基于Transformer结构的高精度湍流波前重构  

High-precision turbulence wavefront reconstruction based on Transformer structure

作　　者：冯佳濠 胡启立 姜律 杨燕燕 华晟骁 吴晶晶 胡立发[1,2] FENG Jia-hao;HU Qi-li;JIANG Lü;YANG Yan-yan;HUA Sheng-xiao;WU Jing-jing;HU Li-fa(College of Science,Jiangnan University,Wuxi 214122,China;Jiangsu Provincial Research Center of Light Industry Optoelectronic Engineering and Technology,Wuxi 214122,China;Key Laboratory of Electro-Optical Countermeasure Test&Evaluation Technology,Luoyang 471003,China)

机构地区：[1]江南大学理学院,江苏无锡214122 [2]江苏省轻工光电工程技术研究中心,江苏无锡214122 [3]光电对抗测试评估技术重点实验室,河南洛阳471003

出　　处：《液晶与显示》2023年第6期798-808,共11页Chinese Journal of Liquid Crystals and Displays

基　　金：国家自然科学基金(No.61475152);光电对抗测试与评估技术重点实验室基金(No.GKCP2021001);江苏省轻工业光电工程技术研究中心项目(No.BM2014402)。

摘　　要：动态变化的大气湍流和观测目标的亮度的降低严重影响了夏克-哈特曼波前传感器(SHWFS)探测波前的精度。针对这两种复杂的观测条件,本文提出了一种以Transformer结构为基础的神经网络模型,它具有很好的全局建模能力,可以高精度地从SHWFS光斑阵列图像中重建波前。通过在动态变化的典型大气湍流相干长度r_(0)下进行仿真模拟,所提出的网络模型的残余波前RMS误差值稳定在0.010~0.024μm之间。与已有的方法相比,本文方法能够更准确地重构波前像差。此外,本文方法的重构精度受导星或观测目标的亮度变化影响很小。因此,本文方法的重构精度对两种观测条件变化均具有较强的稳定性,为大口径天文光学望远镜的高分辨率成像提供了一种有前景的方法。The dynamically changing atmospheric turbulence and the reduced brightness of the observed target severely affect the accuracy of the Shack-Hartmann wavefront sensor(SHWFS)to detect wavefronts.Under these two complicated observational conditions,this paper proposes a neural network model based on Transformer structure,which has excellent global modelling capabilities and could reconstruct wavefronts from light spot array images from SHWFS with high accuracy.The residual wavefront RMS error of the presented network model can be stabilized between 0.010μm and 0.024μm by simulating for dynamically varying typical atmospheric turbulence coherence length r_(0).Comparing with reported methods,the wavefront aberrations can be reconstructed more accurately.In addition,the reconstruction accuracy of the method is robust to the magnitude variation of guide stars or detection targets.Therefore,the reconstruction accuracy of this method has strong stability to the changes of two observation conditions,and provides a promising way for high-resolution imaging for large-aperture astronomical optical telescopes.

关 键 词：自适应光学 深度学习 Shack-Hartmann波前传感器 TRANSFORMER 波前重构 

分 类 号：TH74[机械工程—光学工程]