Jing Yan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Jing Yan has a total of 130 co-authors. Here are the top co-authors by number of shared publications:
- Yanxin Wang
State Key Laboratory of Electrical Insulation and Power Equipment, Department of Electrical Engineering, Xian Jiaotong University, Xian, China
37 shared publications - Yingsan Geng
State Key Laboratory of Electrical Insulation and Power Equipment, Department of Electrical Engineering, Xian Jiaotong University, Xian, China
32 shared publications - Jianhua Wang
School of Electrical Engineering, Xian Jiaotong University, Xian, China
30 shared publications Yingsan Geng
State Key Laboratory of Electrical Insulation and Power Equipment, Xi’an Jiaotong University 1 , No. 28 XianNing West Road, Xi’an, Shaanxi Province 710049
19 shared publicationsZhiyuan Liu
State Key Laboratory of Electrical Insulation and Power Equipment, Xi’an Jiaotong University 1 , No. 28 XianNing West Road, Xi’an, Shaanxi Province 710049
15 shared publicationsJianhua Wang
14 shared publications
Latest Publications
- Open Access
- 1 November 2026
- Published by AIP Publishing in AIP Advances
- Vol. 16 (11)
Prestrike characteristics and dynamic dielectric breakdown mechanism of double-break vacuum circuit breakers under AC and DC voltages
Understanding the prestrike characteristics of vacuum circuit breakers is essential for phase-controlled closing and insulation design. Double-break vacuum circuit breakers (DBVCBs) are used in reactive power compensation, but most studies of their prestrike behavior have focused on DC conditions. Systematic comparisons with AC operation remain limited. This study compares the prestrike characteristics of a DBVCB at 20 and 30 kV under DC and power-frequency AC voltages, with AC levels specified as RMS values. Prestrike gaps, voltages, and average gap fields are characterized using Weibull fits, and macroscopic electric field distributions are simulated in ANSYS Maxwell. The AC statistical comparison is restricted to events near the positive voltage peak. At 30 kV, the median prestrike gap on the high-voltage side is 1.26 mm under AC, compared with 0.57 mm under DC. As the applied voltage increases, the median average prestrike field increases under DC but decreases under AC. The results highlight the coupling between voltage phase and contact motion during AC closing, while microscopic initiation mechanisms remain to be verified. These findings inform insulation design and phase-controlled closing strategies for DBVCBs.
- 1 November 2026
- Published by AIP Publishing in AIP Advances
- Vol. 16 (11)
Open AccessPrestrike characteristics and dynamic dielectric breakdown mechanism of double-break vacuum circuit breakers under AC and DC voltages
Understanding the prestrike characteristics of vacuum circuit breakers is essential for phase-controlled closing and insulation design. Double-break vacuum circuit breakers (DBVCBs) are used in reactive power compensation, but most studies of their prestrike behavior have focused on DC conditions. Systematic comparisons with AC operation remain limited. This study compares the prestrike characteristics of a DBVCB at 20 and 30 kV under DC and power-frequency AC voltages, with AC levels specified as RMS values. Prestrike gaps, voltages, and average gap fields are characterized using Weibull fits, and macroscopic electric field distributions are simulated in ANSYS Maxwell. The AC statistical comparison is restricted to events near the positive voltage peak. At 30 kV, the median prestrike gap on the high-voltage side is 1.26 mm under AC, compared with 0.57 mm under DC. As the applied voltage increases, the median average prestrike field increases under DC but decreases under AC. The results highlight the coupling between voltage phase and contact motion during AC closing, while microscopic initiation mechanisms remain to be verified. These findings inform insulation design and phase-controlled closing strategies for DBVCBs.
- 28 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 22 (7) , 6337-6348
A Two-Level Multisensor Fusion Network With Incremental Learning for Insulation Defect Diagnosis in Gas-Insulated Switchgear
Gas-insulated switchgear (GIS) insulation defect diagnosis faces persistent challenges due to heterogeneous multisensor signals, the lack of structured fusion across sensor types, and severe catastrophic forgetting under source-free streaming conditions. To address these issues, this article proposes a two-level fusion multisensor network with incremental learning (TFMNIL) for on-site diagnosis. Unlike conventional one-stage fusion strategies, the proposed framework separates multisensor fusion into channel-level fusion of homogeneous sensors to preserve consistent physical characteristics, and feature-level fusion of heterogeneous sensors to reduce cross-modal semantic discrepancies and redundancy. To support continual adaptation under evolving operating conditions, an incremental domain adaptation strategy is further developed. It integrates dynamic prototype updating to compensate for feature drift with classifier-weight–anchored cross-domain contrastive alignment, enabling stable class-level supervision without access to source data. Experiments on large-scale real-world multisensor GIS datasets show that TFMNIL achieves a diagnostic accuracy of 95.86% and maintains strong adaptability to newly emerging fault types in practical on-site scenarios.
