In this study on the use of ResNet50V2 deep learning architecture for automatic detection of railway track defects from images. It will bring about new approaches to meet the urgent need for rapid and accurate fault systems which guarantee the safety and reliability of railway operation. Using the recent developments in deep learning, particularly the ResNet50V2 model, this work presents a method to distinguish between two kinds of railway track faulty images. This approach uses a dataset of 384 images, with 30 iterations in training and batch size of 16. The default rates for learning are used in this analysis. Through careful testing, the paper demonstrates the ability of the ResNet50V2 model to distinguish railway track faults accurately, It achieves an accuracy rate of 86%. The study discovers the possibility of deep learning models such as ResNet50V2 enhancing efficiency and reliability for railway track fault detection systems. The successful realization of this approach will have significant impacts on railway maintenance processes. It will allow problems to be identified early and allocated with in time to prevent accidents and delays, a long-term effect which grows worse as time goes on. In addition, the study shows the availability of advanced machine learning techniques pose for tackling crucial problems in railway infrastructure management. This will cover the way towards transportation networks that are safer and more robust.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Automated Railway Track Fault Detection using ResNet50V2 Deep Learning Architecture


    Contributors:


    Publication date :

    2024-07-26


    Size :

    1347393 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Railway Track Fasteners Fault Detection using Deep Learning

    Lin, Ya-Wen / Hsieh, Chen-Chiung / Huang, Wei-Hsin et al. | IEEE | 2019


    Automated Railway Track Fault Detection Using Solar Powered Electric Vehicle

    Bhagyalekshmi, S. / Jayasudha / Maya, A. et al. | IEEE | 2019


    TrackNet - A Deep Learning Based Fault Detection for Railway Track Inspection

    James, Ashish / Jie, Wang / Xulei, Yang et al. | IEEE | 2018


    ARTFDS–Advanced Railway Track Fault Detection System Using Machine Learning

    Kondaka, Lakshmisudha / Rangnekar, Adwait / Shetty, Akshay et al. | Springer Verlag | 2022


    Deep Multitask Learning for Railway Track Inspection

    Gibert, Xavier | Online Contents | 2017