The degradation of the insulation performance of cross-linked polyethylene (XLPE) during thermal oxidative aging is a crucial factor affecting the safe operation of cables. Investigating the influence of the structural degradation process of XLPE on its insulation properties from a molecular structure and microscopic parameter perspective can provide a better understanding of the molecular mechanisms behind insulation performance degradation during thermal oxidative aging. In this study, the reaction kinetics of XLPE were simulated using the Ab initio molecular dynamics (AIMDs), resulting in the extraction of five XLPE structures with varying degrees of aging. Density functional theory (DFT) simulations were employed to analyze the variation patterns and differences in discharge-related microscopic parameters of these five different XLPE structures under varying electric field intensities. The results show that there are significant differences in the structure and dipole moment of XLPE with different aging degrees, resulting in large changes in its microscopic parameters. In particular, the formation of carbonyl groups in XLPE has a significant impact on its structure and microscopic parameters. As the aging degree of XLPE increases, the ionization of XLPE molecules and the activity of electron affinity (EA) molecules intensify. The structural evolution of XLPE during the aging process markedly influences the excitation process and molecular orbitals of its molecules, facilitating the release of numerous photons, creating conditions for secondary electron collapse, and enhancing molecular conductivity. The simulation results of the molecular surface electrostatic potential (ESP) reveal that deeper aging of XLPE increases the likelihood of electrophilic and nucleophilic reactions, as well as electron accumulation and collision. Overall, the electric field exerts a minimal effect on the molecular structure and microscopic parameters of different XLPE molecules.
{"title":"Molecular Insights Into the Effects of Thermal Oxidative Aging on the Insulation Properties of Cross-Linked Polyethylene","authors":"Wenyu Ye;Chenyu Gao;Xinhan Qiao;Haolun Che;Jianwen Zhang;Jian Hao","doi":"10.1109/TDEI.2025.3543802","DOIUrl":"https://doi.org/10.1109/TDEI.2025.3543802","url":null,"abstract":"The degradation of the insulation performance of cross-linked polyethylene (XLPE) during thermal oxidative aging is a crucial factor affecting the safe operation of cables. Investigating the influence of the structural degradation process of XLPE on its insulation properties from a molecular structure and microscopic parameter perspective can provide a better understanding of the molecular mechanisms behind insulation performance degradation during thermal oxidative aging. In this study, the reaction kinetics of XLPE were simulated using the Ab initio molecular dynamics (AIMDs), resulting in the extraction of five XLPE structures with varying degrees of aging. Density functional theory (DFT) simulations were employed to analyze the variation patterns and differences in discharge-related microscopic parameters of these five different XLPE structures under varying electric field intensities. The results show that there are significant differences in the structure and dipole moment of XLPE with different aging degrees, resulting in large changes in its microscopic parameters. In particular, the formation of carbonyl groups in XLPE has a significant impact on its structure and microscopic parameters. As the aging degree of XLPE increases, the ionization of XLPE molecules and the activity of electron affinity (EA) molecules intensify. The structural evolution of XLPE during the aging process markedly influences the excitation process and molecular orbitals of its molecules, facilitating the release of numerous photons, creating conditions for secondary electron collapse, and enhancing molecular conductivity. The simulation results of the molecular surface electrostatic potential (ESP) reveal that deeper aging of XLPE increases the likelihood of electrophilic and nucleophilic reactions, as well as electron accumulation and collision. Overall, the electric field exerts a minimal effect on the molecular structure and microscopic parameters of different XLPE molecules.","PeriodicalId":13247,"journal":{"name":"IEEE Transactions on Dielectrics and Electrical Insulation","volume":"32 4","pages":"1915-1922"},"PeriodicalIF":3.1,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144739996","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-18DOI: 10.1109/TDEI.2025.3543147
Ze Li;Yiming Zang;Chenglin Wang;Yanshu Tang;Tongyang Ren;Xiuchen Jiang
The optical method and ultrahigh frequency (UHF) method are important techniques for detecting partial discharge (PD) in gas-insulated switchgear (GIS). However, optical signals and UHF signals may suffer from different degrees of signal loss or interference for different PD types, which leads to incomplete feature information in the optical or UHF patterns and reduces the accuracy of pattern recognition. In this article, a PD detection device in GIS based on the UHF and light guide rod (LGR) technologies is designed. An experimental platform for electrical and optical PD detection in GIS is set up, and measurements of typical PD are carried out. Optical and UHF time-domain signals of corona discharge, floating discharge, and particle discharge are obtained. Then, an image fusion algorithm based on guided filtering fusion (GFF) is proposed to fuse the optical and UHF phase-resolved pulse sequence (PRPS) patterns. Subsequently, a feature extraction method based on speeded-up robust features (SURFs) for PD images is proposed. Finally, the recognition effects of multiple classifiers are compared. The results show that the image fusion and feature extraction method for UHF and optical PD proposed in this article can improve the accuracy of fault diagnosis up to 97.1%.