- 28 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 22 (7) , 6337-6348
A Two-Level Multisensor Fusion Network With Incremental Learning for Insulation Defect Diagnosis in Gas-Insulated Switchgear
Gas-insulated switchgear (GIS) insulation defect diagnosis faces persistent challenges due to heterogeneous multisensor signals, the lack of structured fusion across sensor types, and severe catastrophic forgetting under source-free streaming conditions. To address these issues, this article proposes a two-level fusion multisensor network with incremental learning (TFMNIL) for on-site diagnosis. Unlike conventional one-stage fusion strategies, the proposed framework separates multisensor fusion into channel-level fusion of homogeneous sensors to preserve consistent physical characteristics, and feature-level fusion of heterogeneous sensors to reduce cross-modal semantic discrepancies and redundancy. To support continual adaptation under evolving operating conditions, an incremental domain adaptation strategy is further developed. It integrates dynamic prototype updating to compensate for feature drift with classifier-weight–anchored cross-domain contrastive alignment, enabling stable class-level supervision without access to source data. Experiments on large-scale real-world multisensor GIS datasets show that TFMNIL achieves a diagnostic accuracy of 95.86% and maintains strong adaptability to newly emerging fault types in practical on-site scenarios.
- 16 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 1-15
Electrochemical Coupled Federated Multisensor Measurement Framework for GIS Insulation Fault Detection and Diagnosis
Accurate insulation fault diagnosis in gas-insulated substations (GISs) is hindered by the limited sensitivity of single-sensor systems and the heterogeneity of field data. To enhance both measurement sensitivity and detection reliability of GIS insulation faults, this paper proposes an electro-chemical coupled federated multi-sensor fusion network (FMSFN) that integrates multi-modal sensing and distributed analytics into a unified measurement system. The proposed framework introduces a novel electro-chemical coupled detection mechanism that jointly captures electrical discharge characteristics and gas-chemical decomposition signatures to enable homogeneous and heterogeneous feature fusion under a federated cloud–edge architecture. This design supports distributed, privacy-preserving fault diagnosis across multiple users and devices. Within the proposed FMSFN, a deep fusion network equipped with an adaptive hybrid attention module is employed to strengthen cross-sensor feature interaction and enable dynamic modality-aware weighting, while a federated hierarchical optimization strategy with personalized updates and noise-aware aggregation ensures stable and robust convergence under non-IID data distributions. Experimental results demonstrate that the FMSFN achieves 97.23% accuracy and a 96.83% macro F1-score, consistently outperforming existing single-sensor and centralized diagnostic models. These results confirm the robustness, scalability, and practical applicability of the proposed electrochemical-coupled measurement system, which provides a scalable instrumentation approach for GIS insulation fault diagnosis.
- 16 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 1-15
Electrochemical Coupled Federated Multisensor Measurement Framework for GIS Insulation Fault Detection and Diagnosis
Accurate insulation fault diagnosis in gas-insulated substations (GISs) is hindered by the limited sensitivity of single-sensor systems and the heterogeneity of field data. To enhance both measurement sensitivity and detection reliability of GIS insulation faults, this paper proposes an electro-chemical coupled federated multi-sensor fusion network (FMSFN) that integrates multi-modal sensing and distributed analytics into a unified measurement system. The proposed framework introduces a novel electro-chemical coupled detection mechanism that jointly captures electrical discharge characteristics and gas-chemical decomposition signatures to enable homogeneous and heterogeneous feature fusion under a federated cloud–edge architecture. This design supports distributed, privacy-preserving fault diagnosis across multiple users and devices. Within the proposed FMSFN, a deep fusion network equipped with an adaptive hybrid attention module is employed to strengthen cross-sensor feature interaction and enable dynamic modality-aware weighting, while a federated hierarchical optimization strategy with personalized updates and noise-aware aggregation ensures stable and robust convergence under non-IID data distributions. Experimental results demonstrate that the FMSFN achieves 97.23% accuracy and a 96.83% macro F1-score, consistently outperforming existing single-sensor and centralized diagnostic models. These results confirm the robustness, scalability, and practical applicability of the proposed electrochemical-coupled measurement system, which provides a scalable instrumentation approach for GIS insulation fault diagnosis.
