-line system is explicitly designed with Backpropagation Algorithm and Multilayer Feedforward Network for learning process while its weight is calculated based on Nguyen Widrow number and Genetic Algorithm. There were 310 sample data, which divided into two sets; 149 data for training set and the rest for testing and vice versa. The application performance has achieved up to 85.91% result approaching real viscosity value.

Original languageEnglish
Title of host publicationProceedings - 8th International Symposium on Signal Processing and its Applications, ISSPA 2005
Pages579-582
Number of pages4
Volume2
DOIs
Publication statusPublished - 2005
Event8th International Symposium on Signal Processing and its Applications, ISSPA 2005 - Sydney
Duration: 28 Aug 200531 Aug 2005

Other

Other8th International Symposium on Signal Processing and its Applications, ISSPA 2005
CitySydney
Period28/8/0531/8/05

Fingerprint

Lubricants
Viscosity
Neural networks
Backpropagation algorithms
Shear stress
Atmospheric humidity
Multilayers
Genetic algorithms
Oils
Monitoring
Testing
Temperature

Keywords

  • Back-propagation
  • Genetic algorithm
  • Lubricant oil
  • Neural network
  • Viscosity

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Sheikh Abdullah, S. N. H., Omar, K., Sheikh Abdullah, S. R., Harun, N., Lubis, M. S. A., Che Haron, C. H., ... Baruji, M. E. (2005). Recognizing vehicle lubricant oil quality via neural network. In Proceedings - 8th International Symposium on Signal Processing and its Applications, ISSPA 2005 (Vol. 2, pp. 579-582). [1581004] https://doi.org/10.1109/ISSPA.2005.1581004

Recognizing vehicle lubricant oil quality via neural network. / Sheikh Abdullah, Siti Norul Huda; Omar, Khairuddin; Sheikh Abdullah, Siti Rozaimah; Harun, Norsalina; Lubis, Mohd Syarif Afriansyah; Che Haron, Che Hassan; Ahmad, Kamsuriah; Ahmad Nazri, Mohd Zakree; Nasrudin, Mohammad Faidzul; Lee, Chin Sin; Fakhrudin, Abdul Sahli; Baruji, Mohd Esa.

Proceedings - 8th International Symposium on Signal Processing and its Applications, ISSPA 2005. Vol. 2 2005. p. 579-582 1581004.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sheikh Abdullah, SNH, Omar, K, Sheikh Abdullah, SR, Harun, N, Lubis, MSA, Che Haron, CH, Ahmad, K, Ahmad Nazri, MZ, Nasrudin, MF, Lee, CS, Fakhrudin, AS & Baruji, ME 2005, Recognizing vehicle lubricant oil quality via neural network. in Proceedings - 8th International Symposium on Signal Processing and its Applications, ISSPA 2005. vol. 2, 1581004, pp. 579-582, 8th International Symposium on Signal Processing and its Applications, ISSPA 2005, Sydney, 28/8/05. https://doi.org/10.1109/ISSPA.2005.1581004
Sheikh Abdullah SNH, Omar K, Sheikh Abdullah SR, Harun N, Lubis MSA, Che Haron CH et al. Recognizing vehicle lubricant oil quality via neural network. In Proceedings - 8th International Symposium on Signal Processing and its Applications, ISSPA 2005. Vol. 2. 2005. p. 579-582. 1581004 https://doi.org/10.1109/ISSPA.2005.1581004
Sheikh Abdullah, Siti Norul Huda ; Omar, Khairuddin ; Sheikh Abdullah, Siti Rozaimah ; Harun, Norsalina ; Lubis, Mohd Syarif Afriansyah ; Che Haron, Che Hassan ; Ahmad, Kamsuriah ; Ahmad Nazri, Mohd Zakree ; Nasrudin, Mohammad Faidzul ; Lee, Chin Sin ; Fakhrudin, Abdul Sahli ; Baruji, Mohd Esa. / Recognizing vehicle lubricant oil quality via neural network. Proceedings - 8th International Symposium on Signal Processing and its Applications, ISSPA 2005. Vol. 2 2005. pp. 579-582
@inproceedings{c3868935e8de4b989b2f7e771c0bbebc,
title = "Recognizing vehicle lubricant oil quality via neural network",
abstract = "Currently, measuring either vehicle's mileage or duration or either one does maintain lubricant viscosity. However, these judgments are inaccurate because there are many other factors like conductivity, humidity and viscosity that may affect the oil quality. This paper proposed one theory of monitoring viscosity quality with Neural Network (NN) modelling by introducing factors like temperature, shear stress and pressure. One deterministic objective will be highlighted that is to develop NN modelling based on those three factors. This research also introduces normalization approach called Along Channel and logarithmic function due to various range of data input. NN modelling, an off-line system is explicitly designed with Backpropagation Algorithm and Multilayer Feedforward Network for learning process while its weight is calculated based on Nguyen Widrow number and Genetic Algorithm. There were 310 sample data, which divided into two sets; 149 data for training set and the rest for testing and vice versa. The application performance has achieved up to 85.91{\%} result approaching real viscosity value.",
keywords = "Back-propagation, Genetic algorithm, Lubricant oil, Neural network, Viscosity",
author = "{Sheikh Abdullah}, {Siti Norul Huda} and Khairuddin Omar and {Sheikh Abdullah}, {Siti Rozaimah} and Norsalina Harun and Lubis, {Mohd Syarif Afriansyah} and {Che Haron}, {Che Hassan} and Kamsuriah Ahmad and {Ahmad Nazri}, {Mohd Zakree} and Nasrudin, {Mohammad Faidzul} and Lee, {Chin Sin} and Fakhrudin, {Abdul Sahli} and Baruji, {Mohd Esa}",
year = "2005",
doi = "10.1109/ISSPA.2005.1581004",
language = "English",
isbn = "0780392434",
volume = "2",
pages = "579--582",
booktitle = "Proceedings - 8th International Symposium on Signal Processing and its Applications, ISSPA 2005",

