Copyright © 2025 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{186769,
        author = {Yashraj.E. and A Rokade P. P. and Gorde V. S. and Miss.Jadhav Neha.B and Mr.Thorat Yashraj.E. and Mr.Somvanshi Shubham.D. and Mr.Sable Karan.R.},
        title = {Instant Defect Detection for Automotive Lines},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {2028-2036},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=186769},
        abstract = {Ensuring high product quality in modern automotive manufacturing requires rapid and accurate detection of defects across multiple production stages. Traditional manual inspection methods are time-consuming, inconsistent, and ineffective in meeting real-time production demands.This study presents a machine learning–based approach for real-time defect detection in multistage automotive manufacturing environments. The proposed system integrates computer vision and deep learning models with sensor-based data acquisition to identify, classify, and localize defects at various stages of production. A multi-stage data fusion strategy is employed to enhance accuracy, combining visual and process parameters for robust defect prediction. The implementation leverages edge computing for on-site inference, ensuring minimal latency and seamless integration into existing production lines. Experimental results demonstrate that the proposed approach achieves significant improvements in defect detection accuracy, response time, and process efficiency compared to conventional methods. This framework enables predictive quality control, reduces production downtime, and supports the realization of Industry 4.0–driven smart manufacturing systems},
        keywords = {},
        month = {November},
        }