基于残差神经网络的激光转塔气动光学效应快速预测  

Rapid Prediction of Aero-optical Effects of Laser Turret Based on Residual Neural Networks

作　　者：陈周纬宇 任翔 张飞舟[2] 名谷同祥 CHEN Zhouweiyu;REN Xiang;ZHANG Feizhou;GU Tongxiang(Graduate School of China Academy of Engineering Physics,Beijing 100088,China;Institute of Applied Physics and Computational Mathematics,Beijing 100094,China)

机构地区：[1]中国工程物理研究院研究生院,北京100088 [2]北京应用物理与计算数学研究所,北京100094

出　　处：《计算物理》2025年第2期160-170,共11页Chinese Journal of Computational Physics

基　　金：国家自然科学基金(12302295)资助。

摘　　要：采用残差神经网络对来流Ma∞在0.3~0.8范围内球柱型激光转塔模型的稳态流场开展机器学习,建立此范围内任意来流条件下的亚声速/跨声速流场预测,并针对不同视场角下的光束波前畸变评估此模型的预估精度。学习模型可再现转塔流动中的边界层、流动分离以及分离剪切层等流动特征,尤其包括跨声速流动中的非锚定激波间断现象。基于预测流场计算的不同视场角下的波前分布与根据传统计算流体力学(CFD)模拟流场的结果基本一致。该机器学习方法为工程领域中激光转塔气动光学效应自适应校正提供了策略。The residual neural network is used to carry out machine learning on the steady-state flow field of the hemisphere-on-cylinder laser turret model in the range of Ma=0.3~0.8,and the subsonic/transonic flow field under any incoming flow conditions in this range is established.The prediction accuracy of this model is evaluated for beam wavefront distortion under different view-of-field angles.The learning model reproduces flow characteristics such as boundary layers,flow separation,and separated shear layers in turret flows,including in particular unanchored shock discontinuities in transonic flow.The wavefront distribution based on the predicted flow field under different viewing angles is basically consistent with that calculated based on the flow field of CFD.This machine learning method provides a strategy for adaptive correction of laser turret aero-optical effects in the engineering field.

关 键 词：激光转塔 气动光学效应 跨声速流动 机器学习 残差神经网络 

分 类 号：O43[机械工程—光学工程]