A detector based on a multiscale fusion pyramid focus network for catenary support components
As a crucial component of a high-speed rail traction power supply system, the catenary system is responsible for transmitting electrical energy to electric multiple units (EMUs). In practice, continuous impacts from pantograph-net interactions and external environmental factors can lead to defects i...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Science Press
2025-02-01
|
| Series: | 工程科学学报 |
| Subjects: | |
| Online Access: | http://cje.ustb.edu.cn/article/doi/10.13374/j.issn2095-9389.2024.05.09.001 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841561836138266624 |
|---|---|
| author | Xinyu ZHU Haorui CUI Yang SONG |
| author_facet | Xinyu ZHU Haorui CUI Yang SONG |
| author_sort | Xinyu ZHU |
| collection | DOAJ |
| description | As a crucial component of a high-speed rail traction power supply system, the catenary system is responsible for transmitting electrical energy to electric multiple units (EMUs). In practice, continuous impacts from pantograph-net interactions and external environmental factors can lead to defects in the catenary’s supporting parts, such as looseness, detachment, fracture, and cracking. These issues compromise the reliability of the catenary structure and pose risks to its stable operation. Therefore, timely and accurate positioning of the catenary support components (CSCs) is vital for ensuring the safe operation of high-speed rails and improving the catenary maintenance strategies. In 2012, the former Ministry of Railways of China (now the China Railway Corporation) officially promulgated the General Technical Specifications for High-speed Railway Power Supply Safety Detection and Monitoring System. This study marked a shift from traditional manual inspection methods to intelligent non-contact catenary detection and maintenance using computer vision technology. This study addresses challenges in detection systems by focusing on “catenary part positioning” in the whole detection process from the perspective of the functional integrity of the detection system. Detecting CSCs is challenging because of the variety of parts, scale differences, and small size of components. To overcome these challenges, this study proposes a catenary component detection algorithm that utilizes a multiscale fusion pyramid focus network. This approach integrates a balance module and a feature pyramid module to improve the detection performance of small targets. The separable residual pyramid aggregation module (SRPAM) was designed to optimize multi-scale feature extraction, expand the receptive field, and address multi-scale issues in CSC detection. Furthermore, a path aggregation network based on the equilibrium feature pyramid (PA-BFPN) was designed to improve cross-layer feature fusion efficiency and small object detection performance. Finally, the effectiveness of the proposed method is demonstrated through comparative experiments, visual analysis of the results, multi-scale feature fusion module experiments, feature pyramid network experiments, and ablation studies. The results demonstrate that the proposed multiscale feature pyramid FCOS (MFP-FCOS) algorithm offers excellent overall performance compared to many classical algorithms. Visualization experiments confirm its effectiveness in detecting targets across different scales and effectively solving small-scale and multi-scale sample detection challenges. The proposed SPRAM effectively mitigates information loss and improves feature extraction performance, whereas the proposed PA-BFPN obtains more comprehensive feature information. In summary, the proposed MFP-FCOS achieved a detection accuracy (mAP) of 48.6% on the CSC dataset with 30 floating point operations per second (FLOPs), indicating a balanced trade-off between detection accuracy and detection speed. |
| format | Article |
| id | doaj-art-1735dbc1731848b3ad7e6c1631b24693 |
| institution | Kabale University |
| issn | 2095-9389 |
| language | zho |
| publishDate | 2025-02-01 |
| publisher | Science Press |
| record_format | Article |
| series | 工程科学学报 |
| spelling | doaj-art-1735dbc1731848b3ad7e6c1631b246932025-01-03T01:21:00ZzhoScience Press工程科学学报2095-93892025-02-0147231532710.13374/j.issn2095-9389.2024.05.09.001240509-0001A detector based on a multiscale fusion pyramid focus network for catenary support componentsXinyu ZHU0Haorui CUI1Yang SONG2Institute of Electronic and Electrical Engineering, Civil Aviation Flight University of China, Guanghan 618307, ChinaInstitute of Electronic and Electrical Engineering, Civil Aviation Flight University of China, Guanghan 618307, ChinaSouthwest Jiaotong University, SWJTU-Leeds Joint School, Chengdu 611756, ChinaAs a crucial component of a high-speed rail traction power supply system, the catenary system is responsible for transmitting electrical energy to electric multiple units (EMUs). In practice, continuous impacts from pantograph-net interactions and external environmental factors can lead to defects in the catenary’s supporting parts, such as looseness, detachment, fracture, and cracking. These issues compromise the reliability of the catenary structure and pose risks to its stable operation. Therefore, timely and accurate positioning of the catenary support components (CSCs) is vital for ensuring the safe operation of high-speed rails and improving the catenary maintenance strategies. In 2012, the former Ministry of Railways of China (now the China Railway Corporation) officially promulgated the General Technical Specifications for High-speed Railway Power Supply Safety Detection and Monitoring System. This study marked a shift from traditional manual inspection methods to intelligent non-contact catenary detection and maintenance using computer vision technology. This study addresses challenges in detection systems by focusing on “catenary part positioning” in the whole detection process from the perspective of the functional integrity of the detection system. Detecting CSCs is challenging because of the variety of parts, scale differences, and small size of components. To overcome these challenges, this study proposes a catenary component detection algorithm that utilizes a multiscale fusion pyramid focus network. This approach integrates a balance module and a feature pyramid module to improve the detection performance of small targets. The separable residual pyramid aggregation module (SRPAM) was designed to optimize multi-scale feature extraction, expand the receptive field, and address multi-scale issues in CSC detection. Furthermore, a path aggregation network based on the equilibrium feature pyramid (PA-BFPN) was designed to improve cross-layer feature fusion efficiency and small object detection performance. Finally, the effectiveness of the proposed method is demonstrated through comparative experiments, visual analysis of the results, multi-scale feature fusion module experiments, feature pyramid network experiments, and ablation studies. The results demonstrate that the proposed multiscale feature pyramid FCOS (MFP-FCOS) algorithm offers excellent overall performance compared to many classical algorithms. Visualization experiments confirm its effectiveness in detecting targets across different scales and effectively solving small-scale and multi-scale sample detection challenges. The proposed SPRAM effectively mitigates information loss and improves feature extraction performance, whereas the proposed PA-BFPN obtains more comprehensive feature information. In summary, the proposed MFP-FCOS achieved a detection accuracy (mAP) of 48.6% on the CSC dataset with 30 floating point operations per second (FLOPs), indicating a balanced trade-off between detection accuracy and detection speed.http://cje.ustb.edu.cn/article/doi/10.13374/j.issn2095-9389.2024.05.09.001deep learningobject detectioncatenary support components (cscs)path aggregation feature pyramids (pa-fpn)pyramid of hollow space convolutional pooling(aspp) |
| spellingShingle | Xinyu ZHU Haorui CUI Yang SONG A detector based on a multiscale fusion pyramid focus network for catenary support components 工程科学学报 deep learning object detection catenary support components (cscs) path aggregation feature pyramids (pa-fpn) pyramid of hollow space convolutional pooling(aspp) |
| title | A detector based on a multiscale fusion pyramid focus network for catenary support components |
| title_full | A detector based on a multiscale fusion pyramid focus network for catenary support components |
| title_fullStr | A detector based on a multiscale fusion pyramid focus network for catenary support components |
| title_full_unstemmed | A detector based on a multiscale fusion pyramid focus network for catenary support components |
| title_short | A detector based on a multiscale fusion pyramid focus network for catenary support components |
| title_sort | detector based on a multiscale fusion pyramid focus network for catenary support components |
| topic | deep learning object detection catenary support components (cscs) path aggregation feature pyramids (pa-fpn) pyramid of hollow space convolutional pooling(aspp) |
| url | http://cje.ustb.edu.cn/article/doi/10.13374/j.issn2095-9389.2024.05.09.001 |
| work_keys_str_mv | AT xinyuzhu adetectorbasedonamultiscalefusionpyramidfocusnetworkforcatenarysupportcomponents AT haoruicui adetectorbasedonamultiscalefusionpyramidfocusnetworkforcatenarysupportcomponents AT yangsong adetectorbasedonamultiscalefusionpyramidfocusnetworkforcatenarysupportcomponents AT xinyuzhu detectorbasedonamultiscalefusionpyramidfocusnetworkforcatenarysupportcomponents AT haoruicui detectorbasedonamultiscalefusionpyramidfocusnetworkforcatenarysupportcomponents AT yangsong detectorbasedonamultiscalefusionpyramidfocusnetworkforcatenarysupportcomponents |