COMPARISON OF ADVANCED CAMERA VISION SYSTEMS FOR DEFECT INSPECTION OF 3D PRINT PARTS

Jozef HUSÁR, Justyna TROJANOVSKA, Olha KALMAN, Peter LAZORÍK

Abstract


The quality inspection of 3D-printed parts is of paramount importance in ensuring their structural integrity and functional reliability. The present study compares four advanced camera vision systems for defect detection in additive manufacturing. Each system was evaluated on 3D-printed samples that exhibited common defects, including surface irregularities, cracks, voids, and material inconsistencies. The evaluation criteria encompassed aspects such as detection accuracy, processing speed, repeatability, and suitability for automated inspection. The experimental results obtained highlighted the superior performance of multispectral imaging in detecting material inconsistencies, while structured white light was found to be effective for precise surface topography analysis. The Keyence AI system demonstrated adaptability in identifying complex defects through machine learning, offering fast and reliable detection. The macro-optical SLR, despite its high level of detail, was found to be less efficient for real-time automated inspection. The findings suggest that hybrid approaches, which combine multiple imaging techniques, can optimize defect detection performance for various types of flaws. This research provides valuable insights for industrial engineers and manufacturers seeking to enhance quality control in additive manufacturing. By comprehending the strengths and limitations of each vision system, industries can select or integrate the most suitable technology for their specific inspection needs, ultimately enhancing production efficiency and reducing defective output.


Full Text:

PDF

References


Kalman, O., Husár, J., Lazorík, P. Using Laser Profilometry to Investigation FDM Printing Parameters for Outer-Perimeter Analysis and Surface Quality Improvement, Applied Sciences, ISSN 2076-3417, Basel, 2024.

Židek, K., Hosovsky, A., Piteľ, J., Bednár, S. Recognition of Assembly Parts by Convolutional Neural Networks, In: Hloch, S., Klichová, D., Krolczyk, G., Chattopadhyaya, S., Ruppenthalová, L. (Ed.), Advances in Manufacturing Engineering and Materials, Lecture Notes in Mechanical Engineering, ISBN 978-3-319-99353-9, Bratislava, October 2019, Springer, Cham.

Demčák, J., Lishchenko, N., Pavlenko, I., Pitel’, J., Židek, K. The Experimental SMART Manufacturing System in SmartTechLab, In: Trojanowska, J., Kujawińska, A., Machado, J., Pavlenko, I. (Ed.), Advances in Manufacturing III, MANUFACTURING 2022, Lecture Notes in Mechanical Engineering, ISBN 978-3-030-99310-8, Poznań, September 2022, Springer, Cham.

Gao, F., Xu, Y., Li, Y., et al. In-Situ Form Metrology of Structured Composite Surfaces Using Hybrid Structured-Light Measurement with a Novel Calibration Method, Nanomanufacturing and Metrology, ISSN 2520-811X, Beijing, 2024.

Zhou, H.A., Wolfschläger, D., Florides, C., et al. Generative AI in industrial machine vision: a review, Journal of Intelligent Manufacturing, ISSN 0956-5515, Heidelberg, 2025.

Zheng, S. Design of intelligent manufacturing product identification and detection system based on machine vision, In: Xu, Z., Parizi, R.M., Hammoudeh, M., Loyola-González, O. (Ed.), CSIA 2020, AISC, Vol. 1146, pp. 258–265, ISBN 978-3-030-50029-0, Hangzhou, June 2020, Springer, Cham.

Židek, K., Hladký, V., Pitel’, J., Demčák, J., Hošovský, A., Lazorík, P. SMART Production System with Full Digitalization for Assembly and Inspection in Concept of Industry 4.0, In: Perakovic, D., Knapcikova, L. (Ed.), Future Access Enablers for Ubiquitous and Intelligent Infrastructures, FABULOUS 2021, Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, Vol. 382, ISBN 978-3-030-78459-1, Dubrovnik, October 2021, Springer, Cham.

Jeon, J., Kim, S., Lee, J. Novel real-time structured light 3D scanning technique for powder bed surface inspection in additive manufacturing, Measurement, ISSN 0263-2241, Amsterdam, 2024.

Gomez, C., Su, R., De Groot, P., Leach, R. Noise reduction in coherence scanning interferometry for surface topography measurement, Nanomanufacturing and Metrology, ISSN 2520-811X, 2020.

Wang, Y., Li, H., Zhang, X. Fast and Accurate Defects Detection for Additive Manufactured Parts Using Multispectrum Imaging and Improved YOLOv3 Algorithm, 3D Printing and Additive Manufacturing, ISSN 2329-7662, New Rochelle, 2021.

Chen, L., Yao, X., Liu, K., Tan, C., Moon, S.K. Multisensor fusion-based digital twin in additive manufacturing for in-situ quality monitoring and defect correction, Additive Manufacturing, ISSN 2214-8604, Amsterdam, 2023.

Niu, Y., Chadwick, E., Ma, A.W.K., Yang, Q. Semi-Siamese Network for Robust Change Detection Across Different Domains with Applications to 3D Printing, arXiv preprint, arXiv:2212.08583.

Gobert, C., Reutzel, E.W., Petrich, J., Nassar, A.R., Phoha, S. Application of supervised machine learning for defect detection during metallic powder bed fusion additive manufacturing using high resolution imaging, Additive Manufacturing, ISSN 2214-8604, Amsterdam, 2018.

Wang, W., Wang, P., Zhang, H., Chen, X., Wang, G., Lu, Y., Chen, M., Liu, H., Li, J. A Real-Time Defect Detection Strategy for Additive Manufacturing Processes Based on Deep Learning and Machine Vision Technologies, Micromachines, ISSN 2072-666X, Basel, 2024.

Chen, L., Yao, X., Feng, W., Chew, Y., Moon, S.K. Multimodal sensor fusion for real-time location-dependent defect detection in laser-directed energy deposition, Additive Manufacturing, ISSN 2214-8604, Amsterdam, 2023.

Ahsan, M.M., Raman, S., Siddique, Z. Defect Analysis of 3D Printed Cylinder Object Using Transfer Learning Approaches, arXiv preprint, arXiv:2310.08645.

Grasso, M. In situ monitoring of powder bed fusion homogeneity in electron beam melting, Materials, ISSN 1996-1944, Basel, 2021.

Guerra, M.G., Errico, V., Fusco, A., Lavecchia, F., Campanelli, S.L., Galantucci, L.M. High resolution-optical tomography for in-process layerwise monitoring of a laser-powder bed fusion technology, Additive Manufacturing, ISSN 2214-8604, Amsterdam, 2022.

Antosz, K., Knapčíková, L., Husár, J. Evaluation and Application of Machine Learning Techniques for Quality Improvement in Metal Product Manufacturing, Applied Sciences, ISSN 2076-3417, Basel, 2024.


Refbacks

  • There are currently no refbacks.


JOURNAL INDEXED IN :