Feature Extraction of Oil–Paper Insulation Raman Spectroscopy Based on Manifold Dimension Transformation
Transformers play a crucial role in power systems. In this respect, fault diagnosis and aging state assessment have garnered significant attention from researchers. Herein, accelerated thermal aging and Raman scattering experiments are conducted on oil–paper insulation samples to accurately detect a...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-06-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/13/13/7626 |
_version_ | 1797592149772992512 |
---|---|
author | Xingang Chen Yijie Fan Zhipeng Ma Shiyao Tan Ningyi Li Xin Song Yuyang Huang Jinjing Zhang Wenxuan Zhang |
author_facet | Xingang Chen Yijie Fan Zhipeng Ma Shiyao Tan Ningyi Li Xin Song Yuyang Huang Jinjing Zhang Wenxuan Zhang |
author_sort | Xingang Chen |
collection | DOAJ |
description | Transformers play a crucial role in power systems. In this respect, fault diagnosis and aging state assessment have garnered significant attention from researchers. Herein, accelerated thermal aging and Raman scattering experiments are conducted on oil–paper insulation samples to accurately detect aging states. The samples are categorized into different aging stages based on the polymerization degree of the insulating paper. Principal component analysis (PCA), multi-dimensional scale change method (MDS), and isometric mapping algorithm (Isomap) are employed to extract features from the Raman spectra. Subsequently, the XGBoost strong classifier, optimized through Bayesian hyperparameter optimization (BO-XGBoost), is utilized to distinguish between four and ten states among 175 groups of samples after feature extraction. The subsequent classification results of the three feature-extraction methods are compared. The results indicate that Isoamp, which pertains to the manifold dimension transformation, achieves the highest average discriminative accuracy after feature extraction. The discriminative accuracies for aging states four and ten are 97.0% and 95.1% respectively, demonstrating that Raman spectroscopy manifold dimension transformation enhances the distinctiveness between samples of different aging states in the feature-extraction process. The diagnostic model constructed with Isomap and BO-XGBoost enables accurate discrimination of the aging states of oil–paper insulation. |
first_indexed | 2024-03-11T01:47:23Z |
format | Article |
id | doaj.art-b7d454d0d8694846a62531b33746b5f8 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-11T01:47:23Z |
publishDate | 2023-06-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-b7d454d0d8694846a62531b33746b5f82023-11-18T16:09:07ZengMDPI AGApplied Sciences2076-34172023-06-011313762610.3390/app13137626Feature Extraction of Oil–Paper Insulation Raman Spectroscopy Based on Manifold Dimension TransformationXingang Chen0Yijie Fan1Zhipeng Ma2Shiyao Tan3Ningyi Li4Xin Song5Yuyang Huang6Jinjing Zhang7Wenxuan Zhang8School of Electrical and Electronic Engineering, Chongqing University of Technology, Chongqing 400054, ChinaSchool of Electrical and Electronic Engineering, Chongqing University of Technology, Chongqing 400054, ChinaSchool of Electrical and Electronic Engineering, Chongqing University of Technology, Chongqing 400054, ChinaSchool of Electrical and Electronic Engineering, Chongqing University of Technology, Chongqing 400054, ChinaSchool of Electrical and Electronic Engineering, Chongqing University of Technology, Chongqing 400054, ChinaSchool of Electrical and Electronic Engineering, Chongqing University of Technology, Chongqing 400054, ChinaSchool of Electrical and Electronic Engineering, Chongqing University of Technology, Chongqing 400054, ChinaSchool of Electrical and Electronic Engineering, Chongqing University of Technology, Chongqing 400054, ChinaSchool of Electrical and Electronic Engineering, Chongqing University of Technology, Chongqing 400054, ChinaTransformers play a crucial role in power systems. In this respect, fault diagnosis and aging state assessment have garnered significant attention from researchers. Herein, accelerated thermal aging and Raman scattering experiments are conducted on oil–paper insulation samples to accurately detect aging states. The samples are categorized into different aging stages based on the polymerization degree of the insulating paper. Principal component analysis (PCA), multi-dimensional scale change method (MDS), and isometric mapping algorithm (Isomap) are employed to extract features from the Raman spectra. Subsequently, the XGBoost strong classifier, optimized through Bayesian hyperparameter optimization (BO-XGBoost), is utilized to distinguish between four and ten states among 175 groups of samples after feature extraction. The subsequent classification results of the three feature-extraction methods are compared. The results indicate that Isoamp, which pertains to the manifold dimension transformation, achieves the highest average discriminative accuracy after feature extraction. The discriminative accuracies for aging states four and ten are 97.0% and 95.1% respectively, demonstrating that Raman spectroscopy manifold dimension transformation enhances the distinctiveness between samples of different aging states in the feature-extraction process. The diagnostic model constructed with Isomap and BO-XGBoost enables accurate discrimination of the aging states of oil–paper insulation.https://www.mdpi.com/2076-3417/13/13/7626oil–paper insulationRaman spectroscopyfeature extractionstate classification |
spellingShingle | Xingang Chen Yijie Fan Zhipeng Ma Shiyao Tan Ningyi Li Xin Song Yuyang Huang Jinjing Zhang Wenxuan Zhang Feature Extraction of Oil–Paper Insulation Raman Spectroscopy Based on Manifold Dimension Transformation Applied Sciences oil–paper insulation Raman spectroscopy feature extraction state classification |
title | Feature Extraction of Oil–Paper Insulation Raman Spectroscopy Based on Manifold Dimension Transformation |
title_full | Feature Extraction of Oil–Paper Insulation Raman Spectroscopy Based on Manifold Dimension Transformation |
title_fullStr | Feature Extraction of Oil–Paper Insulation Raman Spectroscopy Based on Manifold Dimension Transformation |
title_full_unstemmed | Feature Extraction of Oil–Paper Insulation Raman Spectroscopy Based on Manifold Dimension Transformation |
title_short | Feature Extraction of Oil–Paper Insulation Raman Spectroscopy Based on Manifold Dimension Transformation |
title_sort | feature extraction of oil paper insulation raman spectroscopy based on manifold dimension transformation |
topic | oil–paper insulation Raman spectroscopy feature extraction state classification |
url | https://www.mdpi.com/2076-3417/13/13/7626 |
work_keys_str_mv | AT xingangchen featureextractionofoilpaperinsulationramanspectroscopybasedonmanifolddimensiontransformation AT yijiefan featureextractionofoilpaperinsulationramanspectroscopybasedonmanifolddimensiontransformation AT zhipengma featureextractionofoilpaperinsulationramanspectroscopybasedonmanifolddimensiontransformation AT shiyaotan featureextractionofoilpaperinsulationramanspectroscopybasedonmanifolddimensiontransformation AT ningyili featureextractionofoilpaperinsulationramanspectroscopybasedonmanifolddimensiontransformation AT xinsong featureextractionofoilpaperinsulationramanspectroscopybasedonmanifolddimensiontransformation AT yuyanghuang featureextractionofoilpaperinsulationramanspectroscopybasedonmanifolddimensiontransformation AT jinjingzhang featureextractionofoilpaperinsulationramanspectroscopybasedonmanifolddimensiontransformation AT wenxuanzhang featureextractionofoilpaperinsulationramanspectroscopybasedonmanifolddimensiontransformation |