Real-Time Quality Control in Thin Glass Forming Using Infrared Thermography and Deep Learning

Abstract:

Towards the growing trends in lightweight, flexible, and optical advantages, thin glasses become key components in numerous applications such as consumer electronics like foldable smartphones, or automotive interiors. Nonisothermal glass molding promises a viable technology for the cost-efficient production of precision glass components. In the existing production, the quality of the glass products can only be accessed at the end of the hot forming process. Due to high rates of product failures often appeared in the precision glass molding processes, the current quality control of the produced optical products suffers low process efficiency. This work introduces an enabling approach for monitoring the product quality in real-time using thermography and machine learning. Specifically, the acquisition of the temperature fields of the glass components during the hot forming stage enabled by an infrared thermographic camera allows machine learning to predict the final shape of the molded components at the end of the forming process. Several transfer learning models have been investigated to demonstrate the proposed method. To further enhance the prediction performance, self-built convolutional neural network models were developed using different types of image data. By incorporating the time-series image data as an input to the learning models, the prediction performance was achieved. The model built in the present work demonstrates an excellent prediction accuracy where the difference between the measured and predicted shapes of the glass products can be kept at low double-digit micrometers. Such accuracy achieved by our self-developed machine learning model promisingly satisfy the quality control in serial productions of numerous precision optical glass components in automotive and consumer electronics sectors.

• Periodical: Key Engineering Materials (Volume 926)
• Pages: 2312-2321
• DOI: https://doi.org/10.4028/p-5w9vr9
• Online since: July 2022
• Authors: Anh Tuan Vu*, Paul Alexander Vogel, Abimathi Siva Subramanian, Tim Grunwald, Thomas Bergs
• Keywords: Glass Molding, Infrared Thermography, Machine Learning, Production Control

References

[1] Bax & Company, A vision on the future of automotive lightweighting. Alliance - A report on the European Union's Horizon 2020. Grant Agreement No. 723893.

[2] Information on. https://www.ipt.fraunhofer.de/en/projects/glass4autofuture.html.

[3] A.T. Vu, P.-A. Vogel, O. Dambon, F. Klocke, Vacuum-assisted precision molding of 3D thin microstructure glass optics, in: Fiber Lasers and Glass Photonics: Materials through Applications, Strasbourg, France, SPIE, Bellingham, Washington, USA, (2018).

DOI: 10.1117/12.2307060

[4] A.T. Vu, H. Kreilkamp, O. Dambon, F. Klocke, Nonisothermal glass molding for the cost-efficient production of precision freeform optics, Opt. Eng 55 (2016) 71207.

DOI: 10.1117/1.oe.55.7.071207

[5] T. Zhou, J. Yan, N. Yoshihara, T. Kuriyagawa, Study on nonisothermal glass molding press for aspherical lens, JAMDSM 4 (2010) 806–815.

DOI: 10.1299/jamdsm.4.806

[6] P.-A. Vogel, A.T. Vu, H. Mende, T. Grunwald, T. Bergs, R.H. Schmitt, Approaches and methodologies for process development of thin glass forming, in: Optifab 2019, Rochester, United States, SPIE, Bellingham, Washington, USA, 2019, p.68.

DOI: 10.1117/12.2536431

[7] H. Zang, J. Yu, Y. Zhou, B. Tao, Non-isothermal molding technology research of ultra-precision glass lens, in: International Symposium on Optoelectronic Technology and Application 2014: Laser Materials Processing; and Micro/Nano Technologies, Beijing, China, SPIE, 2014, p.929517.

DOI: 10.1117/12.2073136

[8] H. Kreilkamp, A.T. Vu, O. Dambon, F. Klocke, Replicative manufacturing of complex lighting optics by non-isothermal glass molding, in: Polymer Optics and Molded Glass Optics: Design, Fabrication, and Materials 2016, San Diego, California, United States, SPIE, 2016, 99490B.

DOI: 10.1117/12.2235848

[9] H. Kreilkamp, A.T. Vu, O. Dambon, N.F. Klocke, Nonisothermal glass moulding of complex LED optics, in: S.K. Sundaram (Ed.), 77th Conference on Glass Problems, John Wiley & Sons, Inc, Hoboken, NJ, USA, 2017, p.141–149.

