Implementation of multiple linear regressions in lubricant degradation prediction algorithm

M. F M Idros, Azrif Manut, R. Yahya, Sawal Hamid Md Ali

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

Abstract

This paper presents the development of the prediction algorithm of lubricant degradation based on Beer Lambert's transmittance theory by using Multiple Linear Regressions (MLR). Recently, an increasing amount of wasted lubricant has been due to the unnecessary changing of lubricant even though the lubricant still remains its lubrication behavior. Therefore, a condition based technique is introduced to monitor the degradation parameters in lubricating oil by using optical approach. This work focuses on Total Acid Number (TAN) that has been identified as the main parameter in determining the lifetime of lubricant and it occurred at band location from 1,050-1,250cm-1 and 1,700-1,730cm-1. The best input parameter has been identified for sensor development and signal processing. Then, the prediction model is used to validate the measured and the predicted value of degradation. The high correlation between the predicted and measured data shows the prediction algorithm can be used for prediction purposes efficiently.

Original languageEnglish
Title of host publicationInternational Conference on Electronic Devices, Systems, and Applications
Pages194-197
Number of pages4
DOIs
Publication statusPublished - 2012
EventIEEE International Conference on Electronics Design, Systems and Applications, ICEDSA 2012 - Kuala Lumpur
Duration: 5 Nov 20126 Nov 2012

Other

OtherIEEE International Conference on Electronics Design, Systems and Applications, ICEDSA 2012
CityKuala Lumpur
Period5/11/126/11/12

Fingerprint

Linear regression
Lubricants
Degradation
Lubricating oils
Lubrication
Signal processing
Acids
Sensors

Keywords

  • Degradation
  • Lubricant
  • Multiple Linear regression (MLR)

ASJC Scopus subject areas

  • Computer Science Applications
  • Hardware and Architecture
  • Software
  • Electrical and Electronic Engineering

Cite this

Idros, M. F. M., Manut, A., Yahya, R., & Md Ali, S. H. (2012). Implementation of multiple linear regressions in lubricant degradation prediction algorithm. In International Conference on Electronic Devices, Systems, and Applications (pp. 194-197). [6507795] https://doi.org/10.1109/ICEDSA.2012.6507795

Implementation of multiple linear regressions in lubricant degradation prediction algorithm. / Idros, M. F M; Manut, Azrif; Yahya, R.; Md Ali, Sawal Hamid.

International Conference on Electronic Devices, Systems, and Applications. 2012. p. 194-197 6507795.

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

Idros, MFM, Manut, A, Yahya, R & Md Ali, SH 2012, Implementation of multiple linear regressions in lubricant degradation prediction algorithm. in International Conference on Electronic Devices, Systems, and Applications., 6507795, pp. 194-197, IEEE International Conference on Electronics Design, Systems and Applications, ICEDSA 2012, Kuala Lumpur, 5/11/12. https://doi.org/10.1109/ICEDSA.2012.6507795
Idros MFM, Manut A, Yahya R, Md Ali SH. Implementation of multiple linear regressions in lubricant degradation prediction algorithm. In International Conference on Electronic Devices, Systems, and Applications. 2012. p. 194-197. 6507795 https://doi.org/10.1109/ICEDSA.2012.6507795
Idros, M. F M ; Manut, Azrif ; Yahya, R. ; Md Ali, Sawal Hamid. / Implementation of multiple linear regressions in lubricant degradation prediction algorithm. International Conference on Electronic Devices, Systems, and Applications. 2012. pp. 194-197
@inproceedings{782ad6d683824ccaa4ae4bd56a5f455f,
title = "Implementation of multiple linear regressions in lubricant degradation prediction algorithm",
abstract = "This paper presents the development of the prediction algorithm of lubricant degradation based on Beer Lambert's transmittance theory by using Multiple Linear Regressions (MLR). Recently, an increasing amount of wasted lubricant has been due to the unnecessary changing of lubricant even though the lubricant still remains its lubrication behavior. Therefore, a condition based technique is introduced to monitor the degradation parameters in lubricating oil by using optical approach. This work focuses on Total Acid Number (TAN) that has been identified as the main parameter in determining the lifetime of lubricant and it occurred at band location from 1,050-1,250cm-1 and 1,700-1,730cm-1. The best input parameter has been identified for sensor development and signal processing. Then, the prediction model is used to validate the measured and the predicted value of degradation. The high correlation between the predicted and measured data shows the prediction algorithm can be used for prediction purposes efficiently.",
keywords = "Degradation, Lubricant, Multiple Linear regression (MLR)",
author = "Idros, {M. F M} and Azrif Manut and R. Yahya and {Md Ali}, {Sawal Hamid}",
year = "2012",
doi = "10.1109/ICEDSA.2012.6507795",
language = "English",
isbn = "9781467321631",
pages = "194--197",
booktitle = "International Conference on Electronic Devices, Systems, and Applications",

}

TY - GEN

T1 - Implementation of multiple linear regressions in lubricant degradation prediction algorithm

AU - Idros, M. F M

AU - Manut, Azrif

AU - Yahya, R.

AU - Md Ali, Sawal Hamid

PY - 2012

Y1 - 2012

N2 - This paper presents the development of the prediction algorithm of lubricant degradation based on Beer Lambert's transmittance theory by using Multiple Linear Regressions (MLR). Recently, an increasing amount of wasted lubricant has been due to the unnecessary changing of lubricant even though the lubricant still remains its lubrication behavior. Therefore, a condition based technique is introduced to monitor the degradation parameters in lubricating oil by using optical approach. This work focuses on Total Acid Number (TAN) that has been identified as the main parameter in determining the lifetime of lubricant and it occurred at band location from 1,050-1,250cm-1 and 1,700-1,730cm-1. The best input parameter has been identified for sensor development and signal processing. Then, the prediction model is used to validate the measured and the predicted value of degradation. The high correlation between the predicted and measured data shows the prediction algorithm can be used for prediction purposes efficiently.

AB - This paper presents the development of the prediction algorithm of lubricant degradation based on Beer Lambert's transmittance theory by using Multiple Linear Regressions (MLR). Recently, an increasing amount of wasted lubricant has been due to the unnecessary changing of lubricant even though the lubricant still remains its lubrication behavior. Therefore, a condition based technique is introduced to monitor the degradation parameters in lubricating oil by using optical approach. This work focuses on Total Acid Number (TAN) that has been identified as the main parameter in determining the lifetime of lubricant and it occurred at band location from 1,050-1,250cm-1 and 1,700-1,730cm-1. The best input parameter has been identified for sensor development and signal processing. Then, the prediction model is used to validate the measured and the predicted value of degradation. The high correlation between the predicted and measured data shows the prediction algorithm can be used for prediction purposes efficiently.

KW - Degradation

KW - Lubricant

KW - Multiple Linear regression (MLR)

UR - http://www.scopus.com/inward/record.url?scp=84877829009&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84877829009&partnerID=8YFLogxK

U2 - 10.1109/ICEDSA.2012.6507795

DO - 10.1109/ICEDSA.2012.6507795

M3 - Conference contribution

AN - SCOPUS:84877829009

SN - 9781467321631

SP - 194

EP - 197

BT - International Conference on Electronic Devices, Systems, and Applications

ER -