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{196324,
        author = {Shripad V. Kale and Mayank A. Agrawal and Sohan R. Pachghare and Prasad S. Laware and Nitin S. Khachane and Sunil R. Gupta},
        title = {Comparative Study of Deep Learning Algorithms for Real-Time Manufacturing Fault Detection},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {2901-2907},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=196324},
        abstract = {Quality control is a necessary part of the manufacturing process. Manual quality control is being applied in many small and medium enterprises (SMEs). Human observers are known to miss 20-30% of the defects due to fatigue and inconsistency. There are Visual Inspection (AVI) systems, which are automated and require expensive industrial equipment and special conditions of lighting. This renders them inapplicable to low budgets. The authors talk about the most recent algorithms that can be used to detect surface defects in this paper with the help of Deep Learning (DL) methods. Two-Stage detectors, e.g., Faster R-CNN, and Single-Stage detectors, e.g., YOLO, will be compared to each other. It is hoped to discover which solution is more feasible and effective when it comes to real-time low-budget apps with the use of standard webcams. The findings indicate that the Two-Stage detectors are not a lot more accurate than the Single-Stage detectors, but the Single-Stage detectors possess a sufficient frame rate (FPS).},
        keywords = {Defect Detection, Deep Learning, YOLO, Faster R-CNN, Quality Control, Computer Vision.},
        month = {April},
        }