Rail defect detection is crucial to rail operations safety. Addressing the problem of high false alarm rates and missed detection rates in rail defect detection, this paper proposes a deep learning method using B-scan image recognition of rail defects with an improved YOLO (you only look once) V3 algorithm. Specifically, the developed model can automatically position a box in B-scan images and recognize EFBWs (electric flash butt welds), normal bolt holes, BHBs (bolt hole breaks), and SSCs (shells, spalling, or corrugation). First, the network structure of the YOLO V3 model is modified to enlarge the receptive field of the model, thus improving the detection accuracy of the model for small-scale objects. Second, B-scan image data are analyzed and standardized. Third, the initial training parameters of the improved YOLO V3 model are adjusted. Finally, the experiments are performed on 453 B-scan images as the test data set. Results show that the B-scan image recognition model based on the improved YOLO V3 algorithm reached high performance in its precision. Additionally, the detection accuracy and efficiency are improved compared with the original model and the final mean average precision can reach 87.41%.


    Zugriff

    Download

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Deep Learning for the Detection and Recognition of Rail Defects in Ultrasound B-Scan Images


    Weitere Titelangaben:

    Transportation Research Record


    Beteiligte:
    Chen, Zhengxing (Autor:in) / Wang, Qihang (Autor:in) / Yang, Kanghua (Autor:in) / Yu, Tianle (Autor:in) / Yao, Jidong (Autor:in) / Liu, Yong (Autor:in) / Wang, Ping (Autor:in) / He, Qing (Autor:in)


    Erscheinungsdatum :

    2021-07-07




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Detection of Rail Defects with Deep Learning Controlled Autonomous UAV

    Aydin, Ilhan / Sevi, Mehmet / Sahbaz, Kadir et al. | IEEE | 2021


    Automatic Detection of Rail Defects from Images

    Hovad, Emil / Hansen, Helena / da Silva Rodrigues, André Filipe et al. | Springer Verlag | 2021


    Rail Defect Detection Using Ultrasonic A-Scan Data and Deep Autoencoder

    Wu, Yuning / Zhu, Xuan | Transportation Research Record | 2023



    JRC2022-79554 Deep Autoencoder for Ultrasound-Based Rail Flaw Detection

    Wu, Yuning / Zhu, Xuan / Baillargeon, Jay | TIBKAT | 2022