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{175719,
        author = {Vipin Chaurasia and Ms. Pragya and Vishnu Rajput and Tanya Rai and Vineet Kumar},
        title = {Railway Track Fault Detection Using Deep Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {3734-3742},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=175719},
        abstract = {In Just 10 years, the Railway network expanded across the country. Railways are the principal mode of transportation that requires regular inspection of the tracks for damages and faults. The traditional way of railway track inspection using railway carts is time-consuming and subject to human mistake. Any track damage may cause to railway accidents, which will lead to human and financial loss. Hence, there is a requirement for self-railway track fault detection to ensure safe and reliable train operation. In this paper present a solution to overcome the manual inspection system and its drawback by automating the train track fault detection based on Deep Learning. The tracks were of several types Normal tracks, Wheel burnt, and Superelevation and their natural prevalence. This paper developed an CNN algorithm for visual fault recognition and proposed a method based on signal processing theories to study the sample data. Based on the improved CNNs algorithm, a mean accuracy score of 94% based on the data available (through the analysis of experimental results). Note, that while this accuracy was significantly superior to that of existing approaches, the performance remains to be validated in real-world settings},
        keywords = {Deep Learning, Convolutional Neural Network},
        month = {April},
        }