Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{178382,
        author = {BADDIPALLI SRIVARDHAN and Dr.M.MAHESH and BYRI AKSHAY and DHANNADA AJAY},
        title = {AUTOMATIC FAULT DETECTION OF RAILWAY TRACKS USING DEEP LEARNING},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {4542-4545},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=178382},
        abstract = {Railway transport plays a crucial role in public transportation due to its affordability, speed, and frequency. However, the safety and reliability of railway systems are frequently compromised by undetected cracks and faults in tracks and fasteners, which are often missed due to the limitations of manual inspection methods. Existing automated systems, though promising, often fall short in real-world performance due to reliance on pre-trained models that lack domain-specific accuracy. This paper proposes an advanced deep learning-based fault detection system that combines the strengths of ResNet and EfficientNet architectures to enhance defect identification. ResNet’s residual learning overcomes vanishing gradient issues, allowing the system to learn intricate fault patterns from deeper networks.},
        keywords = {Railway fault detection, Deep learning, Res-Net, Efficient Net, Track crack detection, Fastener defect identification, Image analysis, Automated inspection, public transport safety},
        month = {May},
        }