基于神经网络的翼盒结构响应重构方法应用  

Application of response reconstruction method of wing box structure based on neural network

作　　者：王显浩 程伟[1] 杨云熙 王鹏辉[2] 周畅 WANG Xianhao;CHENG Wei;YANG Yunxi;WANG Penghui;ZHOU Chang(School of Aeronautical Science and Engineering,Beihang University,Beijing 100191,China;Beijing Institute of Structure and Environment Engineering,China Academy of Launch Vehicle Technology,Beijing 100076,China)

机构地区：[1]北京航空航天大学航空科学与工程学院,北京100191 [2]中国运载火箭技术研究院北京强度环境研究所,北京100076

出　　处：《航空工程进展》2023年第5期61-69,共9页Advances in Aeronautical Science and Engineering

摘　　要：翼盒结构复杂,航行中承载条件恶劣,利用有限测点信息重构其他位置响应对于实时健康监测具有现实意义。通过误差反向传播神经网络训练得到响应之间的非线性关系,建立基于神经网络的响应重构方法,开展有限元分析对其进行数值仿真验证,并将该方法应用于实测随机激励环境下翼盒典型承力结构的响应重构及损伤定位与判断分析。结果表明:采用该方法预测响应功率谱密度的均方根相对误差不超过1.90 dB,主要频点误差小于10%;判断出翼盒关键测点e的损伤或故障发生在所截取片段数据3 s后,其故障特征频率为240 Hz左右,该方法应用于响应重构预测及健康监测分析具有可行性。It is of great practical significance for real-time health monitoring to reconstruct other position responses by using limited measuring point information of wing box structure in complex navigation with harsh bearing condi⁃tions.The nonlinear relationship between the responses is obtained by training the back propagation neural net⁃work,and the response reconstruction method based on neural network is established and verified by numerical sim⁃ulation through finite element analysis.The method is applied to the response reconstruction,damage location and judgment analysis of typical load-bearing structures of wing boxes under measured random excitation environment.The results show that the root mean square relative error of the predicted response power spectral density recon⁃structed by this method is less than 1.90 dB and the main frequency error is less than 10%.The damage or fault of the key measuring point e of the wing box occurred 3 s after the intercepted fragment data,and its fault characteris⁃tic frequency is about 240 Hz.The method is feasible to response reconstruction prediction and health monitoring analysis.

关 键 词：神经网络 翼盒 随机振动 响应重构 健康监测 

分 类 号：V214.1[航空宇航科学与技术—航空宇航推进理论与工程]