Implementasi Deep Learning Berbasis Citra Digital untuk Deteksi Kerusakan Komponen Elektronik
Abstract
Kerusakan komponen elektronik seperti retak, terbakar, dan korosi dapat menurunkan kinerja perangkat serta meningkatkan risiko kegagalan sistem. Proses identifikasi kerusakan secara manual masih bergantung pada ketelitian teknisi sehingga membutuhkan waktu lama dan rentan terhadap subjektivitas. Penelitian ini bertujuan mengimplementasikan model deep learning berbasis citra digital untuk mendeteksi kondisi komponen elektronik secara otomatis. Metode penelitian menggunakan pendekatan eksperimen komputasional melalui tahapan pengumpulan citra, anotasi kelas, pra-pemrosesan, augmentasi data, pelatihan model, evaluasi, dan implementasi prototipe. Dataset yang digunakan terdiri atas 1.200 citra komponen elektronik dengan empat kelas, yaitu normal, terbakar, retak, dan korosi. Model MobileNetV2 berbasis transfer learning digunakan sebagai arsitektur utama dengan ukuran input 224x224 piksel. Hasil pengujian menunjukkan model memperoleh akurasi 95,56%, precision 95,71%, recall 95,56%, dan F1-score 95,58%. Pengujian blackbox pada prototipe menunjukkan seluruh fungsi utama berjalan valid. Hasil ini menunjukkan bahwa deep learning berbasis citra digital dapat digunakan sebagai solusi awal untuk membantu deteksi kerusakan komponen elektronik secara cepat, konsisten, dan objektif
Downloads
References
Bai, D., Li, G., Jiang, D., Yun, J., Tao, B., Jiang, G., Sun, Y., & Ju, Z. (2024). Surface defect detection methods for industrial products with imbalanced samples: A review of progress in the 2020s. Engineering Applications of Artificial Intelligence, 130, 107697. https://doi.org/10.1016/j.engappai.2023.107697
Bai, L., & Xu, W. H. (2025). Improved printed circuit board defect detection scheme. Scientific Reports, 15, 2389. https://doi.org/10.1038/s41598-025-85245-2
Bhattacharya, A., & Cloutier, S. G. (2022). End-to-end deep learning framework for printed circuit board manufacturing defect classification. Scientific Reports, 12, 12559. https://doi.org/10.1038/s41598-022-16302-3
Chen, X., Wu, Y., He, X., & Wuyi, M. (2024). A comprehensive review of deep learning-based PCB defect detection. IEEE Access, 12, 1-1. https://doi.org/10.1109/ACCESS.2023.3339561
Chen, Y., Ding, Y., Zhao, F., Zhang, E., Wu, Z., & Shao, L. (2021). Surface defect detection methods for industrial products: A review. Applied Sciences, 11(16), 7657. https://doi.org/10.3390/app11167657
Elsharkawy, Z. F. (2025). Enhanced YOLOv11 framework for high precision defect detection in printed circuit boards. Scientific Reports, 15, 42550. https://doi.org/10.1038/s41598-025-27415-w
Hermin, H., & Ismail, I. (2026). Prediksi produktivitas jagung berbasis explainable machine learning dan seleksi fitur adaptif. Jurnal Ilmiah Sistem Informasi dan Teknik Informatika (JISTI), 9(1). https://doi.org/10.57093/jisti.v9i1.398
Hosen, M. S., Shehab, M., & Elbeltagi, E. (2024). Advancing PCB quality control: Harnessing YOLOv8 deep learning for real-time fault detection. Computers, Materials & Continua, 81(1), 345-367. https://doi.org/10.32604/cmc.2024.054439
Kang, H., & Yang, Y. (2023). An enhanced detection method of PCB defect based on D-DenseNet (PCBDD-DDNet). Electronics, 12(23), 4737. https://doi.org/10.3390/electronics12234737
Ling, Q., & Mat Isa, N. A. (2023). Printed circuit board defect detection methods based on image processing, machine learning and deep learning: A survey. IEEE Access, 11, 1-1. https://doi.org/10.1109/ACCESS.2023.3245093
Ma, Y., Yin, J., Huang, F., & Li, Q. (2024). Surface defect inspection of industrial products with object detection deep networks: A systematic review. Artificial Intelligence Review, 57, 333. https://doi.org/10.1007/s10462-024-10956-3
Park, J. H., Kim, Y. S., Seo, H., & Cho, Y. J. (2023). Analysis of training deep learning models for PCB defect detection. Sensors, 23(5), 2766. https://doi.org/10.3390/s23052766
Prunella, M., Scardigno, R., Buongiorno, D., Brunetti, A., & Longo, N. (2023). Deep learning for automatic vision-based recognition of industrial surface defects: A survey. IEEE Access, 11, 43370-43423. https://doi.org/10.1109/ACCESS.2023.3271748
Saberironaghi, A., Ren, J., & El-Gindy, M. (2023). Defect detection methods for industrial products using deep learning techniques: A review. Algorithms, 16(2), 95. https://doi.org/10.3390/a16020095
Wardana, M. A., & Ismail, I. (2026). Model explainable machine learning untuk prediksi kecukupan gizi menu MBG. Jurnal Ilmiah Sistem Informasi dan Teknik Informatika (JISTI), 9(1). https://doi.org/10.57093/jisti.v9i1.410
Xiao, G., Hou, S., & Zhou, H. (2024). PCB defect detection algorithm based on CDI-YOLO. Scientific Reports, 14, 7351. https://doi.org/10.1038/s41598-024-57491-3
Yang, W., Huang, X., Zhang, F., & Li, H. (2023). PCB defect detection based on deep learning algorithm. Processes, 11(3), 775. https://doi.org/10.3390/pr11030775
Zhang, X., Wang, J., Jiang, D., Li, Y., Wang, X., & Zhang, H. (2025). Defects detection in screen-printed circuits based on an enhanced YOLOv8n algorithm. International Journal of Computational Intelligence Systems, 18, 101. https://doi.org/10.1007/s44196-025-00815-6
Sun, Z., Ma, R., & Lei, Q. (2026). Small PCB defect detection based on convolutional block attention mechanism and YOLOv8. Applied Sciences, 16(2), 1078. https://doi.org/10.3390/app16021078
Wang, J., Xie, X., Liu, G., & Wu, L. (2025). A lightweight PCB defect detection algorithm based on improved YOLOv8-PCB. Symmetry, 17(2), 309. https://doi.org/10.3390/sym17020309
JISTI