}

TY - GEN

T1 - Recognizing vehicle lubricant oil quality via neural network

AU - Sheikh Abdullah, Siti Norul Huda

AU - Omar, Khairuddin

AU - Sheikh Abdullah, Siti Rozaimah

AU - Harun, Norsalina

AU - Lubis, Mohd Syarif Afriansyah

AU - Che Haron, Che Hassan

AU - Ahmad, Kamsuriah

AU - Ahmad Nazri, Mohd Zakree

AU - Nasrudin, Mohammad Faidzul

AU - Lee, Chin Sin

AU - Fakhrudin, Abdul Sahli

AU - Baruji, Mohd Esa

PY - 2005

Y1 - 2005

N2 - Currently, measuring either vehicle's mileage or duration or either one does maintain lubricant viscosity. However, these judgments are inaccurate because there are many other factors like conductivity, humidity and viscosity that may affect the oil quality. This paper proposed one theory of monitoring viscosity quality with Neural Network (NN) modelling by introducing factors like temperature, shear stress and pressure. One deterministic objective will be highlighted that is to develop NN modelling based on those three factors. This research also introduces normalization approach called Along Channel and logarithmic function due to various range of data input. NN modelling, an off-line system is explicitly designed with Backpropagation Algorithm and Multilayer Feedforward Network for learning process while its weight is calculated based on Nguyen Widrow number and Genetic Algorithm. There were 310 sample data, which divided into two sets; 149 data for training set and the rest for testing and vice versa. The application performance has achieved up to 85.91% result approaching real viscosity value.

AB - Currently, measuring either vehicle's mileage or duration or either one does maintain lubricant viscosity. However, these judgments are inaccurate because there are many other factors like conductivity, humidity and viscosity that may affect the oil quality. This paper proposed one theory of monitoring viscosity quality with Neural Network (NN) modelling by introducing factors like temperature, shear stress and pressure. One deterministic objective will be highlighted that is to develop NN modelling based on those three factors. This research also introduces normalization approach called Along Channel and logarithmic function due to various range of data input. NN modelling, an off-line system is explicitly designed with Backpropagation Algorithm and Multilayer Feedforward Network for learning process while its weight is calculated based on Nguyen Widrow number and Genetic Algorithm. There were 310 sample data, which divided into two sets; 149 data for training set and the rest for testing and vice versa. The application performance has achieved up to 85.91% result approaching real viscosity value.

KW - Back-propagation

KW - Genetic algorithm

KW - Lubricant oil

KW - Neural network

KW - Viscosity

UR - http://www.scopus.com/inward/record.url?scp=33847150510&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33847150510&partnerID=8YFLogxK

U2 - 10.1109/ISSPA.2005.1581004

DO - 10.1109/ISSPA.2005.1581004

M3 - Conference contribution

AN - SCOPUS:33847150510

SN - 0780392434

SN - 9780780392434

VL - 2

SP - 579

EP - 582

BT - Proceedings - 8th International Symposium on Signal Processing and its Applications, ISSPA 2005

ER -