- 26 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dielectrics and Electrical Insulation
- Vol. PP (10709878) , 1
A Multimodal Large Language Model Framework for Partial Discharge Condition Assessment in Gas-Insulated Switchgear
Artificial intelligence–enabled partial discharge (PD) condition assessment in gas-insulated switchgear (GIS) is essential for ensuring reliable operation of power equipment. However, existing methods face significant challenges in dealing with heterogeneous signal modalities, limited labeled data, low multi-task adaptation efficiency, and poor interpretability. To overcome these limitations, this paper proposes a multimodal large language model (LLM) framework for unified PD condition assessment with causal interpretive capability. First, a PD signal unification module is developed to transform PD heterogeneous monitoring data into consistent token sequences, thereby mitigating sampling inconsistencies while retaining critical diagnostic features. Then, an LLM-based data augmentation module generates high-fidelity samples under defect-type and discharge-intensity constraints with self-correction and cross-modal consistency maintenance, alleviating data scarcity. Furthermore, a task-instructed prompt encoder and low-rank adaptation-based lightweight fine-tuning mechanism enable cross-modal semantic alignment and efficient task adaptation while improving interpretability and reducing computational cost. Experimental results demonstrate that the proposed framework achieves accuracies exceeding 98.5% across all tasks, substantially outperforming conventional approaches. The framework also provides interpretable textual reasoning that enhances diagnostic transparency and reliability, offering a promising pathway for intelligent condition assessment of GIS.
- 26 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dielectrics and Electrical Insulation
- Vol. PP (10709878) , 1
A Multimodal Large Language Model Framework for Partial Discharge Condition Assessment in Gas-Insulated Switchgear
Artificial intelligence–enabled partial discharge (PD) condition assessment in gas-insulated switchgear (GIS) is essential for ensuring reliable operation of power equipment. However, existing methods face significant challenges in dealing with heterogeneous signal modalities, limited labeled data, low multi-task adaptation efficiency, and poor interpretability. To overcome these limitations, this paper proposes a multimodal large language model (LLM) framework for unified PD condition assessment with causal interpretive capability. First, a PD signal unification module is developed to transform PD heterogeneous monitoring data into consistent token sequences, thereby mitigating sampling inconsistencies while retaining critical diagnostic features. Then, an LLM-based data augmentation module generates high-fidelity samples under defect-type and discharge-intensity constraints with self-correction and cross-modal consistency maintenance, alleviating data scarcity. Furthermore, a task-instructed prompt encoder and low-rank adaptation-based lightweight fine-tuning mechanism enable cross-modal semantic alignment and efficient task adaptation while improving interpretability and reducing computational cost. Experimental results demonstrate that the proposed framework achieves accuracies exceeding 98.5% across all tasks, substantially outperforming conventional approaches. The framework also provides interpretable textual reasoning that enhances diagnostic transparency and reliability, offering a promising pathway for intelligent condition assessment of GIS.
- 18 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industry Applications
- Vol. PP (00939994) , 1-10
Multi-Task Learning Network-Based Condition Assessment of GIS Partial Discharge: Diagnosis and Severity Evaluation
Current methods for assessing the state of partial discharge (PD) in gas-insulated switchgear (GIS) often treat the diagnosis and severity evaluation tasks independently, which limits model performance and overlooks the role of defect types in the PD development stages. To address these issues, this paper proposes a novel multi-task network for the condition assessment of PD in GIS. Firstly, a lightweight attention combined with an expert network module is introduced to explore the correlations between different tasks while retaining their unique features. Secondly, we incorporate a convolutional neural network (CNN)-Transformer module to capture both local and global features of GIS PD signals. Finally, we implement a dynamic weight averaging method for the multi-task network, which adaptively adjusts the loss weights via the variation rate of the losses of each sub-task. We conducted experiments on two GIS PD datasets with different insulating gases. Experimental results demonstrate that the multi-task network significantly improves the performance of each sub-task in GIS condition assessment, advancing the development stage evaluation of PD for various insulation defects. Furthermore, experiments on two types of insulating gases validate the generalization and versatility of the proposed method.
- 18 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industry Applications
- Vol. PP (00939994) , 1-10
Multi-Task Learning Network-Based Condition Assessment of GIS Partial Discharge: Diagnosis and Severity Evaluation
Current methods for assessing the state of partial discharge (PD) in gas-insulated switchgear (GIS) often treat the diagnosis and severity evaluation tasks independently, which limits model performance and overlooks the role of defect types in the PD development stages. To address these issues, this paper proposes a novel multi-task network for the condition assessment of PD in GIS. Firstly, a lightweight attention combined with an expert network module is introduced to explore the correlations between different tasks while retaining their unique features. Secondly, we incorporate a convolutional neural network (CNN)-Transformer module to capture both local and global features of GIS PD signals. Finally, we implement a dynamic weight averaging method for the multi-task network, which adaptively adjusts the loss weights via the variation rate of the losses of each sub-task. We conducted experiments on two GIS PD datasets with different insulating gases. Experimental results demonstrate that the multi-task network significantly improves the performance of each sub-task in GIS condition assessment, advancing the development stage evaluation of PD for various insulation defects. Furthermore, experiments on two types of insulating gases validate the generalization and versatility of the proposed method.
