A MultiModal Detection Method for UHV Substation Faults Based on Robot Inspection and Deep Learning
Aiming at the problem of multi-modal fault detection of different equipment in ultrahigh voltage (UHV) substations, a method for based on robot inspection and deep learning is proposed. First, the inspection robot is used to collect the image data of different devices in the station and the source d...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | Journal of Robotics |
| Online Access: | http://dx.doi.org/10.1155/2022/1188617 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832553604332912640 |
|---|---|
| author | Rong Meng Zhao-lei Wang Zhi-long Zhao Jian-peng Li Wei-ping Fu |
| author_facet | Rong Meng Zhao-lei Wang Zhi-long Zhao Jian-peng Li Wei-ping Fu |
| author_sort | Rong Meng |
| collection | DOAJ |
| description | Aiming at the problem of multi-modal fault detection of different equipment in ultrahigh voltage (UHV) substations, a method for based on robot inspection and deep learning is proposed. First, the inspection robot is used to collect the image data of different devices in the station and the source data is preprocessed by standard image augmentation and image aliasing augmentation. Then, the HSV color space model based on saliency area detection is used to extract equipment defect areas, which improves the accuracy of defect image classification. Finally, the traditional YOLOv3 network is improved by combining the residual network and the K-means clustering algorithm, and the detailed flow of the corresponding detection method is proposed. The proposed detection method and the other three methods were compared and analyzed under the same conditions through simulation experiments. The results show that the detection accuracy and recall rate of the method proposed in this study are the largest, which are 95.9% and 91.3%, respectively. The average detection accuracy under multiple intersection ratio thresholds is also the highest, and the performance is better than the other three comparison algorithms. |
| format | Article |
| id | doaj-art-5517c22758b74364ac6708510978d073 |
| institution | Kabale University |
| issn | 1687-9619 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Robotics |
| spelling | doaj-art-5517c22758b74364ac6708510978d0732025-02-03T05:53:40ZengWileyJournal of Robotics1687-96192022-01-01202210.1155/2022/1188617A MultiModal Detection Method for UHV Substation Faults Based on Robot Inspection and Deep LearningRong Meng0Zhao-lei Wang1Zhi-long Zhao2Jian-peng Li3Wei-ping Fu4State Grid Hebei Extra High Voltage CompanyState Grid Hebei Extra High Voltage CompanyState Grid Hebei Extra High Voltage CompanyState Grid Hebei Extra High Voltage CompanyState Grid Hebei Extra High Voltage CompanyAiming at the problem of multi-modal fault detection of different equipment in ultrahigh voltage (UHV) substations, a method for based on robot inspection and deep learning is proposed. First, the inspection robot is used to collect the image data of different devices in the station and the source data is preprocessed by standard image augmentation and image aliasing augmentation. Then, the HSV color space model based on saliency area detection is used to extract equipment defect areas, which improves the accuracy of defect image classification. Finally, the traditional YOLOv3 network is improved by combining the residual network and the K-means clustering algorithm, and the detailed flow of the corresponding detection method is proposed. The proposed detection method and the other three methods were compared and analyzed under the same conditions through simulation experiments. The results show that the detection accuracy and recall rate of the method proposed in this study are the largest, which are 95.9% and 91.3%, respectively. The average detection accuracy under multiple intersection ratio thresholds is also the highest, and the performance is better than the other three comparison algorithms.http://dx.doi.org/10.1155/2022/1188617 |
| spellingShingle | Rong Meng Zhao-lei Wang Zhi-long Zhao Jian-peng Li Wei-ping Fu A MultiModal Detection Method for UHV Substation Faults Based on Robot Inspection and Deep Learning Journal of Robotics |
| title | A MultiModal Detection Method for UHV Substation Faults Based on Robot Inspection and Deep Learning |
| title_full | A MultiModal Detection Method for UHV Substation Faults Based on Robot Inspection and Deep Learning |
| title_fullStr | A MultiModal Detection Method for UHV Substation Faults Based on Robot Inspection and Deep Learning |
| title_full_unstemmed | A MultiModal Detection Method for UHV Substation Faults Based on Robot Inspection and Deep Learning |
| title_short | A MultiModal Detection Method for UHV Substation Faults Based on Robot Inspection and Deep Learning |
| title_sort | multimodal detection method for uhv substation faults based on robot inspection and deep learning |
| url | http://dx.doi.org/10.1155/2022/1188617 |
| work_keys_str_mv | AT rongmeng amultimodaldetectionmethodforuhvsubstationfaultsbasedonrobotinspectionanddeeplearning AT zhaoleiwang amultimodaldetectionmethodforuhvsubstationfaultsbasedonrobotinspectionanddeeplearning AT zhilongzhao amultimodaldetectionmethodforuhvsubstationfaultsbasedonrobotinspectionanddeeplearning AT jianpengli amultimodaldetectionmethodforuhvsubstationfaultsbasedonrobotinspectionanddeeplearning AT weipingfu amultimodaldetectionmethodforuhvsubstationfaultsbasedonrobotinspectionanddeeplearning AT rongmeng multimodaldetectionmethodforuhvsubstationfaultsbasedonrobotinspectionanddeeplearning AT zhaoleiwang multimodaldetectionmethodforuhvsubstationfaultsbasedonrobotinspectionanddeeplearning AT zhilongzhao multimodaldetectionmethodforuhvsubstationfaultsbasedonrobotinspectionanddeeplearning AT jianpengli multimodaldetectionmethodforuhvsubstationfaultsbasedonrobotinspectionanddeeplearning AT weipingfu multimodaldetectionmethodforuhvsubstationfaultsbasedonrobotinspectionanddeeplearning |