基于神经网络的自适应光学系统变形镜控制电压预测方法

介绍了在校正大气湍流畸变波前像差的自适应光学系统中,基于神经网络技术对变形镜控制电压进行预测以减少自适应光学系统中时间延迟误差的方法。对受横向风影响的大气湍流畸变波前数据,利用数值仿真方法,研究了基于二阶学习算法的二层反向传播(BP)神经网络对自适应光学系统变形镜控制电压进行超前预测的方法,讨论了回溯帧数及学习速率对预测效果的影响,并与采用最小递归二乘(RLS)算法预测时的效果进行了比较。对比结果表明,基于二阶学习算法的二层BP神经网络预测方法比基于RLS算法的预测方法能更有效地降低系统由伺服延迟引起的误差。

Abstract

To reduce the servo lag error in adaptive optics to correct the atmosphere turbulence distortion,a kind of neural network prediction algorithm to predict the control voltage of deformable mirror is proposed. The two-layer back propagation neural network prediction method with second-order learning algorithm used to predict the voltage of deformable mirror in advance is studied through numerical simulation,based on the atmospheric turbulence wavefront data influenced by transversal wind. The look-back frame and learning-rate parameter influencing the prediction effect is discussed. The residual error of the adaptive optic system is calculated with neural network prediction algorithm and recursive least-square (RLS) algorithm. The results show that the residual error caused by servo lag in the system is reduced more effectively using the neural network prediction algorithm than using the RLS prediction algorithm.

参考文献

[1] 李新阳,姜文汉.自适应光学控制系统的有效带宽分析[J]. 光学学报,1997,17(12):1697-1702

Li Xinyang,Jiang Wenhan. Effective bandwidth analysis of adaptive optics control system[J]. Acta Optica Sinica,1997,17(12):1697-1702

[2] 李新阳,姜文汉.自适应光学系统的控制残余方差分析[J]. 光学学报,2000,20(10):1328-1334

Li Xinyang,Jiang Wenhan. Analysis of the residual servo variance for an adaptive optics system[J]. Acta Optica Sinica,2000,20(10):1328-1334

[3] George J. M. Aitken,Deiphine Rossille,Donald R. McGaughey. Predictability of fractional-Brownian-motion wave-front distortions and some implications for closed-loop adaptive optics control[C]. SPIE,1998,3353:1060-1069

[4] . Jorgenson,George J. M. Aitken. Prediction of atmospherically induced wave-front degradations[J]. Opt. Lett., 1992, 17(7): 466-468.

[5] M. B. Jorgenson,G. J. M. Aitken. Neural network prediction of turbulence induced wave-front degradations with applications to adaptive optics[C]. SPIE,1992,1706:113-121

[6] . Montera,Byron M. Welsh,Michael C. Roggemann et al.. Use of artificial neural networks for Hartmann-sensor lenslet centroid estimation[J]. Appl. Opt., 1996, 35(29): 5747-5757.

[7] . Montera,Byron M. Welsh,Michael C. Roggemann et al.. Prediction of wavefront-sensor slope measurements with artificial neural networks[J]. Appl. Opt., 1997, 36(3): 675-681.

[8] Patrick C. McGuire1,Troy A. Rhoadarmer,Hanna Coy et al.. Linear zonal atmospheric prediction for adaptive optics[C]. SPIE,2000,4007:682-691

[9] Michael Lloyd-Hart,Patrick McGuire. Spatlo-temporal prediction for adaptive optics wavefront reconstructors[C]. Adaptive Optics Topical Mtg. ＆ Tabletop Exhibit,Technieai Universlty of Munich,Garching,Germany,1995

[10] 张秀娟,李新阳,张慧敏.利用复原电压预测大气湍流畸变波前方法[J]. 强激光与粒子束,2006,18(5):757-760

Zhang Xiujuan,Li Xinyang,Zhang Huiming. Prediction algorithm for atmosphere turbulence with control voltage of deformable mirror[J]. High Power Laser and Particle Beams,2006,18(5):757-760

[11] 李新阳,王春红,鲜浩等.自适应光学系统的实时模式复原算法[J]. 强激光与粒子束,2002,14(1):53-56

Li Xinyang,Wang Chunhong,Xian Hao et al.. Real-time modal reconstruction algorithm in adaptive optics[J]. High Power Laser and Particle Beams,2002,14(1):53-56

[12] 李新阳,姜文汉,王春红等.自适应光学系统中的自适应控制算法研究[J]. 光学学报,2001,21(3):283-289

Li Xinyang,Jiang Wenhan,Wang Chunhong et al.. Real-time adaptive control algorithm in adaptive optics system[J]. Acta Optica Sinica,2001,21(3):283-289

[13] 王永骥,涂健.神经元网络控制[M]. 北京:机械工业出版社,1998. 32-43

Wang Yongji,Tu Jian. Neural network control[M]. Beijing:China Machine Press,1998. 32-43

颜召军, 李新阳. 基于神经网络的自适应光学系统变形镜控制电压预测方法[J]. 光学学报, 2010, 30(4): 911. Yan Zhaojun, Li Xinyang. Neural Network Prediction Algorithm for Control Voltage of Deformable Mirror in Adaptive Optical System[J]. Acta Optica Sinica, 2010, 30(4): 911.

基于神经网络的自适应光学系统变形镜控制电压预测方法

关于本站 Cookie 的使用提示

全站搜索

基于神经网络的自适应光学系统变形镜控制电压预测方法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索