Research on key technology of transmission and OPGW line hidden danger prediction based on neural network
This paper focuses on the high-quality detection of hidden safety hazards in transmission and OPGW lines, and adopts neural network technology as the research basis. A Faster-R-CNN network structure model is constructed to realize end-to-end target detection by combining RPN and Fast-R-CNN network s...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2024-01-01
|
| Series: | Applied Mathematics and Nonlinear Sciences |
| Subjects: | |
| Online Access: | https://doi.org/10.2478/amns-2024-0459 |
| _version_ | 1797279119808921600 |
|---|---|
| author | Wang Xin Liang Gang Li Qing Cui Limin Hu Changyue Wang Xiaozhen |
| author_facet | Wang Xin Liang Gang Li Qing Cui Limin Hu Changyue Wang Xiaozhen |
| author_sort | Wang Xin |
| collection | DOAJ |
| description | This paper focuses on the high-quality detection of hidden safety hazards in transmission and OPGW lines, and adopts neural network technology as the research basis. A Faster-R-CNN network structure model is constructed to realize end-to-end target detection by combining RPN and Fast-R-CNN network structure. To further improve the detection accuracy, the BAM algorithm is introduced to enhance the Faster-R-CNN, to realize the accurate detection of hidden dangers in transmission and OPGW lines. This paper also compares the performance of the traditional and improved algorithms, and explores the practical application effect of the constructed model in depth. The experimental results show that the enhanced Faster-R-CNN algorithm significantly improves the correctness of observation in the sky and land regions, with an average accuracy mean value of about 26%, especially when observing field villages, factories, playgrounds, urban areas and swimming pools. Therefore, the improved algorithm proposed in this study effectively enhances the detection capability and accuracy of hidden safety hazards in transmission and OPGW lines. |
| first_indexed | 2024-03-07T16:20:43Z |
| format | Article |
| id | doaj.art-55bcaba88ebb452eacf264ea5ba9e43c |
| institution | Directory Open Access Journal |
| issn | 2444-8656 |
| language | English |
| last_indexed | 2024-03-07T16:20:43Z |
| publishDate | 2024-01-01 |
| publisher | Sciendo |
| record_format | Article |
| series | Applied Mathematics and Nonlinear Sciences |
| spelling | doaj.art-55bcaba88ebb452eacf264ea5ba9e43c2024-03-04T07:30:41ZengSciendoApplied Mathematics and Nonlinear Sciences2444-86562024-01-019110.2478/amns-2024-0459Research on key technology of transmission and OPGW line hidden danger prediction based on neural networkWang Xin0Liang Gang1Li Qing2Cui Limin3Hu Changyue4Wang Xiaozhen51State Grid Xinjiang Electric Power Co., Ltd. Information and Communication Company, Urumqi, Xinjiang, 830000, China.1State Grid Xinjiang Electric Power Co., Ltd. Information and Communication Company, Urumqi, Xinjiang, 830000, China.1State Grid Xinjiang Electric Power Co., Ltd. Information and Communication Company, Urumqi, Xinjiang, 830000, China.1State Grid Xinjiang Electric Power Co., Ltd. Information and Communication Company, Urumqi, Xinjiang, 830000, China.1State Grid Xinjiang Electric Power Co., Ltd. Information and Communication Company, Urumqi, Xinjiang, 830000, China.1State Grid Xinjiang Electric Power Co., Ltd. Information and Communication Company, Urumqi, Xinjiang, 830000, China.This paper focuses on the high-quality detection of hidden safety hazards in transmission and OPGW lines, and adopts neural network technology as the research basis. A Faster-R-CNN network structure model is constructed to realize end-to-end target detection by combining RPN and Fast-R-CNN network structure. To further improve the detection accuracy, the BAM algorithm is introduced to enhance the Faster-R-CNN, to realize the accurate detection of hidden dangers in transmission and OPGW lines. This paper also compares the performance of the traditional and improved algorithms, and explores the practical application effect of the constructed model in depth. The experimental results show that the enhanced Faster-R-CNN algorithm significantly improves the correctness of observation in the sky and land regions, with an average accuracy mean value of about 26%, especially when observing field villages, factories, playgrounds, urban areas and swimming pools. Therefore, the improved algorithm proposed in this study effectively enhances the detection capability and accuracy of hidden safety hazards in transmission and OPGW lines.https://doi.org/10.2478/amns-2024-0459transmission and opgw linesfaster-r-cnn modelbam algorithmneural networkhidden danger prediction91f10 |
| spellingShingle | Wang Xin Liang Gang Li Qing Cui Limin Hu Changyue Wang Xiaozhen Research on key technology of transmission and OPGW line hidden danger prediction based on neural network Applied Mathematics and Nonlinear Sciences transmission and opgw lines faster-r-cnn model bam algorithm neural network hidden danger prediction 91f10 |
| title | Research on key technology of transmission and OPGW line hidden danger prediction based on neural network |
| title_full | Research on key technology of transmission and OPGW line hidden danger prediction based on neural network |
| title_fullStr | Research on key technology of transmission and OPGW line hidden danger prediction based on neural network |
| title_full_unstemmed | Research on key technology of transmission and OPGW line hidden danger prediction based on neural network |
| title_short | Research on key technology of transmission and OPGW line hidden danger prediction based on neural network |
| title_sort | research on key technology of transmission and opgw line hidden danger prediction based on neural network |
| topic | transmission and opgw lines faster-r-cnn model bam algorithm neural network hidden danger prediction 91f10 |
| url | https://doi.org/10.2478/amns-2024-0459 |
| work_keys_str_mv | AT wangxin researchonkeytechnologyoftransmissionandopgwlinehiddendangerpredictionbasedonneuralnetwork AT lianggang researchonkeytechnologyoftransmissionandopgwlinehiddendangerpredictionbasedonneuralnetwork AT liqing researchonkeytechnologyoftransmissionandopgwlinehiddendangerpredictionbasedonneuralnetwork AT cuilimin researchonkeytechnologyoftransmissionandopgwlinehiddendangerpredictionbasedonneuralnetwork AT huchangyue researchonkeytechnologyoftransmissionandopgwlinehiddendangerpredictionbasedonneuralnetwork AT wangxiaozhen researchonkeytechnologyoftransmissionandopgwlinehiddendangerpredictionbasedonneuralnetwork |