In recent years, as electronic devices have become smaller and more powerful, printed wiring boards have been required to have higher densities. The method of simultaneously processing copper foil and insulation layer using a CO₂ laser to process the blind via holes that electrically connect the multilayered layers has become popular. However, laser processing is a noncontact process, and the board is a composite material, which makes it difficult to ensure quality. It is also difficult to observe the internal state of the processed holes from the outside, and the quality inspection of a large number of holes on a single board relies on destructive inspection via sampling. Therefore, we first propose and evaluate an inspection method using multiple machine-learning methods for multipulse machining. We then investigated whether the accuracy of the anomaly detection varied based on the machined hole parameters.

1. [1] M. Noguchi, T. Satomi, Y. Saito, and O. Tsunoda, “Study of printed circuit board inspection system,” Int. J. Automation Technol., Vol.3, No.2, pp. 144-150, 2009. https://doi.org/10.20965/ijat.2009.p0144
2. [2] Electronic Component and Packaging Technology Committee, “The trend of electronic components and packaging technologies,” J. of the Japan Institute of Electronics Packaging, Vol.7, No.1, pp. 17-20, 2004.
3. [3] K. Shibata, “Electronics packaging technology trend for the 2000 – Look for electronics packaging technology,” J. of the Japan Institute of Electronics Packaging, Vol.3, No.1, pp. 1-27, 2000 (in Japanese). https://doi.org/10.5104/jiep.3.1
4. [4] T. Kataoka, “Challenge on new process using ultra-thin copper,” J. of the Japan Institute of Electronics Packaging, Vol.2, No.4, pp. 108-112, 2001 (in Japanese).
5. [5] M. Katayama, S. Yoshihara, S. Seino, and R. Kimizuka, “Study of new removal technique by use of magnetic polishing method for copper overhangs generated in direct laser via process,” J. of the Institute of Electronics Packaging, Vol.17, No.4, pp. 292-296, 2014 (in Japanese). https://doi.org/10.5104/jiep.17.292
6. [6] T. Hirogaki, E. Aoyama, K. Ogawa, S. Onji, and M. Isozumi, “Quality control method of blind via hole based on monitoring Cu direct laser processing in high heat radiation printed circuit board with a high speed camera,” Trans. of the JSME, Vol.82, No.836, Article No.15-00491, 2016 (in Japanese). https://doi.org/10.1299/transjsme.15-00491
7. [7] T. Hirogaki, E. Aoyama, K. Kanki, and R. Yamaguchi, “Estimation of monitoring image in laser blind via-hole drilling process of printed wiring boards with a high speed video camera and temperature visualization from obtained image by two-color method,” Trans. of the JSME, Vol.85, No.874, Article No.19-0009, 2019 (in Japanese). https://doi.org/10.1299/transjsme.19-00009
8. [8] T. Hirogaki, E. Aoyama, R. Yamaguchi, and K. Nakagawa, “Temperature monitoring with a high-speed camera based on two-color method and its CFD analysis in Cu direct laser drilling of printed circuit board,” Trans. of the JSME, Vol.87, No.896, Article No.20-00413, 2021 (in Japanese). https://doi.org/10.1299/transjsme.20-00413
9. [9] C. Zhang, I. A. Salama, N. R. Quick, and A. Kar, “Two-dimensional transient modeling of CO₂ laser drilling of microvias in high density flip chip substrates,” 24th Int. Congress on Laser Materials Processing and Laser Microfabrication, 2025. https://doi.org/10.2351/1.5060567
10. [10] D. Blass, S. Nyga, B. Jungbluth, H.-D. Hoffmann, and K. Dilger, “Composite bonding pre-treatment with laser radiation of 3 µm wavelength: Comparison with conventional laser sources,” Materials, Vol.11, No.7, Article No.1216, 2018. https://doi.org/10.3390/ma11071216
11. [11] J. Gebauer, M. Burkhardt, V. Franke, and A. F. Lasagni, “On the ablation behavior of carbon fiber-reinforced plastics during laser surface treatment using pulsed lasers,” Materials, Vol.13, No.24, Article No.5682, 2020. https://doi.org/10.3390/ma13245682
12. [12] Z. Illyefalvi-Vitez, “Laser processing for microelectronics packaging applications,” Microelectronics Reliability, Vol.41, No.4, pp. 563-570, 2001. https://doi.org/10.1016/S0026-2714(00)00250-X
