Composite Insulator Defect Identification Method Based on Acoustic–Electric Feature Fusion and MMSAE Network
Aiming to solve the partial discharge problem caused by defects in composite insulators, most existing live detection methods are limited by the subjectivity of human judgment, the difficulty of effective quantification, and the use of a single detection method. Therefore, a composite insulator defe...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/16/13/4906 |
| _version_ | 1797591833118769152 |
|---|---|
| author | Bizhen Zhang Shengwen Shu Cheng Chen Xiaojie Wang Jun Xu Chaoying Fang |
| author_facet | Bizhen Zhang Shengwen Shu Cheng Chen Xiaojie Wang Jun Xu Chaoying Fang |
| author_sort | Bizhen Zhang |
| collection | DOAJ |
| description | Aiming to solve the partial discharge problem caused by defects in composite insulators, most existing live detection methods are limited by the subjectivity of human judgment, the difficulty of effective quantification, and the use of a single detection method. Therefore, a composite insulator defect diagnosis model based on acoustic–electric feature fusion and a multi-scale perception multi-input of stacked auto-encoder (MMSAE) network is proposed in this paper. Initially, during the withstanding voltage experiment, the electromagnetic wave spectrometer and ultrasonic detector were used to collect and process the data of six types of composite insulator samples with artificial defects. The electromagnetic wave spectrum, ultrasonic power spectral density, and <i>n</i>-<i>S</i> map were then obtained. Then, the network architecture of MMSAE was built by integrating a stacked auto-encoder and multi-scale perception module; the feature extraction and fusion methods of the electromagnetic wave spectrum and ultrasonic signal were investigated. The proposed method was used to diagnose test samples, and the diagnostic results were compared to those obtained using a single input source and the artificial neural network (ANN) method. The results demonstrate that the detection accuracy of acoustic–electric feature fusion is greater than that of a single feature; the accuracy of the proposed method is 99.17%, which is significantly higher than the accuracy of the conventional ANN method. Finally, composite insulator defect diagnosis software based on PYQT5 and Keras was developed. Ten 500 kV aging composite insulators were used to validate the effectiveness of the proposed method and design software. |
| first_indexed | 2024-03-11T01:42:59Z |
| format | Article |
| id | doaj.art-6ad07298c48d4a9ba025a9eb5fed5540 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-11T01:42:59Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-6ad07298c48d4a9ba025a9eb5fed55402023-11-18T16:27:34ZengMDPI AGEnergies1996-10732023-06-011613490610.3390/en16134906Composite Insulator Defect Identification Method Based on Acoustic–Electric Feature Fusion and MMSAE NetworkBizhen Zhang0Shengwen Shu1Cheng Chen2Xiaojie Wang3Jun Xu4Chaoying Fang5School of Electrical Engineering and Automation, Fuzhou University, Fuzhou 350108, ChinaSchool of Electrical Engineering and Automation, Fuzhou University, Fuzhou 350108, ChinaFuzhou Power Supply Company, State Grid Fujian Electric Power Co., Ltd., Fuzhou 350009, ChinaElectric Power Research Institute, State Grid Fujian Electric Power Co., Ltd., Fuzhou 350007, ChinaElectric Power Research Institute, State Grid Fujian Electric Power Co., Ltd., Fuzhou 350007, ChinaElectric Power Research Institute, State Grid Fujian Electric Power Co., Ltd., Fuzhou 350007, ChinaAiming to solve the partial discharge problem caused by defects in composite insulators, most existing live detection methods are limited by the subjectivity of human judgment, the difficulty of effective quantification, and the use of a single detection method. Therefore, a composite insulator defect diagnosis model based on acoustic–electric feature fusion and a multi-scale perception multi-input of stacked auto-encoder (MMSAE) network is proposed in this paper. Initially, during the withstanding voltage experiment, the electromagnetic wave spectrometer and ultrasonic detector were used to collect and process the data of six types of composite insulator samples with artificial defects. The electromagnetic wave spectrum, ultrasonic power spectral density, and <i>n</i>-<i>S</i> map were then obtained. Then, the network architecture of MMSAE was built by integrating a stacked auto-encoder and multi-scale perception module; the feature extraction and fusion methods of the electromagnetic wave spectrum and ultrasonic signal were investigated. The proposed method was used to diagnose test samples, and the diagnostic results were compared to those obtained using a single input source and the artificial neural network (ANN) method. The results demonstrate that the detection accuracy of acoustic–electric feature fusion is greater than that of a single feature; the accuracy of the proposed method is 99.17%, which is significantly higher than the accuracy of the conventional ANN method. Finally, composite insulator defect diagnosis software based on PYQT5 and Keras was developed. Ten 500 kV aging composite insulators were used to validate the effectiveness of the proposed method and design software.https://www.mdpi.com/1996-1073/16/13/4906composite insulatordefect identificationdeep learningfeature fusionelectromagnetic wave spectrumultrasonic |
| spellingShingle | Bizhen Zhang Shengwen Shu Cheng Chen Xiaojie Wang Jun Xu Chaoying Fang Composite Insulator Defect Identification Method Based on Acoustic–Electric Feature Fusion and MMSAE Network Energies composite insulator defect identification deep learning feature fusion electromagnetic wave spectrum ultrasonic |
| title | Composite Insulator Defect Identification Method Based on Acoustic–Electric Feature Fusion and MMSAE Network |
| title_full | Composite Insulator Defect Identification Method Based on Acoustic–Electric Feature Fusion and MMSAE Network |
| title_fullStr | Composite Insulator Defect Identification Method Based on Acoustic–Electric Feature Fusion and MMSAE Network |
| title_full_unstemmed | Composite Insulator Defect Identification Method Based on Acoustic–Electric Feature Fusion and MMSAE Network |
| title_short | Composite Insulator Defect Identification Method Based on Acoustic–Electric Feature Fusion and MMSAE Network |
| title_sort | composite insulator defect identification method based on acoustic electric feature fusion and mmsae network |
| topic | composite insulator defect identification deep learning feature fusion electromagnetic wave spectrum ultrasonic |
| url | https://www.mdpi.com/1996-1073/16/13/4906 |
| work_keys_str_mv | AT bizhenzhang compositeinsulatordefectidentificationmethodbasedonacousticelectricfeaturefusionandmmsaenetwork AT shengwenshu compositeinsulatordefectidentificationmethodbasedonacousticelectricfeaturefusionandmmsaenetwork AT chengchen compositeinsulatordefectidentificationmethodbasedonacousticelectricfeaturefusionandmmsaenetwork AT xiaojiewang compositeinsulatordefectidentificationmethodbasedonacousticelectricfeaturefusionandmmsaenetwork AT junxu compositeinsulatordefectidentificationmethodbasedonacousticelectricfeaturefusionandmmsaenetwork AT chaoyingfang compositeinsulatordefectidentificationmethodbasedonacousticelectricfeaturefusionandmmsaenetwork |