We considered the process of wavefront reconstruction, which is based on the use of Shack–Hartmann sensor and complex-valued artificial neural network. The pixel positions are mapped on a complex plane. The process of phase reconstruction has been tested with the help of the distorted wavefront, which was obtained in the framework of a statistical model for a turbulent atmosphere. The learning of the network is based on a genetic algorithm. The process has the fast convergence, resistance to the local errors, and dynamic adaptability.
Shack–Hartmann sensor, wavefront reconstruction, turbulent atmosphere, complex neural network, genetic algorithm
1. Gurvich A.S., Kon A.I., Mironov V.L., Hmelevcov S.S. Lazernoe izluchenie v turbulentnoj atmosfere. M.: Nauka, 1976. 277 p.
2. Marakasov D.A. Struktura prostranstvenno-vremennogo spektra lazernogo puchka v atmosfere v uslovijah sil'noj turbulentnosti // Optika atmosf. i okeana. 2013. Т. 26, N 5. P. 345–349.
3. Wilks S.C., Morris J.R., Brase J.M., Olivier S.S., Henderson J.R., Thompson C., Kartz M., Ruggerio A.J. Modeling of adaptive optics-based free-space communications systems // Proc. SPIE. 2002. V. 4421. P. 121–128.
4. Wu H., Yan H., Li X. Modal correction for fiber-coupling efficiency in free-space optical communication systems through atmospheric turbulence // Optik. 2010. V. 121. P. 1789–1793.
5. Zel'dovich B.Ja., Pilipeckij N.F., Shkunov V.V. Obrashhenie volnovogo fronta pri vynuzhdennom rassejanii sveta // Uspehi fiz. nauk. 1982. V. 138, issue 2. P. 249–288.
6. Dmitriev V.G. Nelinejnaja optika i obrashhenie volnovogo fronta. M.: Fizmatlit, 2003. 256 p.
7. Lukin V.P. Adaptivnoe formirovanie puchkov i izobrazhenij v atmosfere i okeane // Optika atmosf. i okeana. 2009. V. 22, N 10. P. 937–944.
8. Garanin S.G., Golubev A.I., Povyshev V.M., Starikov F.A., Shnjagin R.A. Issledovanie vozmozhnosti povyshenija jeffektivnosti adaptivnoj sistemy lazernoj ustanovki «Luch» // Optika atmosf. i okeana. 2013. V. 26, N 5. P. 427–433.
9. Grosset-Grange С., Barnier J., Chappuis C., Cortey H. Design principle and first results obtained on the LMJ deformable mirror prototype // Proc. SPIE. 2007. V. 6584. P. 1–14.
10. Lukin V.P. Atmosfernaja i adaptivnaja optika. Novosibirsk: Nauka, 1986. 248 p.
11. Lee L.H. Closed-loop field conjugation using decentralized multi-conjugate adaptive optics // Proc. SPIE. 2007. V. 6551. P. 65510Q.
12. Hirose A. Complex-valued neural networks fertilize electronics // Studies in Computational Intelligence. 2006. V. 32. P. 3–8.
13. Hirose A. Complex-Valued Neural Networks. Berlin: Springer, 2006. 176 p.
14. Neal D.R., Copland J., Neal D. Shack–Hartman wavefront sensor precision and accuracy // Proc. SPIE. 2002. V. 4779. P. 148–160.
15. Southwell W. Wave-front estimation from wave-front slope measurement // J. Opt. Soc. Amer. 1980. V. 70, N 8. P. 998–1006.
16. Kutishhev S.N., Golovinskij P.A. Opredelenie parametrov tel prostoj formy po rassejaniju ul'trakorotkih impul'sov // Izv. vuzov. Radiofiz. 2008. V. 51, N 6. P. 526–535.
17. Kutishhev S.N., Golovinskij P.A. Primenenie nejrosetej dlja opredelenija formy ob#ektov po otrazheniju ul'trakorotkih impul'sov // Nejrokomp'jutery: razrabotka, primenenie. 2008. N 3–4. P. 108–114.
18. Golovinskij P.A. Kogerentnyj nejron i raspoznavanie obrazov // Problemy upravlenija. 2006. N 5. P. 86–88.
19. Astapenko V.A., Golovinskij P.A. Nejronnye seti s kvantovoj interferenciej // Nejrokomp'jutery: razrabotka, primenenie. 2012. N 4. P. 3–12.
20. Naruse M., Miyazaki T., Kubota F., Kawazoe T., Kobayashi K., Sangu S., Ohtsu M. Nanometric summation architecture based on optical near-field interaction between quantum dots // Opt. Lett. 2005. V. 30, N 2. P. 201–203.
21. Aizenberg I. Complex-Valued Neural Networks with Multi-Valued Neurons. Berlin: Springer-Verlag, 2011. 262 p.
22. Hirose A. Complex-Valued Neural Networks: Advances and Applications. Hoboken: Wiley-IEEE Press, 2013. 304 p.
23. Shabat B.V. Vvedenie v kompleksnyj analiz. SPb.: Lan', 2004. 336 p.
24. Hirose A. Application of complex-valued neural networks to coherent optical computing using phase-sensitive detection scheme // Information Sci. 1994. V. 2. P. 103–117.
25. Jalab H.A., Ibrahim R.W. New activation functions for complex-valued neural network // Int. J. Phys. Sci. 2011. V. 6, N 7. P. 1766–1772.
26. Szilagai M.N., Salik B. Neural Networks with complex activations and connection weights // Complex Systems. 1994. V. 8. P. 115–126.
27. Amin Md.F., Islam Md.M., Murase K. Ensemble of single-layered complex-valued neural networks for classification tasks // Neurocomputing. 2009. V. 72. P. 2227–2234.
28. Savitha R., Suresh S., Sundararajan N., Saratchandran P. A new learning algorithm with logarithmic performance index for complex-valued neural networks // Neurocomputing. 2009. V. 72. P. 3771–3781.
29. Chen X., Tang Zh., Li S. An modified error function for the complex-value backpropagation neural networks // Neural Information Processing. 2005. V. 8, N 1. P. 1–8.
30. Kalitkin N.N. Chislennye metody. SPb: BChV-Peterburg, 2011. 592 p.
31. Melanie M. An introduction to genetic algorithms. Massachusetts: MIT Press, 1996. 158 p.
32. Ellerbroek B.L., Cochran G. Wave optics propagation code for multiconjugate adaptive optics // Proc. SPIE. 2002. V. 4494. P. 104–120.
33. Shanin O.I. Adaptivnye opticheskie sistemy korrekcii naklonov. Rezonansnaja adaptivnaja optika. M.: Tehnosfera, 2013. 296 p.