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{179160,
        author = {PAVITHRA N and TILAK KUMAR SAI NITHI and B BALA ABIRAMI},
        title = {AI DRIVEN STEEL AND WELD DEFECT DETECTION USING DEEP LEARNING},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {5713-5717},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=179160},
        abstract = {Detecting defects in steel materials is essential for ensuring product quality and reliability across various industrial applications. Conventional defect detection methods are often labor-intensive, time-consuming, and susceptible to human error. However, advancements in deep learning have paved the way for automated solutions that significantly enhance accuracy and efficiency. This study presents a Steel Defect Detection system utilizing a custom designed deep neural network inspired by the ResNet architecture. The model integrates novel attention layers, which have not been previously incorporated into similar architectures, to improve predictive performance. Additionally, data augmentation techniques are employed to enhance the model’s ability to generalize and accurately detect defects in complex and subtle patterns. The proposed multiclass semantic segmentation model achieves an accuracy exceeding 91%, making it a viable solution for automating the defect detection process. This automation substantially reduces inspection costs and time, optimizing industrial workflows.},
        keywords = {Deep learning, Residual Network, Attention layers, augmentation, Steel Defect},
        month = {May},
        }