DOI: 10.1002/9781119417507.ch13

[10] Y. Zhong, R. Du, L. Zhang, A.Y. Yi, Structrual Coloration of Surfaces With Microstructures Replicated by Non-Isothermal Precision Glass Molding, in: Proceedings of the ASME 15th International Manufacturing Science and Engineering Conference - 2020, Virtual, Online, the American Society of Mechanical Engineers; Curran Associates Inc, New York, NY, Red Hook, NY, (2020).

DOI: 10.1115/msec2020-8467

[11] C. Rojacher, A.T. Vu, T. Grunwald, T. Bergs, Precision glass molding of infrared optics with anti-reflective microstructures, in: Optical Manufacturing and Testing XIII, Online Only, United States, SPIE, 24.08.2020 - 28.08.2020, p.30.

DOI: 10.1117/12.2570519

[12] A.T. Vu, C. Rojacher, T. Grunwald, T. Bergs, Molded anti-reflective structures of chalcogenide glasses for infrared optics by precision glass molding, in: Optifab 2019, Rochester, United States, SPIE, Bellingham, Washington, USA, 2019, p.67.

DOI: 10.1117/12.2536548

[13] T. Zhou, J. Yan, T. Kuriyagawa, High-Efficiency and Ultra-precision Glass Molding of Aspherical Lens and Microstructures, in: Proceedings of International Symposium on Ultraprecision Engineering and Nanotechnology.

[14] H. Kreilkamp, J.-H. Staasmeyer, L. Niendorf, The Future of Glass Optics Replication, Optik & Photonik 11 (2016) 28–31.

DOI: 10.1002/opph.201600023

[15] Y. Zhang, G. Yan, Z. Li, F. Fang, Quality improvement of collimating lens produced by precision glass molding according to performance evaluation, Opt. Express 27 (2019) 5033–5047.

DOI: 10.1364/oe.27.005033

[16] F. Wang, Y. Chen, F. Klocke, G. Pongs, A.Y. Yi, 2009. Numerical Simulation Assisted Curve Compensation in Compression Molding of High Precision Aspherical Glass Lenses. Journal of Manufacturing Science and Engineering 131, 011014. https://doi.org/10.1115/1.3063652.

DOI: 10.1115/1.3063652

[17] G. Liu, A.T. Vu, O. Dambon, F. Klocke, Glass Material Modeling and its Molding Behavior, MRS Advances 2 (2017) 875–885.

DOI: 10.1557/adv.2017.64

[18] T.D. Pallicity, A.-T. Vu, K. Ramesh, P. Mahajan, G. Liu, O. Dambon, Birefringence measurement for validation of simulation of precision glass molding process, J Am Ceram Soc 100 (2017) 4680–4698.

DOI: 10.1111/jace.15010

[19] A.T. Vu, H. Kreilkamp, B.J. Krishnamoorthi, O. Dambon, F. Klocke, A hybrid optimization approach in non-isothermal glass molding, in: AIP Conference Proceedings, Nantes, France, 2016, p.40006.

DOI: 10.1063/1.4963428

[20] W. Yang, Z. Zhang, W. Ming, L. Yin, G. Zhang, Study on shape deviation and crack of ultra-thin glass molding process for curved surface, Ceramics International (2021).

DOI: 10.1016/j.ceramint.2021.11.228

[21] A.T. Vu, T. Helmig, A.N. Vu, Y. Frekers, T. Grunwald, R. Kneer, T. Bergs, Numerical and experimental determinations of contact heat transfer coefficients in nonisothermal glass molding, J Am Ceram Soc 103 (2020) 1258–1269.

DOI: 10.1111/jace.16756

[22] T. Zhou, Q. Zhou, J. Xie, X. Liu, X. Wang, H. Ruan, Surface defect analysis on formed chalcogenide glass Ge22Se58As20 lenses after the molding process, Appl. Opt. 56 (2017) 8394–8402.