13. [13] H. Zheng, E. Gan, and G. C. Lim, “Investigation of laser via formation technology for the manufacturing of high density substrates,” Optics and Lasers in Engineering, Vol.36, No.4, pp. 355-371, 2001. https://doi.org/10.1016/S0143-8166(01)00057-4
14. [14] M.-F. Chen and Y.-P. Chen, “Compensating technique of field-distorting error for the CO₂ laser galvanometric scanning drilling machines,” Int. J. of Machine Tools and Manufacture, Vol.47, Nos.7-8, pp. 1114-1124, 2007. https://doi.org/10.1016/j.ijmachtools.2006.09.015
15. [15] A. E. Abdulwahab, K. A. Hubeatir, and K. I. Imhan, “Optimization of PC micro-drilling using a continuous CO₂ laser: An experimental and theoretical comparative study,” J. of Engineering and Applied Science, Vol.69, Article No.98, 2022. https://doi.org/10.1186/s44147-022-00151-y
16. [16] K. A. Hubeatir, M. M. AL-Kafaji, and H. J. Omran, “Deep engraving process of PMMA using CO₂ laser complemented by Taguchi Method,” IOP Conf. Series: Materials Science and Engineering, Vol.454, Article No.012068, 2018. https://doi.org/10.1088/1757-899X/454/1/012068
17. [17] L. Qi, C. Ruck, G. Spychalski, B. King, B. Wu, and Y. Zhao, “Writing wrinkles on poly (dimethylsiloxane) (PDMS) by surface oxidation with a CO₂ laser engraver,” ACS Applied Materials & Interfaces, Vol.10, No.4, pp. 4295-4304, 2018. https://doi.org/10.1021/acsami.7b17622
18. [18] A. R. Bucossi, J. E. Rossi, B. J. Landi, and I. Puchades, “Experimental design for CO₂ laser cutting of sub-millimeter features in very large-area carbon nanotube sheets,” Optics & Laser Technology, Vol.134, Article No.106591, 2021. https://doi.org/10.1016/j.optlastec.2020.106591
19. [19] F. Wang, X. J. Wang, Z. Y. Ma, J. H. Yan, Y. Chi, C. Y. Wei, M. J. Ni, and K. F. Cen, “The research on the estimation for the NOx emissive concentration of the pulverized coal boiler by the flame image processing technique,” Fuel, Vol.81, No.1, pp. 2113-2120, 2002. https://doi.org/10.1016/S0016-2361(02)00145-X
20. [20] Z. W. Jiang, Z. X. Luo, and H. C. Zhou, “A simple measurement method of temperature and emissivity of coal-fired flames from visible radiation image and its application in a CFB boiler furnace,” Fuel, Vol.88, No.6, pp. 980-987, 2009. https://doi.org/10.1016/j.fuel.2008.12.014
21. [21] Y. Huang, Y. Yan, and G. Riley, “Vision-based measurement of temperature distribution in a 500 kW model furnace using the two color method,” Measurement, Vol.28, pp. 175-183, 2000. https://doi.org/10.1016/S0263-2241(00)00010-5
22. [22] D. J. Rezende and S. Mohamed, “Variational inference with normalizing flows,” arXiv:1505.05770, 2015. https://doi.org/10.48550/arXiv.1505.05770
23. [23] F. Utaminingrum, R. P. Prasetya, and R. Rizdania, “Combining multiple feature for robust traffic sign detection,” J. of Image and Graphics, Vol.8, No.2, pp. 53-58, 2020. https://doi.org/10.18178/joig.8.2.53-58
24. [24] L. Bergman, N. Cohen, and Y. Hoshen, “Deep nearest neighbor anomaly detection,” arXiv:2002.10445, 2020. https://doi.org/10.48550/arXiv.2002.10445
25. [25] O. Rippel, P. Mertens, and D. Merhof, “Modeling the distribution of normal data in pre-trained deep features for anomaly detection,” arXiv:2005.14140, 2020. https://doi.org/10.48550/arXiv.2005.14140
26. [26] K. Roth, L. Pemula, J. Zepeda, B. Schölkopf, T. Brox, and P. Gehler, “Towards total recall in industrial anomaly detection,” arXiv:2106.08265, 2021. https://arxiv.org/abs/2106.08265
27. [27] Z. Liu, Y. Zhou, Y. Xu, and Z. Wang, “SimpleNet: A simple network for image anomaly detection and localization,” arXiv:2303.15140, 2023. https://doi.org/10.48550/arXiv.2303.15140
28. [28] H. C. Shin, H. R. Roth, M. Gao, L. Lu, Z. Xu, I. Nogues, J. Yao, D. Mollura, and R. M. Summers, “Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning,” IEEE Trans. on Medical Imaging, Vol.35, No.5, pp. 1285-1298, 2016. https://doi.org/10.1109/TMI.2016.2528162
29. [29] A. Canziani, A. Paszke, and E. Culurciello, “An analysis of deep neural network models for practical applications,” arXiv:1605.07678, 2017. https://doi.org/10.48550/arXiv.1605.07678
30. [30] K. Hara, H. Kataoka, and Y. Satoh, “Can spatiotemporal 3D CNNs retrace the history of 2D CNNs and ImageNet?,” arXiv:1711.09577, 2018. https://doi.org/10.48550/arXiv.1711.09577
31. [31] Y. Lecun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, Vol.521, No.7553, pp. 436-444, 2015. https://doi.org/10.1038/nature14539