AI-Based Vision Inspection System for Automated Defect Detection in Additive Manufacturing Processes Using Deep Learning  and Transfer Learning Approaches

Dani Sasmoko; Krisna Widi Nugraha; Rian Ardianto; Rosyid Ridlo Al-Hakim; Helmi Wibowo; Rinna Rachmatika

doi:10.61132/ijiime.v1i2.394

Authors

Dani Sasmoko Universitas Sains dan Teknologi Komputer
Krisna Widi Nugraha Universitas Harapan Bangsa
Rian Ardianto Universitas Harapan Bangsa
Rosyid Ridlo Al-Hakim Universitas Harapan Bangsa
Helmi Wibowo Politeknik Keselamatan Transportasi Jalan
Rinna Rachmatika Universitas Pamulang

DOI:

https://doi.org/10.61132/ijiime.v1i2.394

Keywords:

Additive Manufacturing, Computer Vision Inspection, Convolutional Neural Network, Defect Detection, Transfer Learning

Abstract

Background: Additive manufacturing (AM) requires reliable and efficient defect detection mechanisms to ensure structural integrity and product quality, yet conventional inspection approaches remain time-consuming and often unsuitable for real-time industrial deployment. Objective: This study aims to develop and experimentally validate an artificial intelligence based vision inspection system capable of accurately detecting surface defects in AM components. Methods: A Convolutional Neural Network (CNN) architecture utilizing pretrained backbones (ResNet and EfficientNet) was implemented with a transfer learning strategy and data augmentation techniques. High-resolution AM surface images representing porosity, cracks, and layer misalignment were used for training and evaluation. Model performance was assessed using Accuracy, Precision, Recall, F1-score, and mean Average Precision (mAP), and comparative benchmarking was conducted against traditional machine learning models such as Support Vector Machine and Random Forest. Results: The proposed CNN-based models significantly outperformed conventional approaches, achieving up to 95.1% Accuracy and 92.8% mAP. The EfficientNet backbone demonstrated superior generalization capability, particularly in balancing Precision and Recall, indicating robust defect detection performance across multiple categories. These findings confirm that AI-driven inspection frameworks provide scalable and reliable quality assurance solutions for advanced manufacturing environments.

References

Alami, A. H., Ghani Olabi, A., Alashkar, A., Alasad, S., Aljaghoub, H., Rezk, H., & Abdelkareem, M. A. (2023). Additive manufacturing in the aerospace and automotive industries: Recent trends and role in achieving sustainable development goals. Ain Shams Engineering Journal, 14(11), 102516. https://doi.org/10.1016/j.asej.2023.102516

Al-Meslemi, Y., Ferreira, K., Mehdi-Souzani, C., Obaton, A.-F., Nouira, H., & Anwer, N. (2023). Quality control for additive manufacturing. In Springer Handbooks (pp. 797-819). Springer. https://doi.org/10.1007/978-3-031-20752-5_47

Ansari, M. A., Crampton, A., & Mubarak, S. M. J. (2024). Enhanced detection of surface deformations in LPBF using deep convolutional neural networks and transfer learning from a porosity model. Scientific Reports, 14(1), 26920. https://doi.org/10.1038/s41598-024-76445-3 PMid:39505970 PMCid:PMC11542091

Balakrishna, K., Tiwari, V., Deshpande, A. V., Patil, S. R., Garg, A. K., & Geetha, B. T. (2024). Computer vision for automated quality inspection in manufacturing. Proceedings of the 3rd International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI 2024). https://doi.org/10.1109/ACCAI61061.2024.10601894

Bellini, C., Berto, F., Di Cocco, V., Iacoviello, F., Mocanu, L. P., & Razavi, N. (2021). Additive manufacturing processes for metals and effects of defects on mechanical strength: A review. Procedia Structural Integrity, 33, 498-508. https://doi.org/10.1016/j.prostr.2021.10.057

Bhandarkar, V. V., & Tandon, P. (2023). A review on recent techniques and current challenges in identifying defects in additively manufactured metal components. Lecture Notes in Mechanical Engineering, 683-693. https://doi.org/10.1007/978-981-19-3716-3_55

