摘要
飞机机体结构数字孪生技术通过高逼真度、动态更新的数字模型反映飞机机体全寿命周期力学响应及综合性能。为了提高结构响应预测精度,数字孪生模型通常采用多层级、精细化仿真技术,同时也带来了模型计算量和成本大幅增加的问题,难以满足飞行中对飞机结构强度性能实时预测的需求。基于人工智能的结构强度性能降阶预测是解决飞行中结构响应实时预测的关键技术手段,基于高阶数字孪生模型仿真结果,通过飞行参数、应变等实测数据信息推断的结构载荷,能够快速对飞机结构力学响应进行高精度预测,可以解决实际飞行中飞机结构性能预测的时效性问题,在飞机数字孪生技术领域已得到越来越多的重视。提出一种将结构云图与载荷输入进行像素化处理的方法以表现点云数据间的空间关系,并结合引入了跨层连接机制的卷积神经网络,构造一种以载荷为输入的力学响应智能预测方法。基于329种工况的机翼结构数值试验的结果表明:像素化处理方法能够在保留机体结构响应特征的同时使数据适配卷积等面向像素图的数据处理方式。采用的残差神经网络模型较传统卷积神经网络在预测损失与精度上均有提升,提出的智能预测方法较传统仿真可实现近2个数量级以上的效率提升,预测应力分布与有限元仿真应力分布间相似度较高,具备在机体结构数字孪生中的应用价值。
Digital twin technology for aircraft structures reflects the mechanical response and comprehensive perfor-mance of an aircraft's lifecycle through high-fidelity and dynamically updated digital models.To improve the accuracy of structural response predictions,digital twin models often use multi-level,refined simulation techniques.However,this leads to a significant increase in model computation amount and cost,making it challenging to meet the real-time prediction needs for aircraft structural strength during flight.AI-based reduced-order prediction of structural strength is a key technology for real-time prediction of structural responses during flight.By combining high-order digital twin model simulation results with structural loads inferred from actual flight data such as flight parameters and strain,it is possible to rapidly and accurately predict the mechanical response of aircraft structures.This addresses the timeliness issue of aircraft structural performance prediction during actual flights,and has gained increasing attention in the field of aircraft digital twin technology.This paper proposes a method for pixelating structural cloud maps and load inputs to express spatial relationships between point cloud data.To construct an intelligent prediction method for mechanical responses Based on load inputs,a convolutional neural network with cross-layer connection mechanisms is also introduced.Re-sults from numerical experiments on the wing structure under 329 conditions show that the pixelation method can re-tain structural response characteristics,while making the data compatible with pixel-based data processing methods like convolution.Compared to traditional convolutional neural networks,the proposed residual neural network model achieves improved prediction accuracy and reduced loss.Additionally,this intelligent method achieves more than two orders of magnitude efficiency improvement compared to traditional simulations.The predicted stress distribution shows a high similarity to finite element simulation stress distributions,highlighting its application value in the digital twin of aircraft structures.
作者
张音旋
张起
许镇勇
孟琳书
ZHANG Yinxuan;ZHANG Qi;XU Zhenyong;MENG Linshu(AVIC Shenyang Aircraft Design and Research Institute,Shenyang 110035,China;Key Laboratory of Digital Twin for Aircraft Structural Strength of Liaoning Province,Shenyang 110035,China)
出处
《航空学报》
北大核心
2025年第19期178-188,共11页
Acta Aeronautica et Astronautica Sinica
基金
国防基础科研计划(JCKY2019205A006,JCKY2021205B003)。
关键词
数字孪生
残差神经网络
卷积神经网络
智能预测
实时预测
digital twin
residual neural network
convolutional neural network
intelligent prediction
real-time prediction