- Open Access
Enhanced Mechanical Fault Diagnosis of High-Voltage Circuit Breakers Using a Multi-Strategy Improved Dung Beetle Algorithm and Support Vector Machine
High-voltage circuit breakers (HVCBs) are critical switching devices whose mechanical reliability directly affects power system safety and operational continuity. Accurate fault diagnosis remains challenging due to nonlinear vibration characteristics and the sensitivity of support vector machines (SVMs) to hyperparameter selection. To address this issue, a multi-strategy improved dung beetle optimization–support vector machine (MIDBO–SVM) framework is proposed for vibration-based mechanical fault diagnosis. Frequency-domain features are extracted from vibration signals using the fast Fourier transform to characterize fault-related spectral variations. A multi-strategy improved dung beetle optimization (MIDBO) algorithm incorporating chaotic initialization, adaptive search regulation, and mutation enhancement is developed to improve population diversity, global exploration, and convergence stability. The optimized MIDBO is used to determine the penalty and kernel parameters of the SVM, constructing a robust and well-generalized diagnostic model. Experimental results show that MIDBO–SVM achieves a diagnostic accuracy of 96.67%, outperforming conventional SVM (86.25%) and random forest (89.17%). The proposed method also demonstrates faster convergence and maintains accuracy above 86% under imbalanced sample conditions, confirming its robustness and generalization capability. These advantages contribute to more reliable mechanical condition assessment and improved maintenance decision support for HVCBs.
Open AccessEnhanced Mechanical Fault Diagnosis of High-Voltage Circuit Breakers Using a Multi-Strategy Improved Dung Beetle Algorithm and Support Vector Machine
High-voltage circuit breakers (HVCBs) are critical switching devices whose mechanical reliability directly affects power system safety and operational continuity. Accurate fault diagnosis remains challenging due to nonlinear vibration characteristics and the sensitivity of support vector machines (SVMs) to hyperparameter selection. To address this issue, a multi-strategy improved dung beetle optimization–support vector machine (MIDBO–SVM) framework is proposed for vibration-based mechanical fault diagnosis. Frequency-domain features are extracted from vibration signals using the fast Fourier transform to characterize fault-related spectral variations. A multi-strategy improved dung beetle optimization (MIDBO) algorithm incorporating chaotic initialization, adaptive search regulation, and mutation enhancement is developed to improve population diversity, global exploration, and convergence stability. The optimized MIDBO is used to determine the penalty and kernel parameters of the SVM, constructing a robust and well-generalized diagnostic model. Experimental results show that MIDBO–SVM achieves a diagnostic accuracy of 96.67%, outperforming conventional SVM (86.25%) and random forest (89.17%). The proposed method also demonstrates faster convergence and maintains accuracy above 86% under imbalanced sample conditions, confirming its robustness and generalization capability. These advantages contribute to more reliable mechanical condition assessment and improved maintenance decision support for HVCBs.
- 10 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dielectrics and Electrical Insulation
- Vol. 33 (2) , 1529-1538
Small-Sample Partial Discharge Diagnosis for GIS Based on Improved Capsule Generative Adversarial Network and Dual-Mode Generator Optimization
Data-driven deep learning methods excel in gas insulated switchgear (GIS) partial discharge (PD) diagnosis, but their performance falters in data-scarce scenarios. Constrained by the intricate operating environment of GIS and the transient and stochastic nature of PD, acquiring sufficient PD samples in practical applications remains challenging. Therefore, this paper proposes an improved capsule generative adversarial network (GAN) for small-sample GIS PD diagnosis. Firstly, capsule network is introduced in both the generator and the discriminator to extract more comprehensive feature information from PD signals, thus avoiding the potential loss of crucial features due to pooling operations. Then, a dual-mode optimization method is used to update the model parameters of the generator, and sample quality and diversity are used as evaluation indicators to guide the training process of the generator, realizing automatic optimization of generator parameter-level model construction. Meanwhile, the discriminator stabilizes the GAN training by adopting the Wasserstein distance and incorporating a gradient penalty term. Experimental results show that the proposed method achieves diagnostic accuracy of 97.47% in small datasets, significantly outperforming other methods and exhibiting robust performance, provides a viable solution for high-precision and robust GIS PD diagnosis with limited samples.