Bouaafia, S., Messaoud, S., Maraoui, A., Ammari, A. C., Khriji, L., & MacHhout, M. (2021). Deep pre-trained models for computer vision applications: Traffic sign recognition. 18th IEEE International Multi-Conference on Systems, Signals and Devices (SSD 2021), 23-28. https://doi.org/10.1109/SSD52085.2021.9429420

Chheang, V., Weston, B. T., Cerda, R. W., Au, B., Giera, B., Bremer, P.-T., & Miao, H. (2024). A virtual environment for collaborative inspection in additive manufacturing. Conference on Human Factors in Computing Systems Proceedings. https://doi.org/10.1145/3613905.3650730

Chua, Z. Y., Ahn, I. H., & Moon, S. K. (2017). Process monitoring and inspection systems in metal additive manufacturing: Status and applications. International Journal of Precision Engineering and Manufacturing -- Green Technology, 4(2), 235-245. https://doi.org/10.1007/s40684-017-0029-7

de Pastre, M.-A., Quinsat, Y., & Lartigue, C. (2022). Effects of additive manufacturing processes on part defects and properties: A classification review. International Journal on Interactive Design and Manufacturing, 16(4), 1471-1496. https://doi.org/10.1007/s12008-022-00839-8

Feng, Y., Zhao, B., Zheng, H., Gao, Y., Yang, C., & Tan, J. (2019). Real-time detection of shaft surface defects based on integrated transfer learning. Computer Integrated Manufacturing Systems, 25(12), 3199-3208. https://doi.org/10.13196/j.cims.2019.12.021

Hung, J. C., & Chang, J.-W. (2021). Multi-level transfer learning for improving the performance of deep neural networks. Applied Soft Computing, 109, 107491. https://doi.org/10.1016/j.asoc.2021.107491

Jemghili, R., Ait Taleb, A., & Mansouri, K. (2020). Additive manufacturing progress as a new industrial revolution. 2020 IEEE 2nd International Conference on Electronics, Control, Optimization and Computer Science (ICECOCS). https://doi.org/10.1109/ICECOCS50124.2020.9314623

Khosravani, M. R., & Reinicke, T. (2020). On the use of X-ray computed tomography in assessment of 3D-printed components. Journal of Nondestructive Evaluation, 39(4), 75. https://doi.org/10.1007/s10921-020-00721-1

Koester, L. W., Taheri, H., Bigelow, T. A., Collins, P. C., & Bond, L. J. (2018). Nondestructive testing for metal parts fabricated using powder-based additive manufacturing. Materials Evaluation, 76(4), 514-524.

Kovalskyi, S., & Koval, V. (2024). Comparison of image processing techniques for defect detection. CEUR Workshop Proceedings, 3716, 158-167.

Kumar, A., & Goel, S. (2024). Introduction to 3D printing. IOP Publishing. https://doi.org/10.1088/978-0-7503-5351-9ch1

Lee, K.-J., Jeon, M.-S., & Lee, J.-R. (2023). Evaluation of manufacturing defects in 3D printed carbon fiber reinforced cylindrical composite structure based on laser ultrasonic testing. NDT and E International, 135, 102802. https://doi.org/10.1016/j.ndteint.2023.102802

Li, Z., Zou, X., Bao, F., Gu, F., & Ball, A. D. (2023). A review of acoustic emission monitoring on additive manufacturing. Mechanisms and Machine Science, 117, 867-878. https://doi.org/10.1007/978-3-030-99075-6_70

Liu, Q., & Lu, B. (2024). Review on quality control and relevant hybrid technology in additive manufacturing of metallic materials. Materials Reports, 38(9), 22100064. https://doi.org/10.11896/cldb.22100064

Marks, M., Chigurupati, P. C., & Taheri, H. (2024). Digital twin model for property assessment of metal additive manufacturing. ASME International Mechanical Engineering Congress and Exposition Proceedings (IMECE). https://doi.org/10.1115/IMECE2024-146882

Misiak, P., & Szempruch, D. (2022). Automated quality inspection of high voltage equipment supported by machine learning and computer vision. Lecture Notes in Computer Science, 13652, 211-222. https://doi.org/10.1007/978-3-031-21441-7_15

