ru
Back
DOI: 10.17586/1023-5086-2022-89-02-36-42
УДК: 681.786
Synthesis of freeform optical surfaces using neural networks
Full text on elibrary.ru
Publication in Journal of Optical Technology
Мазур Я.В., Вознесенская А.О. Синтез оптических поверхностей свободной формы с использованием нейронных сетей // Оптический журнал. 2022. Т. 89. № 2. С. 36–42. http:doi.org/10.17586/1023-5086-2022-89-02-36-42
Mazur Ya.V., Voznesenskaya A.O. Synthesis of freeform optical surfaces using neural networks [in Russian] // Opticheskii Zhurnal. 2022. V. 89. № 2. P. 36–42. http:doi.org/10.17586/1023-5086-2022-89-02-36-42
Ya. V. Mazur and A. O. Voznesenskaya, "Synthesis of freeform optical surfaces using neural networks," Journal of Optical Technology. 89(2), 89-93 (2022). https://doi.org/10.1364/JOT.89.000089
Subject of study. Developed methods for synthesis of freeform illumination optics (ellipsoid, Monge-Ampere, string, and flow line methods) do not contain a correct description of the transformation of input and output wavefronts determined by the wave aberration function, do not consider the image quality criteria, and are not suitable for the calculation of imaging systems. The most common methods for synthesis of freeform elements of imaging systems (simultaneous multiple surface and ray-mapping methods) are also not ubiquitous because they are aimed at realization of a specific system configuration and, at least, require modification to solve a specific task. The largest complication in the synthesis stages of systems of imaging optics is the determination of the initial system scheme. Design of a method for synthesis of optical systems that does not require a starting point is a highly relevant objective of applied optics. A method allowing the synthesis of freeform optical surfaces for imaging systems using an artificial neural network is presented in this paper. Method. A neural network was built upon radial-basis functions and uses the geometric mapping method to generate the coordinates of the desired optical surface during backward ray tracing. The neural network was trained on different numbers of optical systems, which were automatically generated with variations in structural parameters and positions of the object and image. Main results. The method was demonstrated to operate effectively using more than 17,000 training systems at the ray set dimension of M=4096. The model of a flat-hyperbolic lens calculated using this method has a wave aberration of W<5×10−2 for wavelengths within the diffraction tolerance. Practical significance. The developed method can be used to design high-performance imaging systems.
freeform optical surfaces, synthesis of optical systems, calculation of optical systems, geometric mapping, neural networks, machine learning
OCIS codes: 330.4060
References:1. A. Anees, “System engineering of complex optical systems: requirements and verification documents,” Proc. SPIE 11100, 111000E (2019).
2. F. Fang, N. Zhang, and X. Zhang, “Precision injection molding of freeform optics,” Adv. Opt. Technol. 5(4), 303–324 (2016).
3. S. R. Patterson and E. B. Magrab, “Design and testing of a fast tool servo for diamond turning,” Precis. Eng. 7(3), 123–128 (1985).
4. L. Zhu, Z. Li, F. Fang, S. Huang, and X. Zhang, “Review on fast tool servo machining of optical freeform surfaces,” Int. J. Adv. Manuf. Technol. 95, 2071–2092 (2018).
5. J. Yang and Y. Altintas, “Generalized kinematics of five-axis serial machines with non-singular tool path generation,” Int. J. Mach. Tools Manuf. 75, 119–132 (2013).
6. G. Bao, L. Cowsar, and W. Masters, Mathematical Modeling in Optical Science (Society for Industrial and Applied Mathematics, Philadelphia, 2001).
7. H. Ries and J. Muschaweck, “Tailored freeform optical surfaces,” J. Opt. Soc. Am. A 19(3), 590–595 (2002).
8. C. Canavesi, W. J. Cassarly, and J. P. Rolland, “Target flux estimation by calculating intersections between neighboring conic reflector patches,” Opt. Lett. 38(23), 5012–5015 (2013).
9. S. Sorgato, R. Mohedano, J. Chaves, M. Hernández, J. Blen, D. Grabovi ˇcki ´c, P. Benítez, J. C. Miñano, H. Thienpont, and F. Duerr, “Compact illumination optic with three freeform surfaces for improved beam control,” Opt. Express 25(24), 29627–29641 (2017).
10. J. Chaves, Introduction to Nonimaging (CRC Press, Boca Raton, 2015).
11. Y. Wang, D. Cheng, and C. Xu, “Freeform optics for virtual and augmented reality,” in Optical Design and Fabrication (Freeform, IODC, OFT) (2017), paper JTu3A.1.
