Rail Internal Defect Detection Method Based on Enhanced Network Structure and Module Design Using Ultrasonic Images
Abstract Improving the detection accuracy of rail internal defects and the generalization ability of detection models are not only the main problems in the field of defect detection but also the key to ensuring the safe operation of high-speed trains. For this reason, a rail internal defect detectio...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-12-01
|
| Series: | Chinese Journal of Mechanical Engineering |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s10033-023-00980-9 |
| _version_ | 1797388508755656704 |
|---|---|
| author | Fupei Wu Xiaoyang Xie Weilin Ye |
| author_facet | Fupei Wu Xiaoyang Xie Weilin Ye |
| author_sort | Fupei Wu |
| collection | DOAJ |
| description | Abstract Improving the detection accuracy of rail internal defects and the generalization ability of detection models are not only the main problems in the field of defect detection but also the key to ensuring the safe operation of high-speed trains. For this reason, a rail internal defect detection method based on an enhanced network structure and module design using ultrasonic images is proposed in this paper. First, a data augmentation method was used to extend the existing image dataset to obtain appropriate image samples. Second, an enhanced network structure was designed to make full use of the high-level and low-level feature information in the image, which improved the accuracy of defect detection. Subsequently, to optimize the detection performance of the proposed model, the Mish activation function was used to design the block module of the feature extraction network. Finally, the proposed rail defect detection model was trained. The experimental results showed that the precision rate and $${F}_{1}$$ F 1 score of the proposed method were as high as 98%, while the model’s recall rate reached 99%. Specifically, good detection results were achieved for different types of defects, which provides a reference for the engineering application of internal defect detection. Experimental results verified the effectiveness of the proposed method. |
| first_indexed | 2024-03-08T22:41:51Z |
| format | Article |
| id | doaj.art-e6669395aeaf4ca9aed1f8840a38e9f8 |
| institution | Directory Open Access Journal |
| issn | 2192-8258 |
| language | English |
| last_indexed | 2024-03-08T22:41:51Z |
| publishDate | 2023-12-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Chinese Journal of Mechanical Engineering |
| spelling | doaj.art-e6669395aeaf4ca9aed1f8840a38e9f82023-12-17T12:09:05ZengSpringerOpenChinese Journal of Mechanical Engineering2192-82582023-12-0136111210.1186/s10033-023-00980-9Rail Internal Defect Detection Method Based on Enhanced Network Structure and Module Design Using Ultrasonic ImagesFupei Wu0Xiaoyang Xie1Weilin Ye2Department of Mechanical Engineering, College of Engineering, Shantou UniversityDepartment of Mechanical Engineering, College of Engineering, Shantou UniversityDepartment of Mechanical Engineering, College of Engineering, Shantou UniversityAbstract Improving the detection accuracy of rail internal defects and the generalization ability of detection models are not only the main problems in the field of defect detection but also the key to ensuring the safe operation of high-speed trains. For this reason, a rail internal defect detection method based on an enhanced network structure and module design using ultrasonic images is proposed in this paper. First, a data augmentation method was used to extend the existing image dataset to obtain appropriate image samples. Second, an enhanced network structure was designed to make full use of the high-level and low-level feature information in the image, which improved the accuracy of defect detection. Subsequently, to optimize the detection performance of the proposed model, the Mish activation function was used to design the block module of the feature extraction network. Finally, the proposed rail defect detection model was trained. The experimental results showed that the precision rate and $${F}_{1}$$ F 1 score of the proposed method were as high as 98%, while the model’s recall rate reached 99%. Specifically, good detection results were achieved for different types of defects, which provides a reference for the engineering application of internal defect detection. Experimental results verified the effectiveness of the proposed method.https://doi.org/10.1186/s10033-023-00980-9Ultrasonic detectionRail defects detectionDeep learningEnhanced network structureModule design |
| spellingShingle | Fupei Wu Xiaoyang Xie Weilin Ye Rail Internal Defect Detection Method Based on Enhanced Network Structure and Module Design Using Ultrasonic Images Chinese Journal of Mechanical Engineering Ultrasonic detection Rail defects detection Deep learning Enhanced network structure Module design |
| title | Rail Internal Defect Detection Method Based on Enhanced Network Structure and Module Design Using Ultrasonic Images |
| title_full | Rail Internal Defect Detection Method Based on Enhanced Network Structure and Module Design Using Ultrasonic Images |
| title_fullStr | Rail Internal Defect Detection Method Based on Enhanced Network Structure and Module Design Using Ultrasonic Images |
| title_full_unstemmed | Rail Internal Defect Detection Method Based on Enhanced Network Structure and Module Design Using Ultrasonic Images |
| title_short | Rail Internal Defect Detection Method Based on Enhanced Network Structure and Module Design Using Ultrasonic Images |
| title_sort | rail internal defect detection method based on enhanced network structure and module design using ultrasonic images |
| topic | Ultrasonic detection Rail defects detection Deep learning Enhanced network structure Module design |
| url | https://doi.org/10.1186/s10033-023-00980-9 |
| work_keys_str_mv | AT fupeiwu railinternaldefectdetectionmethodbasedonenhancednetworkstructureandmoduledesignusingultrasonicimages AT xiaoyangxie railinternaldefectdetectionmethodbasedonenhancednetworkstructureandmoduledesignusingultrasonicimages AT weilinye railinternaldefectdetectionmethodbasedonenhancednetworkstructureandmoduledesignusingultrasonicimages |