DOI: 10.1364/ao.56.008394

[23] A.T. Vu, Avila Hernandez, Rocio de los Angeles, T. Grunwald, T. Bergs, Modeling nonequilibrium thermoviscoelastic material behaviors of glass in Nonisothermal Glass Molding, J Am Ceram Soc (2022).

DOI: 10.1111/jace.18605

[24] A.T. Vu, T. Grunwald, T. Bergs, Thermo-viscoelastic Modeling of Nonequilibrium Material Behavior of Glass in Nonisothermal Glass Molding, Procedia Manufacturing 47 (2020) 1561–1568.

DOI: 10.1016/j.promfg.2020.04.350

[25] A.T. Vu, A.N. Vu, T. Grunwald, T. Bergs, Modeling of thermo‐viscoelastic material behavior of glass over a wide temperature range in glass compression molding, J Am Ceram Soc 103 (2020) 2791–2807.

DOI: 10.1111/jace.16963

[26] H. Kreilkamp, J.-H. Staasmeyer, L. Niendorf, The Future of Glass Optics Replication, Optik & Photonik 11 (2016) 28–31.

DOI: 10.1002/opph.201600023

[27] A.T. Vu, A.N. Vu, G. Liu, T. Grunwald, O. Dambon, F. Klocke, T. Bergs, Experimental investigation of contact heat transfer coefficients in nonisothermal glass molding by infrared thermography, J Am Ceram Soc 102 (2019) 2116–2134.

DOI: 10.1111/jace.16029

[28] A. Krizhevsky, I. Sutskever, G.E. Hinton, ImageNet Classification with Deep Convolutional Neural Networks, in: Advances in Neural Information Processing Systems, Curran Associates, Inc, (2012).

DOI: 10.1145/3065386

[29] J. Donahue, Y. Jia, O. Vinyals, J. Hoffman, N. Zhang, E. Tzeng, T. Darrell, DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition, in: Proceedings of the 31st International Conference on Machine Learning, PMLR, Bejing, China, 2014, p.647–655.

[30] D. Bau, B. Zhou, A. Khosla, A. Oliva, A. Torralba, Network Dissection: Quantifying Interpretability of Deep Visual Representations, (2017).

DOI: 10.1109/cvpr.2017.354

[31] B. Neyshabur, H. Sedghi, C. Zhang, What is being transferred in transfer learning?, in: Advances in Neural Information Processing Systems, Curran Associates, Inc, 2020, p.512–523.

[32] J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, L. Fei-Fei, ImageNet: A large-scale hierarchical image database, in: IEEE Conference on Computer Vision and Pattern Recognition, 2009, Miami, FL, IEEE, Piscataway, NJ, 2009, p.248–255.

DOI: 10.1109/cvpr.2009.5206848

[33] L. Li, K. Jamieson, G. DeSalvo, A. Rostamizadeh, A. Talwalkar, Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization, J. Mach. Learn. Res. 18 (2018) 1–52.

[34] Diederik P. Kingma, Jimmy Ba, Adam: A Method for Stochastic Optimization, CoRR abs/1412.6980 (2015).

[35] A.T. Vu, S. Gulati, P.-A. Vogel, T. Grunwald, T. Bergs, Physics-Informed Data-Driven Models for Predicting Time- and Temperature-Dependent Viscoelastic Material Behaviors of Optical Glasses, SSRN Journal (2021). https://doi.org/10.2139/SSRN.3822865.

DOI: 10.2139/ssrn.3822865

[36] A.T. Vu, S. Gulati, P.-A. Vogel, T. Grunwald, T. Bergs, Machine learning-based predictive modeling of contact heat transfer, International Journal of Heat and Mass Transfer 174 (2021) 121300.

DOI: 10.1016/j.ijheatmasstransfer.2021.121300

[37] Y. Yao, L. Rosasco, A. Caponnetto, On Early Stopping in Gradient Descent Learning, Constr Approx 26 (2007) 289–315.

DOI: 10.1007/s00365-006-0663-2

[38] S.S. Alahmari, D.B. Goldgof, P.R. Mouton, L.O. Hall, Challenges for the Repeatability of Deep Learning Models, IEEE Access 8 (2020) 211860–211868.

DOI: 10.1109/access.2020.3039833