Measuring color index of transformer oil-enabling single-wavelength spectroscopy with artificial neural network-fuzzy logic model

Conventionally, the color index of transformer oil is determined by a color comparator based on the American Society for Testing and Materials (ASTM) D 1500 standard. The equipment requires humans to operate, which leads to human error and limited number of samples tested per day. This work proposes...

Full description

Bibliographic Details
Main Authors: Hasnul Hadi, M.H., Ker, Pin Jern, Lee, Hui Jing, Leong, Yang Sing, Thiviyanathan, Vimal A., Hannan, M.A., Jamaludin, Md. Zaini, Mahdi, M.A.
Format: Article
Published: Institute of Electrical and Electronics Engineers (IEEE) 2024
Online Access:http://psasir.upm.edu.my/id/eprint/115526/
_version_ 1848866800108830720
author Hasnul Hadi, M.H.
Ker, Pin Jern
Lee, Hui Jing
Leong, Yang Sing
Thiviyanathan, Vimal A.
Hannan, M.A.
Jamaludin, Md. Zaini
Mahdi, M.A.
author_facet Hasnul Hadi, M.H.
Ker, Pin Jern
Lee, Hui Jing
Leong, Yang Sing
Thiviyanathan, Vimal A.
Hannan, M.A.
Jamaludin, Md. Zaini
Mahdi, M.A.
author_sort Hasnul Hadi, M.H.
building UPM Institutional Repository
collection Online Access
description Conventionally, the color index of transformer oil is determined by a color comparator based on the American Society for Testing and Materials (ASTM) D 1500 standard. The equipment requires humans to operate, which leads to human error and limited number of samples tested per day. This work proposes the utilization of single-wavelength spectroscopy with 405 nm laser diode using artificial neural network (ANN) to determine the color index of transformer oil. Two ANN models were developed using data collected from 50 oil samples with different optical pathlengths of 1 to 10 mm, and laser output powers of 1 to 15 mW. The first model classified the input into different color indices and another model correlated the input parameters through regression analysis to determine the color index. A hybrid ANN-fuzzy logic model was also developed to improve the color index prediction. The root-mean-squared error (RMSE) obtained from the prediction by ANN regressor and ANN classifier are 0.5602 and 0.6416, respectively. The hybrid ANN-fuzzy logic model improves the RMSE especially for optical pathlengths < 5 mm, which is required for measuring samples with high color index. This proposed method reduces the dependency on complex optoelectronic hardware to obtain highly accurate results.Note to Practitioners - Unlike the conventional testing method for color index of transformer oil that requires human observation, the findings of this study enables the possibility of compact and smart portable device through the utilization of single wavelength spectroscopy with machine learning models. With no human involvement, more computational power with lesser hardware dependency, the maintenance cost and error can be reduced. This proposed method can potentially be applied to measure the color of other amber-colored liquid products such as olive oil, honey and others.
first_indexed 2025-11-15T14:26:21Z
format Article
id upm-115526
institution Universiti Putra Malaysia
institution_category Local University
last_indexed 2025-11-15T14:26:21Z
publishDate 2024
publisher Institute of Electrical and Electronics Engineers (IEEE)
recordtype eprints
repository_type Digital Repository
spelling upm-1155262025-03-06T07:43:32Z http://psasir.upm.edu.my/id/eprint/115526/ Measuring color index of transformer oil-enabling single-wavelength spectroscopy with artificial neural network-fuzzy logic model Hasnul Hadi, M.H. Ker, Pin Jern Lee, Hui Jing Leong, Yang Sing Thiviyanathan, Vimal A. Hannan, M.A. Jamaludin, Md. Zaini Mahdi, M.A. Conventionally, the color index of transformer oil is determined by a color comparator based on the American Society for Testing and Materials (ASTM) D 1500 standard. The equipment requires humans to operate, which leads to human error and limited number of samples tested per day. This work proposes the utilization of single-wavelength spectroscopy with 405 nm laser diode using artificial neural network (ANN) to determine the color index of transformer oil. Two ANN models were developed using data collected from 50 oil samples with different optical pathlengths of 1 to 10 mm, and laser output powers of 1 to 15 mW. The first model classified the input into different color indices and another model correlated the input parameters through regression analysis to determine the color index. A hybrid ANN-fuzzy logic model was also developed to improve the color index prediction. The root-mean-squared error (RMSE) obtained from the prediction by ANN regressor and ANN classifier are 0.5602 and 0.6416, respectively. The hybrid ANN-fuzzy logic model improves the RMSE especially for optical pathlengths < 5 mm, which is required for measuring samples with high color index. This proposed method reduces the dependency on complex optoelectronic hardware to obtain highly accurate results.Note to Practitioners - Unlike the conventional testing method for color index of transformer oil that requires human observation, the findings of this study enables the possibility of compact and smart portable device through the utilization of single wavelength spectroscopy with machine learning models. With no human involvement, more computational power with lesser hardware dependency, the maintenance cost and error can be reduced. This proposed method can potentially be applied to measure the color of other amber-colored liquid products such as olive oil, honey and others. Institute of Electrical and Electronics Engineers (IEEE) 2024 Article PeerReviewed Hasnul Hadi, M.H. and Ker, Pin Jern and Lee, Hui Jing and Leong, Yang Sing and Thiviyanathan, Vimal A. and Hannan, M.A. and Jamaludin, Md. Zaini and Mahdi, M.A. (2024) Measuring color index of transformer oil-enabling single-wavelength spectroscopy with artificial neural network-fuzzy logic model. IEEE Transactions on Automation Science and Engineering, 21 (2). pp. 1358-1368. ISSN 1545-5955; eISSN: 1558-3783 https://ieeexplore.ieee.org/document/10026239/ 10.1109/tase.2023.3238645
spellingShingle Hasnul Hadi, M.H.
Ker, Pin Jern
Lee, Hui Jing
Leong, Yang Sing
Thiviyanathan, Vimal A.
Hannan, M.A.
Jamaludin, Md. Zaini
Mahdi, M.A.
Measuring color index of transformer oil-enabling single-wavelength spectroscopy with artificial neural network-fuzzy logic model
title Measuring color index of transformer oil-enabling single-wavelength spectroscopy with artificial neural network-fuzzy logic model
title_full Measuring color index of transformer oil-enabling single-wavelength spectroscopy with artificial neural network-fuzzy logic model
title_fullStr Measuring color index of transformer oil-enabling single-wavelength spectroscopy with artificial neural network-fuzzy logic model
title_full_unstemmed Measuring color index of transformer oil-enabling single-wavelength spectroscopy with artificial neural network-fuzzy logic model
title_short Measuring color index of transformer oil-enabling single-wavelength spectroscopy with artificial neural network-fuzzy logic model
title_sort measuring color index of transformer oil-enabling single-wavelength spectroscopy with artificial neural network-fuzzy logic model
url http://psasir.upm.edu.my/id/eprint/115526/
http://psasir.upm.edu.my/id/eprint/115526/
http://psasir.upm.edu.my/id/eprint/115526/