Mobarak, M. H., Islam, M. A., Hossain, N., Al Mahmud, M. Z., Rayhan, M. T., Nishi, N. J., & Chowdhury, M. A. (2023). Recent advances of additive manufacturing in implant fabrication - A review. Applied Surface Science Advances, 18, 100462. https://doi.org/10.1016/j.apsadv.2023.100462

Mostafaei, A., Zhao, C., He, Y., & others. (2022). Defects and anomalies in powder bed fusion metal additive manufacturing. Current Opinion in Solid State and Materials Science, 26(2), 100974. https://doi.org/10.1016/j.cossms.2021.100974

Nayeem, A. M., & Hossain, M. M. N. (2023). Usage of additive manufacturing in the automotive industry: A review. Bangladesh Journal of Multidisciplinary Scientific Research, 8(1), 9-20. https://doi.org/10.46281/bjmsr.v8i1.2135

Oleff, A., Kuster, B., Stonis, M., & Overmeyer, L. (2021). Process monitoring for material extrusion additive manufacturing: A state-of-the-art review. Progress in Additive Manufacturing, 6(4), 705-730. https://doi.org/10.1007/s40964-021-00192-4

Ozbay Kisasoz, B., & Kisasoz, A. (2023). An overview of the quality characteristics challenges in additive manufacturing. In Handbook of Post-Processing in Additive Manufacturing (pp. 181-192). https://doi.org/10.1201/9781003276111-10

Pazhamannil, R. V., & Govindan, P. (2020). Current state and future scope of additive manufacturing technologies via vat photopolymerization. Materials Today: Proceedings, 43, 130-136. https://doi.org/10.1016/j.matpr.2020.11.225

Perez, M., Carou, D., Rubio, E. M., & Teti, R. (2020). Current advances in additive manufacturing. Procedia CIRP, 88, 439-444. https://doi.org/10.1016/j.procir.2020.05.076

Qi, S., Yang, J., & Zhong, Z. (2020). A review on industrial surface defect detection based on deep learning technology. ACM International Conference Proceeding Series, 24-30. https://doi.org/10.1145/3426826.3426832

Rekic, T., Beissmann, I., Cebo, A., & Novoselnik, F. (2022). Visual quality inspection of rotors and stators. International Conference on Smart Systems and Technologies (SST 2022). https://doi.org/10.1109/SST55530.2022.9954883

Saini, T., Shiakolas, P. S., & McMurrough, C. (2024). Evaluation of image segmentation methods for in situ quality assessment in additive manufacturing. Metrology, 4(4), 598-618. https://doi.org/10.3390/metrology4040037

Sasongko, A. T., Khofiyah, N. A., & Hadikristanto, W. (2024). AI-driven defect detection in glass bangles manufacturing using transfer-learning with MobileNet model. 2024 8th International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE), 463-468. https://doi.org/10.1109/ICITISEE63424.2024.10730715

Sljivic, M., Pavlovic, A., & Fragassa, C. (2024). A review of sustainable development of additive manufacturing in the conditions of digital and green transition. Proceedings on Engineering Sciences, 6(2), 477-484. https://doi.org/10.24874/PES06.02.005

Srilakshmi, V., Kiran, G. U., Mounika, M., Sravanthi, A., Sravya, N. V. K., Akhil, V. N. S., & Manasa, M. (2023). Evolving convolutional neural networks with meta-heuristics for transfer learning in computer vision. Procedia Computer Science, 230, 658-668. https://doi.org/10.1016/j.procs.2023.12.121

Usha, S. (2021). In situ monitoring of metal additive manufacturing process: A review. In Additive Manufacturing: A Tool for Industrial Revolution 4.0 (pp. 275-299). Elsevier. https://doi.org/10.1016/B978-0-12-822056-6.00007-2

Vaish, R., & Hollinger, M. C. (2023). Case study: IBM - Automating visual inspection. In Springer Handbooks (pp. 1439-1450). https://doi.org/10.1007/978-3-030-96729-1_69

Wolf, P., Mrowca, A., Nguyen, T. T., Baker, B., & Gunnemann, S. (2018). Pre-ignition detection using deep neural networks: A step towards data-driven automotive diagnostics. IEEE Conference on Intelligent Transportation Systems (ITSC), 176-183. https://doi.org/10.1109/ITSC.2018.8569908