AI-POWERED INTELLIGENT SYSTEM MODEL FOR DEFECT DETECTION IN THE MANUFACTURING PROCESS OF ELECTRONIC COMPONENTS
Keywords:
Deep Learning, Convolutional Neural Networks (CNN), Deteksi Cacat, Manufaktur Elektronik, Mekanisme Atensi, Real-timeAbstract
The rapid advancement of the electronics manufacturing industry demands extremely high precision to achieve zero-defect production standards. However, conventional manual inspection processes remain constrained by human fatigue, subjectivity, and limited inspection speed. To address these limitations, this study proposes an AI-powered intelligent inspection system based on Deep Learning for real-time defect classification in electronic component manufacturing. The proposed approach integrates a Convolutional Neural Network (CNN) architecture with an attention mechanism to enhance feature representation by focusing on defect-prone regions, such as soldering anomalies, missing components, and surface cracks. The research methodology encompasses a complete processing pipeline, starting from the utilization of a publicly available high-resolution PCB defect image dataset, followed by systematic data augmentation to mitigate class imbalance, and the application of a lightweight CNN-based feature extraction framework to support efficient inference. Experimental results demonstrate that the proposed model achieves a classification accuracy of 98.5%, outperforming conventional machine vision–based inspection approaches with a significantly lower false discovery rate. Furthermore, robustness evaluations indicate that the system maintains stable performance under varying lighting conditions and simulated production speeds. These findings confirm the effectiveness and scalability of the proposed intelligent inspection system as a practical solution for automated quality assurance in smart manufacturing environments.
Downloads
References
Adibhatla, V. A., Chih, H.-C., Hsu, C.-C., Cheng, J., & Abbod, M. F. (2020). Defect detection in printed circuit boards using deep learning. Electronics, 9(11), 1845. https://doi.org/10.3390/electronics9111845
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). ImageNet: A large-scale hierarchical image database. Dalam 2009 IEEE Conference on Computer Vision and Pattern Recognition (hlm. 248–255). IEEE. https://doi.org/10.1109/CVPR.2009.5206848
Ferguson, M., Ak, R., Lee, Y.-T. T., & Law, K. H. (2018). Automatic localization of casting defects with convolutional neural networks. Dalam 2017 IEEE International Conference on Big Data (Big Data) (hlm. 1726–1735). IEEE. https://doi.org/10.1109/BigData.2017.8258111
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Dalam Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (hlm. 770–778). https://doi.org/10.1109/CVPR.2016.90
Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
Kuo, C.-F. J., Lin, C.-H., & Lee, M.-H. (2022). Defect detection and classification for electronic components using deep learning with an attention mechanism. The International Journal of Advanced Manufacturing Technology, 121(3-4), 2207–2220. https://doi.org/10.1007/s00170-022-09476-7
Li, D., Wang, R., Xie, C., Liu, L., Zhang, J., Li, R., Wang, F., Zhou, M., & Liu, W. (2020). A recognition method for rice plant diseases and pests video detection based on deep convolutional neural network. Sensors, 20(3), 578. https://doi.org/10.3390/s20030578
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014). Microsoft COCO: Common objects in context. Dalam Computer Vision – ECCV 2014 (hlm. 740–755). Springer. https://doi.org/10.1007/978-3-319-10602-1_48
Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of Big Data, 6(1), 60. https://doi.org/10.1186/s40537-019-0197-0
Wang, J., Ma, Y., Zhang, L., Gao, R. X., & Wu, D. (2018). Deep learning for smart manufacturing: Methods and applications. Journal of Manufacturing Systems, 48, 144–156. https://doi.org/10.1016/j.jmsy.2018.01.003
Woo, S., Park, J., Lee, J.-Y., & Kweon, I. S. (2018). CBAM: Convolutional block attention module. Dalam Proceedings of the European Conference on Computer Vision (ECCV) (hlm. 3–19). Springer. https://doi.org/10.1007/978-3-030-01234-2_1