{"title":"Analysis and Diagnosis of Optical and UHF Partial Discharges in GIS Based on Guided Filtering Fusion","authors":"Ze Li;Yiming Zang;Chenglin Wang;Yanshu Tang;Tongyang Ren;Xiuchen Jiang","doi":"10.1109/TDEI.2025.3543147","DOIUrl":"https://doi.org/10.1109/TDEI.2025.3543147","url":null,"abstract":"The optical method and ultrahigh frequency (UHF) method are important techniques for detecting partial discharge (PD) in gas-insulated switchgear (GIS). However, optical signals and UHF signals may suffer from different degrees of signal loss or interference for different PD types, which leads to incomplete feature information in the optical or UHF patterns and reduces the accuracy of pattern recognition. In this article, a PD detection device in GIS based on the UHF and light guide rod (LGR) technologies is designed. An experimental platform for electrical and optical PD detection in GIS is set up, and measurements of typical PD are carried out. Optical and UHF time-domain signals of corona discharge, floating discharge, and particle discharge are obtained. Then, an image fusion algorithm based on guided filtering fusion (GFF) is proposed to fuse the optical and UHF phase-resolved pulse sequence (PRPS) patterns. Subsequently, a feature extraction method based on speeded-up robust features (SURFs) for PD images is proposed. Finally, the recognition effects of multiple classifiers are compared. The results show that the image fusion and feature extraction method for UHF and optical PD proposed in this article can improve the accuracy of fault diagnosis up to 97.1%.","PeriodicalId":13247,"journal":{"name":"IEEE Transactions on Dielectrics and Electrical Insulation","volume":"32 5","pages":"2978-2985"},"PeriodicalIF":3.1,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145189970","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The performance of polypropylene (PP) insulation material used in high-voltage power cables is crucial for ensuring the safe and reliable operation of the cables. To deeply understand the aging and failure mechanisms of graft-modified PP cable insulation, accelerated aging experiments were conducted on the cable insulation layer. The ac breakdown field strength and elongation at break were tested, the density functional theory calculations were performed on the graft-modified PP molecular chains, and further analyses of the physicochemical properties, such as the microstructure and molecular structure changes of the insulation material, were conducted. The results show that when the insulation material reaches the aging failure point, the breakdown performance significantly decreases, the perfection of the crystalline region structure of PP deteriorates with aging time, the content of C=O carbonyl groups significantly increases with aging time, and thermal-oxidative aging accelerates the destruction of PP spherulites. The appearance of oxidation products, structure loosening, and decreased crystallinity during the aging process are the main reasons for the reduction in mechanical performance and breakdown strength. This study provides new insights into the research on the aging mechanism, structure, and performance relationship of PP cable insulation and has important guiding significance for the design of PP insulation materials.
