Partial Least Squares (PLS) Integrated Fourier Transform Infrared (FTIR) Approach for Prediction of Moisture in Transformer Oil and Lubricating Oil

Sim, Siong Fong and Amelia Laccy, Anak Jeffrey Kimura (2019) Partial Least Squares (PLS) Integrated Fourier Transform Infrared (FTIR) Approach for Prediction of Moisture in Transformer Oil and Lubricating Oil. Journal of Spectroscopy, 2019. pp. 1-10. ISSN 2314-4939

[img] PDF
Partial least squares (pls) integrated fourier transform.pdf

Download (2MB)
Official URL: https://www.hindawi.com/journals/jspec/2019/591650...

Abstract

Fourier transform infrared (FTIR) spectroscopy has been advocating a promising alternative for Karl Fischer titration method for quantification of moisture in oil. +is study aims to integrate partial least squares regression (PLSR) approach on FTIR spectra for prediction of moisture in locally accessible transformer oil and lubricating oil. +e oil samples spiked with known moisture concentrations were extracted with acetonitrile and subjected to analysis with an FTIR spectrophotometer. +e PLSR model was built based on 100 training/test splits, and the prediction performance was measured with the percentage root mean squares error (% RMSE). +e range of concentration studied was between 0 and 5000 ppm. +e marker region of moisture was found at 3750–3400 and 1700–1600 cm−1 with the latter demonstrating a better predictive ability in both lubricating oil and transformer oil. +e prediction of moisture in lubricating oil was characterized with lower % RMSE. At concentration less than 700 ppm, the prediction accuracy deteriorates suggesting poor sensitivity. +e PLSR was implemented on IR spectra of a set of blind samples, verified with Karl Fischer (for transformer oil) method and Kittiwake (for lubricating oil) method. +e prediction was encouraging at concentrations above 1000 ppm; at lower concentrations, the prediction was characterized with high percent error. +e algorithm, validated with 100 training/test splits, was converted into an executable program for prediction of moisture based on FTIR spectra. +is program can be used for prediction of other substances given that the marker region is identified. FTIR can be used for prediction of moisture in oil nevertheless the sensitivity and precision is low for samples with low moisture concentration.

Item Type: Article
Uncontrolled Keywords: Partial Least Squares (PLS), Fourier Transform Infrared (FTIR), Transformer Oil and Lubricating Oil, unimas, university, universiti, Borneo, Malaysia, Sarawak, Kuching, Samarahan, ipta, education, research, Universiti Malaysia Sarawak.
Subjects: Q Science > Q Science (General)
Q Science > QD Chemistry
Divisions: Academic Faculties, Institutes and Centres > Faculty of Resource Science and Technology
Depositing User: Gani
Date Deposited: 19 Feb 2019 07:53
Last Modified: 26 Aug 2020 03:03
URI: http://ir.unimas.my/id/eprint/23518

Actions (For repository members only: login required)

View Item View Item