12. P. Benítez, J. C. Miñano, D. Grabovickic, B. Narasimhan, and M. Nikolic, “Freeform optics for virtual reality applications,” in Optical Design and Fabrication (Freeform, IODC, OFT) (2017), paper ITu2A.1.
13. A. Domhardt, Analytical Design of Freeform Optics for Point Light Sources (KIT Scientific Publishing, Karlsruhe, 2013).
14. J. Jiang, S. To, W. B. Lee, and B. Cheung, “Optical design of a freeform TIR lens for LED streetlight,” Optik 121(19), 1761–1765 (2010).
15. A. O. Voznesenskaya, G. E. Romanova, and X. Qiao, “Modeling of LED scheme for street lighting on the basis of chip-on-board scheme,” Proc. SPIE 10693, 106930X (2018).
16. G. E. Romanova, X. Qiao, and V. E. Strigalev, “Designing a side-emitting lens using the composing method,” Nauchno-Tekh. Vestn. Inf. Tekhnol., Mekh. Opt. 21(2), 147–153 (2021).
17. M. Chrisp, L. Petrilli, M. Echter, and A. Smith, “Freeform surveillance telescope demonstration,” in MSS Parallel Conference, MSS by BRTRC Federal Solutions under Contract (2019), pp. 2769–2775.
18. J. Reimers, A. Bauer, K. P. Thompson, and J. P. Rolland, “Freeform spectrometer enabling increased compactness,” Light Sci. Appl. 6, e17026 (2017).
19. R. Geyl, E. Ruch, R. Bourgois, R. Mercier-Ythier, H. Leplan, and F. Riguet, “Freeform optics design, fabrication and testing technologies for space applications,” Proc. SPIE 11180, 111800P (2019).
20. E. M. Schiesser, A. Bauer, and J. P. Rolland, “Effect of freeform surfaces on the volume and performance of unobscured three mirror imagers in comparison with off-axis rotationally symmetric polynomials,” Opt. Express 27(15), 21750–21765 (2019).
21. S. Cui, N. P. Lyons, L. R. Diaz, R. Ketchum, K.-J. Kim, H.-C. Yuan, M. Frasier, W. Pan, and R. A. Norwood, “Silicone optical elements for cost-effective freeform solar concentration,” Opt. Express 27(8), A572–A580 (2019).
22. C. Yoon, A. Bauer, D. Xu, C. Dorrer, and J. P. Rolland, “Absolute linear-in-k spectrometer designs enabled by freeform optics,” Opt. Express 27(24), 34593–34602 (2019).
23. F. Muñoz, P. Benítez, and J. C. Miñano, “High-order aspherics: the SMS nonimaging design method applied to imaging optics,” Proc. SPIE 7100, 70610G (2011).
24. A. Bruneton, A. Bäuerle, R. Wester, J. Stollenwerk, and P. Loosen, “Limitations of the ray mapping approach in freeform optics design,” Opt. Lett. 38(11), 1945–1947 (2013).
25. S. A. Rodionov, Automation of the Design of Optical Systems (Mashinostroenie, Leningrad, 1982).
26. I. Mazur, A. Voznesenskaya, A. Trifanov, and M. Svintsov, “Development of a neural network for the synthesis of freeform optical elements with a flat wavefront,” in Proceedings of the 30th International Conference on Computer Graphics and Machine Vision (2020).
27. P. L. Papaev, I. V. Maklyaev, and S. P. Dudarov, “Comparison of modeling ability between radial basis function neural networks and double-layer perceptrons,” Usp. Khim. Khim. Tekhnol. 34(6(229)), 109–111 (2020).
28. T. M. Mitchell, Machine Learning (McGraw Hill, New York, 1997).
29. E. Parzen, “On estimation of a probability density function and mode,” Ann. Math. Stat. 33(3), 1065–1076 (1962).
30. E. A. Nadaraya, “On estimating regression,” Theory Probab. Its Appl. 9(1), 141–142 (1964).
31. G. S. Watson, “Smooth regression analysis,” Sankhya A 26(4), 359–372 (1964).
32. M. Rosenblatt, “Remarks on some nonparametric estimates of a density function,” Ann. Math. Stat. 27(3), 832–837 (1956).
33. G. I. Tsukanova, Applied Optics, Part 1: Lecture Notes (SPbGU, ITMO, St. Petersburg, 2008), pp. 54–55.
34. A. O. Voznesenskaya, Ya. V. Mazur, and P. Yu. Krizskii, “Interpolation equations of freeform refractive surfaces,” J. Opt. Technol. 85(9), 579–581 (2018) [Opt. Zh. 85(9), 70–73 (2018)].