College of Aerospace Engineering,Shenyang Aerospace University,Shenyang 110136,China
Show less
文章历史+
Received
Accepted
Published
2024-11-06
2025-01-15
Issue Date
2026-01-26
PDF (1895K)
摘要
为了解决训练样本有限和极端环境条件下飞机结构强度分析的难题,提高分析效率,将深度迁移学习方法应用于RX4E电动飞机复合材料层合板的力学性能研究。基于复合材料层合板试验结果的分析,对比了多种深度学习模型对试验结果的预测,最终选定卷积-长短期记忆(convolutional long short-term memory,CLSTM)网络作为最优的深度学习模型。此外,还引入了迁移学习(transfer learning,TL)模型,以精确预测复合材料层合板在不同温度、湿度及铺层方式下的应力-应变关系。结果表明,提出的TL-CLSTM网络模型在预测复合材料的力学性能方面具有显著的优势,特别是在预测应力-应变关系方面,其均方误差和均方根误差分别为10-5和10-3。所提出的模型克服了传统力学性能测量方法的复杂性和低效性,能够有效地预测电动飞机复合材料层合板的力学性能,为电动飞机制造研究提供了新的途径。
Abstract
In order to address the challenges in structural strength analysis caused by limited training samples and extreme environmental conditions while improving analytical efficiency,deep transfer learning methods was applied to investigate the mechanical properties of composite laminates for the RX4E electric aircraft.Based on the analysis of experimental results obtained from composite laminates, multiple deep learning models were compared in terms of their ability to predict the experimental results. Finally, the convolutional long short-term memory (CLSTM) was selected as the optimal deep learning model. Furthermore, a transfer learning (TL) model was introduced to accurately predict the stress-strain relationships of composite laminates under varying temperatures, humidities and layup configurations. The results indicate that the proposed TL-CLSTM network model has exceptional capability in predicting the mechanical properties of composites, particularly in predicting the stress-strain relationship, with a mean squared error and a root-mean-square error of 10-5and 10-3 respectively.The proposed model can effectively predict the mechanical properties of composite laminates for electric aircraft, overcoming the complexities and inefficiencies of traditional mechanical properties measurement methods,which providing a novel pathway for the future study of electric aircraft manufacturing.
JiaZ A, LiT T, ChiangF P,et al.An experimental investigation of the temperature effect on the mechanics of carbon fiber reinforced polymer composites[J].Composites Science and Technology,2018,154:53-63.
[3]
MengJ X, WangY, YangH Y,et al.Mechanical properties and internal microdefects evolution of carbon fiber reinforced polymer composites:cryogenic temperature and thermocycling effects[J].Composites Science and Technology,2020,191(3):108083.
[4]
HoheJ, SchoberM, FliegenerS,et al.Effect of cryogenic environments on failure of carbon fiber reinforced composites[J].Composites Science and Technology,2021,212(18):108850.
[5]
OunA, AlajarmehO, ManaloA,et al.Durability of hybrid flax fibre-reinforced epoxy composites with graphene in hygrothermal environment[J].Construction and Building Materials,2024,420:135584.
[6]
ParkH J.Effects of stacking sequence and clam-ping force on the bearing strengths of mechanically fastened joints in composite laminates[J].Composite Structures,2001,53(2):213-221.
[7]
RadzuanN A M, SulongA B, VermaA,et al.Layup sequence and interfacial bonding of additively manufactured polymeric composite:a brief review[J].Nanotechnology Reviews,2021,10(1):1853-1872.
[8]
GennaS, TrovalusciF, TagliaferriV.Indentation test to study the moisture absorption effect on CFRP composite[J].Composites Part B:Enginee-ring,2017,124(5):1-8.
[9]
ZhangW, LiX, MaH,et al.Transfer learning using deep representation regularization in remai-ning useful life prediction across operating conditions[J].Reliability Engineering & System Safety,2021,211(7):107556.
WeiY P, WuD Z.Prediction of state of health and remaining useful life of lithium-ion battery using graph convolutional network with dual attention mechanisms[J].Reliability Engineering & System Safety,2023,230:108947.
[12]
LatifS D.Concrete compressive strength prediction modeling utilizing deep learning long short-term memory algorithm for a sustainable environment[J].Environmental Science and Pollution Research,2021,28(23):30294-30302.
[13]
XuZ W, LiuX M, ZhangK.Mechanical properties prediction for hot rolled alloy steel using convolutional neural network[J].IEEE Access,2019,7:47068-47078.
[14]
LiL F, ChenC Q.Equilibrium-based convolution neural networks for constitutive modeling of hype-relastic materials[J].Journal of the Mechanics and Physics of Solids,2022,164:104931.
[15]
WanS K, LiX H, ZhangY F,et al.Bearing remaining useful life prediction with convolutional long short-term memory fusion networks[J].Re-liability Engineering & System Safety,2022,224:108528.
AzadM M, KumarP, KimH S.Delamination detection in CFRP laminates using deep transfer learning with limited experimental data[J].Journal of Materials Research and Technology,2024,29:3024-3035.