Evaluation of transformer insulating oil quality using NIR, fluorescence, and NMR spectroscopic data fusion

Godinho, Mariana S.; Blanco, Marcos R.; Neto, Francisco Fernandes Gambarra; Lião, Luciano M.; Sena, Marcelo M.; Tauler, Romà; Oliveira, Anselmo E. de

doi:10.1016/j.talanta.2014.05.021

Cited by 40 publications

(18 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, electrical techniques do not always provide adequate effectivity, sensitivity, and reproducibility because moisture, which reversibly migrates between the paper and the oil with changes in the transformer operating temperature [20], has a dominant effect on most of the measured electrical properties [16]. Therefore, in addition to traditional methods, alternative methods, including UV-Vis spectroscopy, turbidity, near-infrared (NIR) spectroscopy, FT-IR spectroscopy [21][22][23][24][25], and differential scanning calorimetry (DSC) [26], have also been continuously explored as effective diagnostic tools to assess transformer oil quality. For these reasons, we utilized UV-Vis spectroscopy and FT-IR spectroscopy in this study.…”

Section: A Brief Overview Of Methods For Assessing the Condition Of Tmentioning

confidence: 99%

Quantifying the Effect of Catalysts on the Lifetime of Transformer Oil

et al. 2020

View full text Add to dashboard Cite

The effect of catalysts in the form of a transformer copper winding with Kraft paper insulation on the lifetime of transformer oil was studied via ultraviolet-visible (UV-Vis) spectroscopy and Fourier transform infrared (FT-IR) spectroscopy. The tested naphthenic mineral oil was exposed to accelerated thermo-oxidative aging with limited access to air at temperatures of 110, 120, and 130 °C for times ranging from 24 to 2424 h in the presence and absence of catalysts. The UV-Vis technique focused on assessing the change in the color of the oil and quantified a 35%–45% reduction in oil lifetime, depending on the aging temperature, due to the influence of catalysts. The FT-IR analysis focused on the decrease in the spectral band at 3650 cm−1, which corresponds to the low-temperature antioxidant present in the oil, and quantified the 35% reduction in the oil lifetime independent of the aging temperature. This high rate of reduction in the transformer oil lifetime points to the dominant catalytic role of the Kraft paper and copper during the aging process of the transformer insulation system.

show abstract

Section: A Brief Overview Of Methods For Assessing the Condition Of Tmentioning

confidence: 99%

Quantifying the Effect of Catalysts on the Lifetime of Transformer Oil

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Spectral data are one of the most common data types to which chemometric techniques are applied . Owing to the development of modern spectroscopy instrumentations, each spectrum can consist of hundreds and even thousands of variables.…”

Section: Introductionmentioning

confidence: 99%

“…KEYWORDS genetic algorithm, similar offspring, spectral variable selection, voting 1 | INTRODUCTION Spectral data are one of the most common data types to which chemometric techniques are applied. [1][2][3][4] Owing to the development of modern spectroscopy instrumentations, each spectrum can consist of hundreds and even thousands of variables. Calibration with the full range of variables is time consuming, and the irrelevant information within the spectrum would affect the accuracy and robustness of the prediction.…”

mentioning

confidence: 99%

Similar offspring voting genetic algorithm for spectral variable selection

Zheng

2017

Journal of Chemometrics

View full text Add to dashboard Cite

This paper proposes a novel spectral variable selection approach named similar offspring voting genetic algorithm (sovGA). Unlike the traditional voting method (here called voting genetic algorithm) that attempts to overcome the stochastic risk of a genetic algorithm but may damage its optimal variable combination, sovGA aims to achieve a trade‐off between prediction precision and reliability of models. Genetic algorithm was repeated many times, and some effective similar offspring were obtained by a proposed algorithm; then, the spectral variables were selected by a voting mechanism. Two calibration methods, partial least square regression and multiple linear regression, were constructed to evaluate performance. The experimental results show that sovGA outperformed genetic algorithm, voting genetic algorithm, and the full spectrum situation in most cases.

show abstract

“…Hui Yan combined the near-infrared and mid-infrared spectral data to rapidly detect linoleic acid and linolenic acid and obtained positive results [2]. Mariana S. Godinho, et al performed data fusion of NIR, fluorescence, and NMR spectra, and the resulting data were coupled with partial least squares (PLS) to rapidly evaluate the quality of transformer insulating oil by detecting two quality indexes, interfacial tension and chroma [3].…”

Section: Introductionmentioning

confidence: 99%

Quantitative Analysis of Peanut Oil Adulteration Based on Data Fusion of Multi-source Spectra

Wu¹,

Tu²,

Yu³

et al. 2017

dteees

View full text Add to dashboard Cite

Abstract.This study aimed to analyze peanut oil adulteration based on chemometrics combined Raman and near-infrared (NIR) spectrum. The spectral data of 134 adulterated oil samples were collected by laser Raman and NIR spectrometer. The Raman spectra data and NIR were preprocessed respectively by different preprocessing approaches. The backward interval partial least squares (BiPLS) method was applied to extract the featured wavelengths. Based on the full spectrum and the characteristic wavelengths, adulteration quantity prediction models were established by the support vector machine regression (SVR) method. According to the analysis, the SVR model could predict the adulteration content in the peanut oil. Furthermore, the correlation coefficient R was greater than 0.97, and the mean square error (MSE) was smaller than 3.2E-4. The SVR model had advantageous properties such as strong generalization ability and good prediction accuracy. The results showed that Raman and NIR fusion analysis was effective in the quantitative analysis of the adulteration in peanut oil. Multi-spectral analysis for edible oil adulteration is an important field of study.

show abstract

Evaluation of transformer insulating oil quality using NIR, fluorescence, and NMR spectroscopic data fusion

Cited by 40 publications

References 31 publications

Quantifying the Effect of Catalysts on the Lifetime of Transformer Oil

Quantifying the Effect of Catalysts on the Lifetime of Transformer Oil

Similar offspring voting genetic algorithm for spectral variable selection

Quantitative Analysis of Peanut Oil Adulteration Based on Data Fusion of Multi-source Spectra

Contact Info

Product

Resources

About