基于深度学习的主动光学校正算法研究  

Research on Active Optical Correction Algorithm Based on Deep Learning

作　　者：亢超 李文祥[1,2] 黄屾 管恒睿 赵金标 朱庆生[1,2,3] Kang Chao;Li Wenxiang;Huang Sheng;Guan Hengrui;Zhao Jinbiao;Zhu Qingsheng(CAS Nanjing Astronomical Instruments Research Center,Namjing,Jiangsu 210042,China;University of Science and Technology of China,Hefei,Anhui 230026,China;CAS Nanjing Astronomical Instruments Co.,LTD.,Nanjing,Jiangsu 210042,China)

机构地区：[1]中国科学院南京天文仪器研制中心,江苏南京210042 [2]中国科学技术大学,安徽合肥230026 [3]中国科学院南京天文仪器有限公司,江苏南京210042

出　　处：《光学学报》2021年第6期124-132,共9页Acta Optica Sinica

基　　金：国家自然科学基金(12003067);上海市星系与宇宙学半解析研究重点实验室开放课题(SKLA1901)。

摘　　要：主动光学是现代大型反射式光学望远镜领域的一项关键技术,能够有效减少像差,提升成像质量,然而,现有校正算法严重依赖系统的响应矩阵和物理参数;由于实际望远镜系统的误差具有一定的随机性和非线性,往往难以获得精确的响应矩阵和物理参数模型,从而导致校正精度不理想或者需要多次校正。针对这些问题,提出一种不依赖响应矩阵和物理参数模型的深度学习校准(DLCM)算法。该算法借助深度神经网络强大的预测和自学习能力,建立校正算法所需的动力学模型网络、策略网络和决策单元,只需要结合相应设备就可以让控制系统自动学习并自动优化,从而完成镜面校正工作。最后,使用ANSYS有限元仿真对DLCM算法进行验证,结果表明,本文算法能够快速精准地完成校正工作,并且,无论校准速度还是校准精度,均优于传统校准算法。Active optics is a key technology in the field of modern large reflective optical telescopes, which can effectively reduce the aberration and improve the imaging quality. The calibration algorithm depends heavily on the response matrix and physical parameters of the system. Due to the randomness and nonlinearity of the errors of the actual telescope system, the accurate response matrix and physical parameter model are often difficult to obtain, which leads to the unsatisfactory correction accuracy or the need for multiple corrections. To solve these problems, this paper proposes a deep learning calibration algorithm(DLCM) which does not depend on response matrix and physical parameter model. With the powerful prediction and self-learning ability of the deep neural network, this algorithm establishes the dynamic model network, strategy network, and decision-making unit needed by the correction algorithm. The control system can learn and optimize automatically by combining the corresponding equipment, so as to complete the mirror calibration work. Finally, using ANSYS finite element simulation to verify the DLCM algorithm, the results show that the proposed control algorithm can quickly and accurately complete the calibration work, and the calibration speed and accuracy are better than the traditional calibration algorithm.

关 键 词：成像系统 主动光学 深度学习 卷积神经网络 启发式搜索 进化策略 

分 类 号：TH751[机械工程—仪器科学与技术]