基于机器学习的汽车吸能结构耐撞性智能预测方法
作者:
作者单位:

1.同济大学 汽车学院,上海 201804;2.同济大学 软件学院,上海 201804

作者简介:

贺宏伟(1999—),男,硕士研究生,主要研究方向为汽车轻量化及机器学习在汽车上的应用。E-mail:2233517@tongji.edu.cn

通讯作者:

余海燕(1976—),女,教授,博士生导师,工学博士,主要研究方向为汽车轻量化。E-mail:yuhaiyan@tongji.edu.cn

中图分类号:

U463;TP181

基金项目:

国家重点研发计划项目(2022YFE0208000)


Machine Learning Method for Intelligent Prediction of the Crashworthiness of Automotive Energy Absorbing Boxes
Author:
Affiliation:

1.School of Automotive Studies, Tongji University, Shanghai 201804, China;2.School of Software, Tongji University, Shanghai 201804, China

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [41]
  • | | | |
  • 文章评论
    摘要:

    汽车零部件正向设计中,为快速预测所设计的吸能结构的碰撞吸能特性,以吸能盒为研究对象,通过有限元压溃变形仿真生成数据集,训练得到一种新的可识别几何结构和记忆时序特征的预测模型。模型通过基于图的编码器进行几何结构识别,采用长短期记忆网络和图卷积神经网络处理时序数据,并输出预测结果。对比表明:吸能盒压溃形态预测结果与有限元仿真结果一致,压溃变形量的预测精度可达95.33%,最大吸能值的预测精度可达99.98%。预测模型相较于有限元计算,其计算效率分别提高了174.5倍和210.5倍,可以快速准确地预测吸能盒的碰撞性能。

    Abstract:

    This study aims to achieve intelligent prediction of collision energy absorption characteristics of new structures in forward design of automotive parts. An energy-absorbing box is taken as the research object to generate training data sets by finite element crush deformation simulation. A graph-based encoder is adopted for geometric structure recognition. Long and short-term memory networks and graph convolutional neural networks were used to process adjacent temporal data. The novel neural network prediction system proposed can recognize geometric structures and memorize temporal data. The comparison between the model prediction results and simulation results shows that the predicted crush pattern of the energy-absorbing box is consistent with the finite element simulation results, and the prediction accuracy of the model for the crush deformation amount can reach up to 95.33%, while the prediction accuracy of the maximum energy absorption value can reach 99.98%. Compared with the finite element calculations, computational efficiency is 174.5 times and 210.5 times higher respectively, which manifested that the system can accurately and quickly predict the crash performance of the energy-absorbing box.

