A dimension-enhanced residual multi-scale attention framework for identifying anomalous waveforms of fault recorders
The continuous introduction of technologies such as distributed generation, wind power, and photovoltaic energy poses challenges to identifying abnormal waveforms in power disturbances. Due to the constant increase in abnormal features, existing waveform recognition schemes for power disturbance abn...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | International Journal of Electrical Power & Energy Systems |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0142061524006008 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832595404425789440 |
|---|---|
| author | Lixin Jia Lihang Feng Dong Wang Jiapeng Jiang Guannan Wang Jiantao Shi |
| author_facet | Lixin Jia Lihang Feng Dong Wang Jiapeng Jiang Guannan Wang Jiantao Shi |
| author_sort | Lixin Jia |
| collection | DOAJ |
| description | The continuous introduction of technologies such as distributed generation, wind power, and photovoltaic energy poses challenges to identifying abnormal waveforms in power disturbances. Due to the constant increase in abnormal features, existing waveform recognition schemes for power disturbance abnormalities cannot meet the requirements of high accuracy and reliability. In this paper, a Dimension-Enhanced Residual Multi-Scale Attention Framework for identifying power disturbance abnormal waveforms is proposed. This framework first employs the Phase Adaptive Adjustment (PAA) method to address the phase offset problem of original recording data, then uses the Gramian Angle Field method to perform dimensionality expansion on the data processed by PAA, and finally utilizes the Residual Pyramid Squeeze Attention Network (ResPSANet) for identifying power disturbance abnormal waveforms. Experiments demonstrate that the proposed approach improves the performance of power disturbance abnormal waveform recognition by 10% compared to existing schemes. |
| format | Article |
| id | doaj-art-7aee699331b14000ac535dc154f90ae6 |
| institution | Kabale University |
| issn | 0142-0615 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Electrical Power & Energy Systems |
| spelling | doaj-art-7aee699331b14000ac535dc154f90ae62025-01-19T06:23:52ZengElsevierInternational Journal of Electrical Power & Energy Systems0142-06152025-03-01164110377A dimension-enhanced residual multi-scale attention framework for identifying anomalous waveforms of fault recordersLixin Jia0Lihang Feng1Dong Wang2Jiapeng Jiang3Guannan Wang4Jiantao Shi5College of Electrical Engineering and Control Science, Nanjing Tech University, Nanjing, 211816, ChinaCollege of Electrical Engineering and Control Science, Nanjing Tech University, Nanjing, 211816, China; Corresponding author.School of Instrument Science and Engineering, Southeast University, Nanjing, 210096, ChinaSchool of Instrument Science and Engineering, Southeast University, Nanjing, 210096, ChinaState Grid Jiangxi Electric Power Co., Ltd. Electric Power Science Research Institute, Nanchang, 330006, ChinaCollege of Electrical Engineering and Control Science, Nanjing Tech University, Nanjing, 211816, ChinaThe continuous introduction of technologies such as distributed generation, wind power, and photovoltaic energy poses challenges to identifying abnormal waveforms in power disturbances. Due to the constant increase in abnormal features, existing waveform recognition schemes for power disturbance abnormalities cannot meet the requirements of high accuracy and reliability. In this paper, a Dimension-Enhanced Residual Multi-Scale Attention Framework for identifying power disturbance abnormal waveforms is proposed. This framework first employs the Phase Adaptive Adjustment (PAA) method to address the phase offset problem of original recording data, then uses the Gramian Angle Field method to perform dimensionality expansion on the data processed by PAA, and finally utilizes the Residual Pyramid Squeeze Attention Network (ResPSANet) for identifying power disturbance abnormal waveforms. Experiments demonstrate that the proposed approach improves the performance of power disturbance abnormal waveform recognition by 10% compared to existing schemes.http://www.sciencedirect.com/science/article/pii/S0142061524006008Power disturbance waveform identificationPhase adaptive adjustmentGramian angle fieldMulti-scale feature extractionAttention mechanism |
| spellingShingle | Lixin Jia Lihang Feng Dong Wang Jiapeng Jiang Guannan Wang Jiantao Shi A dimension-enhanced residual multi-scale attention framework for identifying anomalous waveforms of fault recorders International Journal of Electrical Power & Energy Systems Power disturbance waveform identification Phase adaptive adjustment Gramian angle field Multi-scale feature extraction Attention mechanism |
| title | A dimension-enhanced residual multi-scale attention framework for identifying anomalous waveforms of fault recorders |
| title_full | A dimension-enhanced residual multi-scale attention framework for identifying anomalous waveforms of fault recorders |
| title_fullStr | A dimension-enhanced residual multi-scale attention framework for identifying anomalous waveforms of fault recorders |
| title_full_unstemmed | A dimension-enhanced residual multi-scale attention framework for identifying anomalous waveforms of fault recorders |
| title_short | A dimension-enhanced residual multi-scale attention framework for identifying anomalous waveforms of fault recorders |
| title_sort | dimension enhanced residual multi scale attention framework for identifying anomalous waveforms of fault recorders |
| topic | Power disturbance waveform identification Phase adaptive adjustment Gramian angle field Multi-scale feature extraction Attention mechanism |
| url | http://www.sciencedirect.com/science/article/pii/S0142061524006008 |
| work_keys_str_mv | AT lixinjia adimensionenhancedresidualmultiscaleattentionframeworkforidentifyinganomalouswaveformsoffaultrecorders AT lihangfeng adimensionenhancedresidualmultiscaleattentionframeworkforidentifyinganomalouswaveformsoffaultrecorders AT dongwang adimensionenhancedresidualmultiscaleattentionframeworkforidentifyinganomalouswaveformsoffaultrecorders AT jiapengjiang adimensionenhancedresidualmultiscaleattentionframeworkforidentifyinganomalouswaveformsoffaultrecorders AT guannanwang adimensionenhancedresidualmultiscaleattentionframeworkforidentifyinganomalouswaveformsoffaultrecorders AT jiantaoshi adimensionenhancedresidualmultiscaleattentionframeworkforidentifyinganomalouswaveformsoffaultrecorders AT lixinjia dimensionenhancedresidualmultiscaleattentionframeworkforidentifyinganomalouswaveformsoffaultrecorders AT lihangfeng dimensionenhancedresidualmultiscaleattentionframeworkforidentifyinganomalouswaveformsoffaultrecorders AT dongwang dimensionenhancedresidualmultiscaleattentionframeworkforidentifyinganomalouswaveformsoffaultrecorders AT jiapengjiang dimensionenhancedresidualmultiscaleattentionframeworkforidentifyinganomalouswaveformsoffaultrecorders AT guannanwang dimensionenhancedresidualmultiscaleattentionframeworkforidentifyinganomalouswaveformsoffaultrecorders AT jiantaoshi dimensionenhancedresidualmultiscaleattentionframeworkforidentifyinganomalouswaveformsoffaultrecorders |