{"title":"Aging Failure Mechanism of Graft Modified Polypropylene Cable Insulation","authors":"Yunjian Wu;Danfeng Zhang;Yifan Guo;Fanwu Chu;Guangke Li;Xiaoxing Zhang","doi":"10.1109/TDEI.2025.3543154","DOIUrl":"https://doi.org/10.1109/TDEI.2025.3543154","url":null,"abstract":"The performance of polypropylene (PP) insulation material used in high-voltage power cables is crucial for ensuring the safe and reliable operation of the cables. To deeply understand the aging and failure mechanisms of graft-modified PP cable insulation, accelerated aging experiments were conducted on the cable insulation layer. The ac breakdown field strength and elongation at break were tested, the density functional theory calculations were performed on the graft-modified PP molecular chains, and further analyses of the physicochemical properties, such as the microstructure and molecular structure changes of the insulation material, were conducted. The results show that when the insulation material reaches the aging failure point, the breakdown performance significantly decreases, the perfection of the crystalline region structure of PP deteriorates with aging time, the content of C=O carbonyl groups significantly increases with aging time, and thermal-oxidative aging accelerates the destruction of PP spherulites. The appearance of oxidation products, structure loosening, and decreased crystallinity during the aging process are the main reasons for the reduction in mechanical performance and breakdown strength. This study provides new insights into the research on the aging mechanism, structure, and performance relationship of PP cable insulation and has important guiding significance for the design of PP insulation materials.","PeriodicalId":13247,"journal":{"name":"IEEE Transactions on Dielectrics and Electrical Insulation","volume":"32 4","pages":"2205-2212"},"PeriodicalIF":3.1,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144739899","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This article explores the behavior of charge transport and the surface electrical properties of epoxy spacers within high-voltage alternating current (HVac) gas-insulated switchgear (GIS), which may be exposed to the dc-ac switching electric field at the end of dc ice melting. Simulation and experimental results reveal that increasing dc voltage and duration enhances charge accumulation at the gas-solid interface, whose polarity aligns with the electrodes. When the electric field transitions to ac, charge accumulation occurs gradually during the half-cycle, where the voltage polarity matches the charge polarity. However, during the half-cycle of opposite polarity, the probability of flashover increases dramatically. Positive polarity dc charging leads to greater charge accumulation and more severe electric field distortion than negative polarity, thereby increasing the risk to the insulation performance.
{"title":"Effect of the DC–AC Switching Electric Field on Surface Electrical Properties of GIS Epoxy Spacer","authors":"Song Yanze;Zhang Yutong;Xie Jun;Liang Guishu;Ran Huijuan;Zhong Yuyao;Xia Guowei;Zhang Minhan;Zhang Zhenli;Xie Qing","doi":"10.1109/TDEI.2025.3543146","DOIUrl":"https://doi.org/10.1109/TDEI.2025.3543146","url":null,"abstract":"This article explores the behavior of charge transport and the surface electrical properties of epoxy spacers within high-voltage alternating current (HVac) gas-insulated switchgear (GIS), which may be exposed to the dc-ac switching electric field at the end of dc ice melting. Simulation and experimental results reveal that increasing dc voltage and duration enhances charge accumulation at the gas-solid interface, whose polarity aligns with the electrodes. When the electric field transitions to ac, charge accumulation occurs gradually during the half-cycle, where the voltage polarity matches the charge polarity. However, during the half-cycle of opposite polarity, the probability of flashover increases dramatically. Positive polarity dc charging leads to greater charge accumulation and more severe electric field distortion than negative polarity, thereby increasing the risk to the insulation performance.","PeriodicalId":13247,"journal":{"name":"IEEE Transactions on Dielectrics and Electrical Insulation","volume":"32 5","pages":"3028-3038"},"PeriodicalIF":3.1,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145210108","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-14DOI: 10.1109/TDEI.2025.3542749
Can Ding;Donghai Yu;Xianqiao Li;Daomin Min
For the prediction of each gas concentration in oil-immersed transformers, in this article, improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) is first applied to the original gas data, and the sample entropy (SE) value of each subsequence is computed, the high-frequency sequences with the highest SE are subjected to quadratic variational mode decomposition (VMD) to further reduce the degree of its instability, that is, the ICEEMDAN-SE-VMD decomposition model is formed. Second, reconstruction operations are performed on the subsequences with close SE values after ICEEMDAN decomposition to reduce the prediction time while ensuring the accuracy. Finally, a bidirectional long short-term memory with attention mechanism (Bi-LSTM-AT) is used to predict each subsequence separately; for the optimization of the parameters in prediction algorithms, the latest black-winged kite algorithm (BKA) is used in this article for optimization of the parameters, and the prediction results of the subsequence are superimposed to be the final prediction value for the gas concentration. The prediction results of the six gases produced by the transformer show that compared with other methods, the prediction method used in this article reduces the prediction time, while the prediction accuracy is also guaranteed.
