Active Hard Sample Learning for Violation Action Recognition in Power Grid Operation
Power grid operation occurs in complex, dynamic environments where the timely identification of operator violations is essential for safety. Traditional methods often rely on manual supervision and rule-based detection, leading to inefficiencies. Existing deep learning approaches, while powerful, re...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/16/1/67 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588330174251008 |
|---|---|
| author | Lingwen Meng Di He Guobang Ban Guanghui Xi Anjun Li Xinshan Zhu |
| author_facet | Lingwen Meng Di He Guobang Ban Guanghui Xi Anjun Li Xinshan Zhu |
| author_sort | Lingwen Meng |
| collection | DOAJ |
| description | Power grid operation occurs in complex, dynamic environments where the timely identification of operator violations is essential for safety. Traditional methods often rely on manual supervision and rule-based detection, leading to inefficiencies. Existing deep learning approaches, while powerful, require fully labeled data and long training times, thereby increasing costs. To address these challenges, we propose an active hard sample learning method specifically for the violation action recognition of operators in power grid operation. We design a hard instance sampling module with multi-strategy fusion based on active learning to improve training efficiency. This module identifies hard samples based on the consistency of models or samples, where we develop uncertainty evaluation and the instance discrimination strategy to assess the contributions of samples effectively. We utilize ResNet50 and ViT architectures with Faster-RCNN for detection and recognition, developed using PyTorch 2.0. The dataset comprises 2000 samples, and 30% and 60% labeled data are employed. Experimental results show significant improvements in model performance and training efficiency, demonstrating the method’s effectiveness in complex power grid environments. Our approach enhances safety monitoring and advances active learning and hard sample techniques in practical applications. |
| format | Article |
| id | doaj-art-25c1ab1f33314c6da4d712908c63494f |
| institution | Kabale University |
| issn | 2078-2489 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj-art-25c1ab1f33314c6da4d712908c63494f2025-01-24T13:35:20ZengMDPI AGInformation2078-24892025-01-011616710.3390/info16010067Active Hard Sample Learning for Violation Action Recognition in Power Grid OperationLingwen Meng0Di He1Guobang Ban2Guanghui Xi3Anjun Li4Xinshan Zhu5Electric Power Research Institute of Guizhou Power Grid Co., Ltd., Guiyang 550002, ChinaSchool of Electrical and Information Engineering, Tianjin University, Tianjin 300072, ChinaElectric Power Research Institute of Guizhou Power Grid Co., Ltd., Guiyang 550002, ChinaElectric Power Research Institute of Guizhou Power Grid Co., Ltd., Guiyang 550002, ChinaElectric Power Research Institute of Guizhou Power Grid Co., Ltd., Guiyang 550002, ChinaSchool of Electrical and Information Engineering, Tianjin University, Tianjin 300072, ChinaPower grid operation occurs in complex, dynamic environments where the timely identification of operator violations is essential for safety. Traditional methods often rely on manual supervision and rule-based detection, leading to inefficiencies. Existing deep learning approaches, while powerful, require fully labeled data and long training times, thereby increasing costs. To address these challenges, we propose an active hard sample learning method specifically for the violation action recognition of operators in power grid operation. We design a hard instance sampling module with multi-strategy fusion based on active learning to improve training efficiency. This module identifies hard samples based on the consistency of models or samples, where we develop uncertainty evaluation and the instance discrimination strategy to assess the contributions of samples effectively. We utilize ResNet50 and ViT architectures with Faster-RCNN for detection and recognition, developed using PyTorch 2.0. The dataset comprises 2000 samples, and 30% and 60% labeled data are employed. Experimental results show significant improvements in model performance and training efficiency, demonstrating the method’s effectiveness in complex power grid environments. Our approach enhances safety monitoring and advances active learning and hard sample techniques in practical applications.https://www.mdpi.com/2078-2489/16/1/67violation action recognitionhard sample learningactive learningsemi-supervised learningpower grid operation |
| spellingShingle | Lingwen Meng Di He Guobang Ban Guanghui Xi Anjun Li Xinshan Zhu Active Hard Sample Learning for Violation Action Recognition in Power Grid Operation Information violation action recognition hard sample learning active learning semi-supervised learning power grid operation |
| title | Active Hard Sample Learning for Violation Action Recognition in Power Grid Operation |
| title_full | Active Hard Sample Learning for Violation Action Recognition in Power Grid Operation |
| title_fullStr | Active Hard Sample Learning for Violation Action Recognition in Power Grid Operation |
| title_full_unstemmed | Active Hard Sample Learning for Violation Action Recognition in Power Grid Operation |
| title_short | Active Hard Sample Learning for Violation Action Recognition in Power Grid Operation |
| title_sort | active hard sample learning for violation action recognition in power grid operation |
| topic | violation action recognition hard sample learning active learning semi-supervised learning power grid operation |
| url | https://www.mdpi.com/2078-2489/16/1/67 |
| work_keys_str_mv | AT lingwenmeng activehardsamplelearningforviolationactionrecognitioninpowergridoperation AT dihe activehardsamplelearningforviolationactionrecognitioninpowergridoperation AT guobangban activehardsamplelearningforviolationactionrecognitioninpowergridoperation AT guanghuixi activehardsamplelearningforviolationactionrecognitioninpowergridoperation AT anjunli activehardsamplelearningforviolationactionrecognitioninpowergridoperation AT xinshanzhu activehardsamplelearningforviolationactionrecognitioninpowergridoperation |