Diagnosis of Commutation Failure in a High- Voltage Direct Current Transmission System Based on Fuzzy Entropy Feature Vectors and a PCNN-GRU
To enhance the diagnostic accuracy of commutation failure in weak receiving-end high-voltage direct current (HVDC) transmission systems, this study proposes a novel diagnostic model that integrates Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN)-based fuzzy entropy and a...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11048891/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849422270392434688 |
|---|---|
| author | Cao Ruirui Yang Taigang Li Guohui Chen Shilong |
| author_facet | Cao Ruirui Yang Taigang Li Guohui Chen Shilong |
| author_sort | Cao Ruirui |
| collection | DOAJ |
| description | To enhance the diagnostic accuracy of commutation failure in weak receiving-end high-voltage direct current (HVDC) transmission systems, this study proposes a novel diagnostic model that integrates Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN)-based fuzzy entropy and a Parallel Convolutional Gated Recurrent Unit Neural Network (PCNN-GRU). The model initially decomposes the rectifier-side DC voltage signal through CEEMDAN to obtain the high- and low-frequency characteristic components of fault voltages, followed by fuzzy entropy calculation for each component to construct the fault diagnosis input matrix. Subsequently, the PCNN-GRU architecture performs deep feature extraction through two distinct mechanisms: the PCNN branch employs dual-path convolutional kernels of varying sizes for multidimensional feature mining, whereas the GRU network enhances temporal feature extraction capabilities. The simulation results demonstrate the model’s exceptional performance in discriminating DC line faults and commutation failures, achieving diagnostic accuracies of 98.75%, 99.17%, and 99.5833% under 20 dB, 30 dB, and noise-free environments, respectively, significantly outperforming conventional deep learning models. The proposed approach not only improves diagnostic precision, but also exhibits remarkable noise immunity, providing a novel methodology for HVDC commutation failure detection. This breakthrough research offers critical technical support for stable HVDC system operation and holds significant application value for smart grid maintenance. |
| format | Article |
| id | doaj-art-8c8ec5dd86df4d7b98f7623c7cdad86f |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-8c8ec5dd86df4d7b98f7623c7cdad86f2025-08-20T03:31:10ZengIEEEIEEE Access2169-35362025-01-011311070911072410.1109/ACCESS.2025.358272311048891Diagnosis of Commutation Failure in a High- Voltage Direct Current Transmission System Based on Fuzzy Entropy Feature Vectors and a PCNN-GRUCao Ruirui0https://orcid.org/0009-0002-1364-0034Yang Taigang1https://orcid.org/0009-0005-0152-5153Li Guohui2Chen Shilong3Chongqing Vocational Institute of Safety Technology, Wanzhou, Chongqing, ChinaSchool of Electrical Engineering, Kunming University of Science and Technology, Kunming, ChinaQujing Power Supply Bureau, Yunnan Power Grid Company Ltd.,, Qujing, Yunnan, ChinaSchool of Electrical Engineering, Kunming University of Science and Technology, Kunming, ChinaTo enhance the diagnostic accuracy of commutation failure in weak receiving-end high-voltage direct current (HVDC) transmission systems, this study proposes a novel diagnostic model that integrates Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN)-based fuzzy entropy and a Parallel Convolutional Gated Recurrent Unit Neural Network (PCNN-GRU). The model initially decomposes the rectifier-side DC voltage signal through CEEMDAN to obtain the high- and low-frequency characteristic components of fault voltages, followed by fuzzy entropy calculation for each component to construct the fault diagnosis input matrix. Subsequently, the PCNN-GRU architecture performs deep feature extraction through two distinct mechanisms: the PCNN branch employs dual-path convolutional kernels of varying sizes for multidimensional feature mining, whereas the GRU network enhances temporal feature extraction capabilities. The simulation results demonstrate the model’s exceptional performance in discriminating DC line faults and commutation failures, achieving diagnostic accuracies of 98.75%, 99.17%, and 99.5833% under 20 dB, 30 dB, and noise-free environments, respectively, significantly outperforming conventional deep learning models. The proposed approach not only improves diagnostic precision, but also exhibits remarkable noise immunity, providing a novel methodology for HVDC commutation failure detection. This breakthrough research offers critical technical support for stable HVDC system operation and holds significant application value for smart grid maintenance.https://ieeexplore.ieee.org/document/11048891/Commutation failureconvolutional neural networkempirical mode decompositionfuzzy entropyhigh voltage direct current (HVDC) transmission |
| spellingShingle | Cao Ruirui Yang Taigang Li Guohui Chen Shilong Diagnosis of Commutation Failure in a High- Voltage Direct Current Transmission System Based on Fuzzy Entropy Feature Vectors and a PCNN-GRU IEEE Access Commutation failure convolutional neural network empirical mode decomposition fuzzy entropy high voltage direct current (HVDC) transmission |
| title | Diagnosis of Commutation Failure in a High- Voltage Direct Current Transmission System Based on Fuzzy Entropy Feature Vectors and a PCNN-GRU |
| title_full | Diagnosis of Commutation Failure in a High- Voltage Direct Current Transmission System Based on Fuzzy Entropy Feature Vectors and a PCNN-GRU |
| title_fullStr | Diagnosis of Commutation Failure in a High- Voltage Direct Current Transmission System Based on Fuzzy Entropy Feature Vectors and a PCNN-GRU |
| title_full_unstemmed | Diagnosis of Commutation Failure in a High- Voltage Direct Current Transmission System Based on Fuzzy Entropy Feature Vectors and a PCNN-GRU |
| title_short | Diagnosis of Commutation Failure in a High- Voltage Direct Current Transmission System Based on Fuzzy Entropy Feature Vectors and a PCNN-GRU |
| title_sort | diagnosis of commutation failure in a high voltage direct current transmission system based on fuzzy entropy feature vectors and a pcnn gru |
| topic | Commutation failure convolutional neural network empirical mode decomposition fuzzy entropy high voltage direct current (HVDC) transmission |
| url | https://ieeexplore.ieee.org/document/11048891/ |
| work_keys_str_mv | AT caoruirui diagnosisofcommutationfailureinahighvoltagedirectcurrenttransmissionsystembasedonfuzzyentropyfeaturevectorsandapcnngru AT yangtaigang diagnosisofcommutationfailureinahighvoltagedirectcurrenttransmissionsystembasedonfuzzyentropyfeaturevectorsandapcnngru AT liguohui diagnosisofcommutationfailureinahighvoltagedirectcurrenttransmissionsystembasedonfuzzyentropyfeaturevectorsandapcnngru AT chenshilong diagnosisofcommutationfailureinahighvoltagedirectcurrenttransmissionsystembasedonfuzzyentropyfeaturevectorsandapcnngru |