{"title":"Transformer Dissolved Gas Concentration Prediction Based on Quadratic Decomposition Reconstruction and BKA-BiLSTM","authors":"Can Ding;Donghai Yu;Xianqiao Li;Daomin Min","doi":"10.1109/TDEI.2025.3542749","DOIUrl":"https://doi.org/10.1109/TDEI.2025.3542749","url":null,"abstract":"For the prediction of each gas concentration in oil-immersed transformers, in this article, improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) is first applied to the original gas data, and the sample entropy (SE) value of each subsequence is computed, the high-frequency sequences with the highest SE are subjected to quadratic variational mode decomposition (VMD) to further reduce the degree of its instability, that is, the ICEEMDAN-SE-VMD decomposition model is formed. Second, reconstruction operations are performed on the subsequences with close SE values after ICEEMDAN decomposition to reduce the prediction time while ensuring the accuracy. Finally, a bidirectional long short-term memory with attention mechanism (Bi-LSTM-AT) is used to predict each subsequence separately; for the optimization of the parameters in prediction algorithms, the latest black-winged kite algorithm (BKA) is used in this article for optimization of the parameters, and the prediction results of the subsequence are superimposed to be the final prediction value for the gas concentration. The prediction results of the six gases produced by the transformer show that compared with other methods, the prediction method used in this article reduces the prediction time, while the prediction accuracy is also guaranteed.","PeriodicalId":13247,"journal":{"name":"IEEE Transactions on Dielectrics and Electrical Insulation","volume":"32 4","pages":"2433-2442"},"PeriodicalIF":3.1,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144739863","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-14DOI: 10.1109/TDEI.2025.3542343
Ciptian Weried Priananda;Hazlee Azil Illias;Wong Jee Keen Raymond;I. Made Yulistiya Negara
Partial discharge (PD) monitoring plays a crucial role in identifying insulation defects in high-voltage rotating machinery, where accurate classification is essential for improving the reliability and efficiency of condition-based maintenance (CBM). This work proposes hybrid convolutional neural network (CNN) models to classify phase-resolved PD (PRPD) patterns from six different defects in a rotating machine insulation. Various hybrid models were evaluated by integrating CNN with machine learning (ML) algorithms, which include support vector machines (SVMs), k-nearest neighbors (KNNs), logistic regression (LR), decision trees (DTs), random forests (RFs), and naive Bayes (NB). The results reveal that all proposed hybrid models consistently outperform CNN in terms of computational efficiency, by achieving an average accuracy of 94.87% across all models using two optimizers, ADAM and stochastic gradient descent with momentum (SGDM). Notably, CNN-RF (CNN-RF) and CNN-KNN (CNN-KNN) models achieve the best performance, with an accuracy exceeding 96% with lower computational time compared to CNN, which only achieves 94.44% accuracy. Thus, this work provides valuable insight into enhancing PRPD classification with lower computational cost while increasing the classification accuracy of PRPD patterns from rotating machine insulation.
