Diagnostic Model for Transformer Core Loosening Faults Based on the Gram Angle Field and Multi-Head Attention Mechanism
Aiming to address the problems of difficulty in selecting characteristic quantities and the reliance on manual experience in the diagnosis of transformer core loosening faults, a diagnosis method for transformer core looseness based on the Gram angle field (GAF), residual network (ResNet), and multi...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/14/23/10906 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846124486423740416 |
|---|---|
| author | Junyu Chen Nana Duan Xikun Zhou Ziyu Wang |
| author_facet | Junyu Chen Nana Duan Xikun Zhou Ziyu Wang |
| author_sort | Junyu Chen |
| collection | DOAJ |
| description | Aiming to address the problems of difficulty in selecting characteristic quantities and the reliance on manual experience in the diagnosis of transformer core loosening faults, a diagnosis method for transformer core looseness based on the Gram angle field (GAF), residual network (ResNet), and multi-head attention mechanism (MA) is proposed. This method automatically learns effective fault features directly from GAF images without the need for manual feature extraction. Firstly, the vibration signal is denoised using ensemble empirical mode decomposition (EEMD), and the one-dimensional temporal signal is converted into a two-dimensional image using Gram angle field to generate an image dataset. Subsequently, the image set is input into ResNet to train the model, and the output of ResNet is weighted and summed using a multi-head attention module to obtain the deep feature representation of the image signal. Finally, the classification probabilities of different iron-core loosening states of the transformer are output through fully connected layers and Softmax layers. The experimental results show that the diagnostic model proposed in this paper has an accuracy of 99.52% in identifying loose iron cores in transformers, and can effectively identify loose iron cores in different positions. It is suitable for the identification and diagnosis of loose iron cores in transformers. Compared with traditional methods, this method has better fault classification performance and noise resistance. |
| format | Article |
| id | doaj-art-1f004f5dffb04f609e6c41d419c8d7ee |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-1f004f5dffb04f609e6c41d419c8d7ee2024-12-13T16:22:07ZengMDPI AGApplied Sciences2076-34172024-11-0114231090610.3390/app142310906Diagnostic Model for Transformer Core Loosening Faults Based on the Gram Angle Field and Multi-Head Attention MechanismJunyu Chen0Nana Duan1Xikun Zhou2Ziyu Wang3State Key Laboratory of Electrical Insulation and Power Equipment, Xi’an Jiaotong University, Xi’an 710049, ChinaState Key Laboratory of Electrical Insulation and Power Equipment, Xi’an Jiaotong University, Xi’an 710049, ChinaState Key Laboratory of Electrical Insulation and Power Equipment, Xi’an Jiaotong University, Xi’an 710049, ChinaState Key Laboratory of Electrical Insulation and Power Equipment, Xi’an Jiaotong University, Xi’an 710049, ChinaAiming to address the problems of difficulty in selecting characteristic quantities and the reliance on manual experience in the diagnosis of transformer core loosening faults, a diagnosis method for transformer core looseness based on the Gram angle field (GAF), residual network (ResNet), and multi-head attention mechanism (MA) is proposed. This method automatically learns effective fault features directly from GAF images without the need for manual feature extraction. Firstly, the vibration signal is denoised using ensemble empirical mode decomposition (EEMD), and the one-dimensional temporal signal is converted into a two-dimensional image using Gram angle field to generate an image dataset. Subsequently, the image set is input into ResNet to train the model, and the output of ResNet is weighted and summed using a multi-head attention module to obtain the deep feature representation of the image signal. Finally, the classification probabilities of different iron-core loosening states of the transformer are output through fully connected layers and Softmax layers. The experimental results show that the diagnostic model proposed in this paper has an accuracy of 99.52% in identifying loose iron cores in transformers, and can effectively identify loose iron cores in different positions. It is suitable for the identification and diagnosis of loose iron cores in transformers. Compared with traditional methods, this method has better fault classification performance and noise resistance.https://www.mdpi.com/2076-3417/14/23/10906transformer vibrationloose iron coreGram angle fieldmulti-head attention mechanismfault diagnosis |
| spellingShingle | Junyu Chen Nana Duan Xikun Zhou Ziyu Wang Diagnostic Model for Transformer Core Loosening Faults Based on the Gram Angle Field and Multi-Head Attention Mechanism Applied Sciences transformer vibration loose iron core Gram angle field multi-head attention mechanism fault diagnosis |
| title | Diagnostic Model for Transformer Core Loosening Faults Based on the Gram Angle Field and Multi-Head Attention Mechanism |
| title_full | Diagnostic Model for Transformer Core Loosening Faults Based on the Gram Angle Field and Multi-Head Attention Mechanism |
| title_fullStr | Diagnostic Model for Transformer Core Loosening Faults Based on the Gram Angle Field and Multi-Head Attention Mechanism |
| title_full_unstemmed | Diagnostic Model for Transformer Core Loosening Faults Based on the Gram Angle Field and Multi-Head Attention Mechanism |
| title_short | Diagnostic Model for Transformer Core Loosening Faults Based on the Gram Angle Field and Multi-Head Attention Mechanism |
| title_sort | diagnostic model for transformer core loosening faults based on the gram angle field and multi head attention mechanism |
| topic | transformer vibration loose iron core Gram angle field multi-head attention mechanism fault diagnosis |
| url | https://www.mdpi.com/2076-3417/14/23/10906 |
| work_keys_str_mv | AT junyuchen diagnosticmodelfortransformercorelooseningfaultsbasedonthegramanglefieldandmultiheadattentionmechanism AT nanaduan diagnosticmodelfortransformercorelooseningfaultsbasedonthegramanglefieldandmultiheadattentionmechanism AT xikunzhou diagnosticmodelfortransformercorelooseningfaultsbasedonthegramanglefieldandmultiheadattentionmechanism AT ziyuwang diagnosticmodelfortransformercorelooseningfaultsbasedonthegramanglefieldandmultiheadattentionmechanism |