- 10 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dielectrics and Electrical Insulation
- Vol. 33 (2) , 1529-1538
Small-Sample Partial Discharge Diagnosis for GIS Based on Improved Capsule Generative Adversarial Network and Dual-Mode Generator Optimization
Data-driven deep learning methods excel in gas insulated switchgear (GIS) partial discharge (PD) diagnosis, but their performance falters in data-scarce scenarios. Constrained by the intricate operating environment of GIS and the transient and stochastic nature of PD, acquiring sufficient PD samples in practical applications remains challenging. Therefore, this paper proposes an improved capsule generative adversarial network (GAN) for small-sample GIS PD diagnosis. Firstly, capsule network is introduced in both the generator and the discriminator to extract more comprehensive feature information from PD signals, thus avoiding the potential loss of crucial features due to pooling operations. Then, a dual-mode optimization method is used to update the model parameters of the generator, and sample quality and diversity are used as evaluation indicators to guide the training process of the generator, realizing automatic optimization of generator parameter-level model construction. Meanwhile, the discriminator stabilizes the GAN training by adopting the Wasserstein distance and incorporating a gradient penalty term. Experimental results show that the proposed method achieves diagnostic accuracy of 97.47% in small datasets, significantly outperforming other methods and exhibiting robust performance, provides a viable solution for high-precision and robust GIS PD diagnosis with limited samples.
- Open Access
- 1 February 2026
- Published by AIP Publishing in AIP Advances
- Vol. 16 (2)
Investigation of arc contact erosion characteristics in SF6 circuit breakers
To address the erosion of arc contacts caused by repeated current interruptions in SF6 circuit breakers and to ensure the safe and stable operation of the power grid, this study employs numerical simulation methods to investigate the erosion characteristics of the contacts and validates the results through experiments. A thermodynamic model of arc-contact melting is established, and the level-set method is used to track the free surface while comprehensively considering heat transfer, phase change, and evaporative ablation. The temperature field, velocity field, and surface morphology evolution of the molten pool are obtained, and the melting, flow, and evaporation behavior of CuW80 contacts under a 20 kA interrupting current and a heat flux density of 4.9 × 109 W/m2 are systematically analyzed. The results show that the maximum temperature of the molten pool varies with the flow of the liquid metal, and the maximum depth and width of the crater are 0.09 and 1.997 mm, respectively. Under the combined action of recoil pressure, surface tension, and the Marangoni force, the maximum velocity of the liquid metal occurs in the tangential direction at the crater edge. The analysis of material properties indicates that thermal conductivity has the most significant influence on the molten-pool temperature. Reducing the latent heat of vaporization, increasing the boiling point, and decreasing the atomic molar mass can effectively suppress the evaporative mass flux, among which increasing the boiling point is the most effective. This study provides a theoretical basis for the design and optimization of arc-contact materials with enhanced erosion resistance.
- 1 February 2026
- Published by AIP Publishing in AIP Advances
- Vol. 16 (2)
Open AccessInvestigation of arc contact erosion characteristics in SF6 circuit breakers
To address the erosion of arc contacts caused by repeated current interruptions in SF6 circuit breakers and to ensure the safe and stable operation of the power grid, this study employs numerical simulation methods to investigate the erosion characteristics of the contacts and validates the results through experiments. A thermodynamic model of arc-contact melting is established, and the level-set method is used to track the free surface while comprehensively considering heat transfer, phase change, and evaporative ablation. The temperature field, velocity field, and surface morphology evolution of the molten pool are obtained, and the melting, flow, and evaporation behavior of CuW80 contacts under a 20 kA interrupting current and a heat flux density of 4.9 × 109 W/m2 are systematically analyzed. The results show that the maximum temperature of the molten pool varies with the flow of the liquid metal, and the maximum depth and width of the crater are 0.09 and 1.997 mm, respectively. Under the combined action of recoil pressure, surface tension, and the Marangoni force, the maximum velocity of the liquid metal occurs in the tangential direction at the crater edge. The analysis of material properties indicates that thermal conductivity has the most significant influence on the molten-pool temperature. Reducing the latent heat of vaporization, increasing the boiling point, and decreasing the atomic molar mass can effectively suppress the evaporative mass flux, among which increasing the boiling point is the most effective. This study provides a theoretical basis for the design and optimization of arc-contact materials with enhanced erosion resistance.