{"title":"Hybrid Deep Learning Models for Enhanced Classification of Phase-Resolved Partial Discharge Patterns From High-Voltage Rotating Machine Insulation","authors":"Ciptian Weried Priananda;Hazlee Azil Illias;Wong Jee Keen Raymond;I. Made Yulistiya Negara","doi":"10.1109/TDEI.2025.3542343","DOIUrl":"https://doi.org/10.1109/TDEI.2025.3542343","url":null,"abstract":"Partial discharge (PD) monitoring plays a crucial role in identifying insulation defects in high-voltage rotating machinery, where accurate classification is essential for improving the reliability and efficiency of condition-based maintenance (CBM). This work proposes hybrid convolutional neural network (CNN) models to classify phase-resolved PD (PRPD) patterns from six different defects in a rotating machine insulation. Various hybrid models were evaluated by integrating CNN with machine learning (ML) algorithms, which include support vector machines (SVMs), k-nearest neighbors (KNNs), logistic regression (LR), decision trees (DTs), random forests (RFs), and naive Bayes (NB). The results reveal that all proposed hybrid models consistently outperform CNN in terms of computational efficiency, by achieving an average accuracy of 94.87% across all models using two optimizers, ADAM and stochastic gradient descent with momentum (SGDM). Notably, CNN-RF (CNN-RF) and CNN-KNN (CNN-KNN) models achieve the best performance, with an accuracy exceeding 96% with lower computational time compared to CNN, which only achieves 94.44% accuracy. Thus, this work provides valuable insight into enhancing PRPD classification with lower computational cost while increasing the classification accuracy of PRPD patterns from rotating machine insulation.","PeriodicalId":13247,"journal":{"name":"IEEE Transactions on Dielectrics and Electrical Insulation","volume":"32 5","pages":"3059-3067"},"PeriodicalIF":3.1,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145210164","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-14DOI: 10.1109/TDEI.2025.3542752
Xize Dai;Jian Hao;Mohamed El Moursi;Rongxin Chen;Ruijin Liao;Claus Leth Bak
High-voltage (HV) crosslinked polyethylene (XLPE) cables are subjected to electrothermal stress gradients during service, which often leads to nonuniform degradation within insulation systems, significantly affecting their endurance, resilience, and overall lifetime. This article presents a comprehensive study of dielectric mechanisms and health state estimation of XLPE insulation under nonuniform thermal aging, with a particular emphasis on 500-kV XLPE cables. First, the distinct effects of uniform versus nonuniform thermal aging mechanisms on XLPE systems are compared through selected five combinations in two groups. Furthermore, the mechanisms by which nonuniform thermal aging influences XLPE insulation systems are revealed using three dielectric analysis techniques. Additionally, this work innovatively introduces a quantitative framework for the health state estimation of XLPE cable insulation under nonuniform thermal aging, utilizing the previously developed equivalent circuit model that incorporates a fractional-order circuit module (FOCM). The aging features extracted from the FOCM are utilized to develop health state estimation models for XLPE insulation under different nonuniform thermal aging conditions. The performance and limitations of health estimation models are discussed using a stacked XLPE system. This study deepens the understanding of nonuniform thermal aging mechanisms and provides insights to support condition-based maintenance of HV cable insulation under complex aging conditions.
{"title":"Dielectric Mechanisms and Health State Estimation for High-Voltage XLPE Cable Insulation Under Nonuniform Thermal Aging","authors":"Xize Dai;Jian Hao;Mohamed El Moursi;Rongxin Chen;Ruijin Liao;Claus Leth Bak","doi":"10.1109/TDEI.2025.3542752","DOIUrl":"https://doi.org/10.1109/TDEI.2025.3542752","url":null,"abstract":"High-voltage (HV) crosslinked polyethylene (XLPE) cables are subjected to electrothermal stress gradients during service, which often leads to nonuniform degradation within insulation systems, significantly affecting their endurance, resilience, and overall lifetime. This article presents a comprehensive study of dielectric mechanisms and health state estimation of XLPE insulation under nonuniform thermal aging, with a particular emphasis on 500-kV XLPE cables. First, the distinct effects of uniform versus nonuniform thermal aging mechanisms on XLPE systems are compared through selected five combinations in two groups. Furthermore, the mechanisms by which nonuniform thermal aging influences XLPE insulation systems are revealed using three dielectric analysis techniques. Additionally, this work innovatively introduces a quantitative framework for the health state estimation of XLPE cable insulation under nonuniform thermal aging, utilizing the previously developed equivalent circuit model that incorporates a fractional-order circuit module (FOCM). The aging features extracted from the FOCM are utilized to develop health state estimation models for XLPE insulation under different nonuniform thermal aging conditions. The performance and limitations of health estimation models are discussed using a stacked XLPE system. This study deepens the understanding of nonuniform thermal aging mechanisms and provides insights to support condition-based maintenance of HV cable insulation under complex aging conditions.","PeriodicalId":13247,"journal":{"name":"IEEE Transactions on Dielectrics and Electrical Insulation","volume":"32 5","pages":"2868-2876"},"PeriodicalIF":3.1,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145189971","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-13DOI: 10.1109/TDEI.2025.3542015
Haitao Wang;Shirong Zhang
An acoustic time reversal-convolutional neural network (ATR-CNN) approach is proposed for localizing partial discharge (PD) in power transformers with temperature compensation. A digital twin model is developed through multiphysics coupling analysis to accurately describe temperature distributions in oil-immersed natural air-cooling (ONAN) transformers. The temperature-compensated dual-sensor configuration demonstrates a root-mean-square error (RMSE) of 4.48 mm in PD localization, exhibiting a minimal accuracy degradation of 1.4 mm in unseen datasets while maintaining consistent performance across noise levels (0%–10%). Comparative analyses reveal the ATR-CNN methodology’s superior localization accuracy over traditional machine learning algorithms and enhanced performance in non-line-of-sight regions compared to the time difference of arrival (TDoA) approaches. A significant 264 000-fold reduction in computation time is achieved relative to ATR implementations. Integrating deep learning with ATR techniques offers an enhanced approach to PD localization in complex transformer environments.
{"title":"A Temperature-Compensated CNN-Based Method for Transformer Partial Discharge Localization","authors":"Haitao Wang;Shirong Zhang","doi":"10.1109/TDEI.2025.3542015","DOIUrl":"https://doi.org/10.1109/TDEI.2025.3542015","url":null,"abstract":"An acoustic time reversal-convolutional neural network (ATR-CNN) approach is proposed for localizing partial discharge (PD) in power transformers with temperature compensation. A digital twin model is developed through multiphysics coupling analysis to accurately describe temperature distributions in oil-immersed natural air-cooling (ONAN) transformers. The temperature-compensated dual-sensor configuration demonstrates a root-mean-square error (RMSE) of 4.48 mm in PD localization, exhibiting a minimal accuracy degradation of 1.4 mm in unseen datasets while maintaining consistent performance across noise levels (0%–10%). Comparative analyses reveal the ATR-CNN methodology’s superior localization accuracy over traditional machine learning algorithms and enhanced performance in non-line-of-sight regions compared to the time difference of arrival (TDoA) approaches. A significant 264 000-fold reduction in computation time is achieved relative to ATR implementations. Integrating deep learning with ATR techniques offers an enhanced approach to PD localization in complex transformer environments.","PeriodicalId":13247,"journal":{"name":"IEEE Transactions on Dielectrics and Electrical Insulation","volume":"32 5","pages":"2958-2967"},"PeriodicalIF":3.1,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145210090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-13DOI: 10.1109/TDEI.2025.3541613
Purnabhishek Muppala;C. C. Reddy
Despite being an experimentally well-studied phenomena, a consistent lacuna has always persisted in the theoretical and mathematical understanding of space charge dynamics in low-density polyethylene (LDPE). The macroscopic models reported so far in the literature seem to be insufficient and fail to predict the formation of homo- and hetero-charges near the electrodes and transport of charge packets. On the other hand, while microscopic models such as bipolar charge transport (BCT) model were able to explain homo-charge accumulation and movement of charge packets to a limited success, they are often fraught with assumptions such as neglection of diffusion phenomena and are structurally complicated when compared to macroscopic models. In this work, the authors have derived analytical solutions for space charge dynamics based on Maxwell’s equations and transient space charge limited current (TSLC)-based volumetric current models, which take into consideration the measured absorption (slow polarization) and steady-state volumetric currents. The proposed analytical (macroscopic) model can thus predict the homo- and hetero-charge accumulation in LDPE, which is validated through comparisons with the experimentally measured space charge, wherein a remarkable agreement was observed. Furthermore, the relation between the transient volumetric current and space charge dynamics is reaffirmed.
{"title":"Analytical Model for Transient Space Charge in Low-Density Polyethylene","authors":"Purnabhishek Muppala;C. C. Reddy","doi":"10.1109/TDEI.2025.3541613","DOIUrl":"https://doi.org/10.1109/TDEI.2025.3541613","url":null,"abstract":"Despite being an experimentally well-studied phenomena, a consistent lacuna has always persisted in the theoretical and mathematical understanding of space charge dynamics in low-density polyethylene (LDPE). The macroscopic models reported so far in the literature seem to be insufficient and fail to predict the formation of homo- and hetero-charges near the electrodes and transport of charge packets. On the other hand, while microscopic models such as bipolar charge transport (BCT) model were able to explain homo-charge accumulation and movement of charge packets to a limited success, they are often fraught with assumptions such as neglection of diffusion phenomena and are structurally complicated when compared to macroscopic models. In this work, the authors have derived analytical solutions for space charge dynamics based on Maxwell’s equations and transient space charge limited current (TSLC)-based volumetric current models, which take into consideration the measured absorption (slow polarization) and steady-state volumetric currents. The proposed analytical (macroscopic) model can thus predict the homo- and hetero-charge accumulation in LDPE, which is validated through comparisons with the experimentally measured space charge, wherein a remarkable agreement was observed. Furthermore, the relation between the transient volumetric current and space charge dynamics is reaffirmed.","PeriodicalId":13247,"journal":{"name":"IEEE Transactions on Dielectrics and Electrical Insulation","volume":"32 3","pages":"1567-1574"},"PeriodicalIF":2.9,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144205931","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-13DOI: 10.1109/TDEI.2025.3542009
Mahmoud A. Ali;Xingliang Jiang;Salah Kamel;Asad Awan
This study explores the impact of various high-voltage insulator string configurations on pollution and icing flashover characteristics under different environmental conditions. The inverted T-string design is suggested, offering improvements over the traditional I-string configuration. An experimental investigation is conducted using high-voltage glass-type disks (LD-160), along with the development of two artificial neural network (ANN) models to simulate and predict flashover voltages. The results demonstrate that the inverted T-string arrangement enhances the flashover voltage for polluted insulator strings by approximately 7% and increases the icing flashover voltage by 3.43%–5.01% compared to standard I-strings. The ANN models successfully determine optimal insulator configurations, demonstrating their potential to enhance high-voltage insulation performance with minimal experimentation. This study emphasizes the innovative use of ANN in optimizing insulator string arrangements, providing a practical solution for tackling pollution and icing issues in power systems.
{"title":"Enhancing Insulator String Performance: Pollution and Icing Flashover Analysis Through Artificial Neural Network-Based Layout Optimization for Inverted T-Type String","authors":"Mahmoud A. Ali;Xingliang Jiang;Salah Kamel;Asad Awan","doi":"10.1109/TDEI.2025.3542009","DOIUrl":"https://doi.org/10.1109/TDEI.2025.3542009","url":null,"abstract":"This study explores the impact of various high-voltage insulator string configurations on pollution and icing flashover characteristics under different environmental conditions. The inverted T-string design is suggested, offering improvements over the traditional I-string configuration. An experimental investigation is conducted using high-voltage glass-type disks (LD-160), along with the development of two artificial neural network (ANN) models to simulate and predict flashover voltages. The results demonstrate that the inverted T-string arrangement enhances the flashover voltage for polluted insulator strings by approximately 7% and increases the icing flashover voltage by 3.43%–5.01% compared to standard I-strings. The ANN models successfully determine optimal insulator configurations, demonstrating their potential to enhance high-voltage insulation performance with minimal experimentation. This study emphasizes the innovative use of ANN in optimizing insulator string arrangements, providing a practical solution for tackling pollution and icing issues in power systems.","PeriodicalId":13247,"journal":{"name":"IEEE Transactions on Dielectrics and Electrical Insulation","volume":"32 3","pages":"1653-1659"},"PeriodicalIF":2.9,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144205972","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：