    参考文献
    [1] MARZBANRAD J, ALIJANPOUR M, KIASAT M S. Design and analysis of an automotive bumper beam in low-speed frontal crashes[J]. Thin-Walled Structures. 2009, 47(8/9):902.
    [2] BAIGES J, CODINA R, CASTA?AR I, et al. A finite element reduced‐order model based on adaptive mesh refinement and artificial neural networks[J]. International Journal for Numerical Methods in Engineering. 2019, 121(4):588.
    [3] MOHAN AT, GAITONDE D V. A deep learning based approach to reduced order modeling for turbulent flow control using LSTM neural networks[J]. arXiv preprint, 2018, arXiv:1804.09269.
    [4] ROY A G, CONJETI S, KARRI S P K, et al. ReLayNet: retinal layer and fluid segmentation of macular optical coherence tomography using fully convolutional networks[J]. Biomed Opt Express, 2017, 8(8):3627.
    [5] HERATH S, HAPUTHANTHRI U. Topologically optimal design and failure prediction using conditional generative adversarial networks[J]. International Journal for Numerical Methods in Engineering. 2021, 122(23):6867.
    [6] WANG L, SHI D, ZHANG B, et al. Real-time topology optimization based on deep learning for moving morphable components[J]. Automation in Construction. 2022, 142: 112.
    [7] LIANG L, LIU M, MARTIN C, et al. A deep learning approach to estimate stress distribution: a fast and accurate surrogate of finite-element analysis[J]. J R Soc Interface, 2018, 15(138). DOI: 10.1098/rsif.2017.0844.
    [8] ABUEIDDA D W, LU Q, KORIC S. Meshless physics‐informed deep learning method for three‐dimensional solid mechanics[J]. International Journal for Numerical Methods in Engineering. 2021, 122(23):7182.
    [9] TANDALE S B, MARKERT B, STOFFEL M. Intelligent stiffness computation for plate and beam structures by neural network enhanced finite element analysis[J]. International Journal for Numerical Methods in Engineering. 2022, 123(17):4001.
    [10] CHEN H, NIE Z, XU Q, et al. Intelligent detection and classification of surface defects on cold-rolled galvanized steel strips using a data-driven faulty model with attention mechanism[J]. Journal of Computing and Information Science in Engineering, 2022, 23(4): 041001.
    [11] XU W, WANG C, YUAN J. Impact performance of an annular shaped charge designed by convolutional neural networks[J]. Thin-Walled Structures, 2021,160(35): 107241.
    [12] SHAMASS R, FERREIRA F P V, LIMBACHIYA V, et al. Web-post buckling prediction resistance of steel beams with elliptically-based web openings using Artificial Neural Networks(ANN)[J]. Thin-Walled Structures, 2022, 180: 522.
    [13] OMAR T, ESKANDARIAN A, BEDEWI N. Vehicle crash modelling using recurrent neural networks[J]. Mathematical and Computer Modelling, 1998, 28(9): 31.
    [14] VAN DE WEG B P, GREVE L, ANDRES M, et al. Neural network-based surrogate model for a bifurcating structural fracture response[J]. Engineering Fracture Mechanics, 2021, 241(1). https://www.zhangqiaokeyan.com/journal-foreign-detail/0704028668404.html.
    [15] KOHAR C P, CONNOLLY D, LIUSKO T. et al. Using artificial intelligence to aid vehicle lightweighting in crashworthiness with aluminum[J]. MATEC Web of Conferences. 2020, 326(1): 01006.
    [16] LANZI L, BISAGNI C, RICCI S. Neural network systems to reproduce crash behavior of structural components[J]. Computers & Structures. 2004, 82(1):93.
    [17] GUO X X, LI W, IORIO F. Convolutional neural networks for steady flow approximation[C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2016: 481. https://www.kdd.org/kdd2016/papers/files/adp1175-guoA.pdf.
    [18] HE B, XU F, ZHANG D, et al. A convolutional neural network-based recognition method of gear performance degradation mode[J]. Journal of Computing and Information Science in Engineering. 2022, 22(5): 050902.
    [19] NIE Z G, JIANG H L, KARA L B. Stress field prediction in cantilevered structures using convolutional neural networks[J]. J Comput Inf Sci Eng, 2020, 20.
    [20] GUO Y L, WANG H Y, HU Q Y, et al. Deep learning for 3d point clouds: a survey [J]. Ieee T Pattern Anal, 2021, 43(12): 4338.
    [21] XIANG C, WANG D L, PAN Y, et al. Accelerated topology optimization design of 3D structures based on deep learning[J]. Struct Multidiscip O,2022, 65(3).
    [22] KOHAR C P, GREVE L, ELLER T K, et al. A machine learning framework for accelerating the design process using CAE simulations: an application to finite element analysis in structural crashworthiness[J]. Computer Methods in Applied Mechanics and Engineering, 2021, 385.
    [23] RAO C, LIU Y. Three-dimensional convolutional neural network (3D-CNN) for heterogeneous material homogenization[J]. arXiv preprint,2020, arXiv: 2002.07600.
    [24] LIU Z, TANG H, LIN Y, et al. Point-voxel CNN for efficient 3D deep learning[J]. arXiv preprint,2019, arXiv: 1907.03739.
    [25] ZHOU J, CUI G, HU S, et al. Graph neural networks: a review of methods and applications[J]. AI Open, 2020, 1:57.
    [26] JIN W, YANG K, BARZILAY R, et al. Learning multimodal graph-to-graph translation for molecular optimization[J]. arXiv preprint, 2028, arXiv: 1812.01070.
    [27] YU B, YIN H T, ZHU Z X. Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting[C]//Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence. 2018:3634.
    [28] MAURIZI M, GAO C, BERTO F. Predicting stress, strain and deformation fields in materials and structures with graph neural networks[J]. Scientific Reports, 2022, 12 (1).
    [29] PFAFF T, FORTUNATO M, SANCHEZ-GONZALEZ A, et al. Learning mesh-based simulation with graph networks[J]. arXiv preprint,2020, arXiv: 2010.03409.
    [30] WU F, JING X Y, WEI P F, et al. Semi-supervised multi-view graph convolutional networks with application to webpage classification[J]. Inform Sciences, 2022, 591:142.
    [31] GORI M, MONFARDINI G, SCARSELLI F. A new model for learning in graph domains[C]. Ieee Ijcnn, 2005:729.
    [32] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Comput, 1997, 9(8):1735.
    [33] WU Z H, PAN S R, LONG G D, et al. Connecting the dots: multivariate time series forecasting with graph neural networks[C]//Proceedings of the 26th Acm Sigkdd International Conference on Knowledge Discovery & Data Mining. 2020:753.
    [34] NUGRAHA R D, HE K, LIU A, et al. Short-term cross-sectional time-series wear prediction by deep learning approaches[J]. Journal of Computing and Information Science in Engineering, 2023, 23(2).
    [35] BAROUTAJI A, SAJJIA M, OLABI A G. On the crashworthiness performance of thin-walled energy absorbers: Recent advances and future developments[J]. Thin-Walled Structures, 2017, 118:137.
    [36] C-NCAP. C-NCAP management regulation[EB/OL]. 2018. https://cncap.obs.cn-north-4.myhuaweicloud.com/cms/picture/319721353147125760.pdf.
    [37] YAO S, YAN K, LU S, et al. Prediction and application of energy absorption characteristics of thin-walled circular tubes based on dimensional analysis[J]. Thin-Walled Structures, 2018, 130:505.
    [38] SINGH K, KAPANIA R K. Accelerated optimization of curvilinearly stiffened panels using deep learning[J]. Thin-Walled Structures, 2021, 161.
    [39] ZHANG Y, ZHU P, CHEN G L. Lightweight design of automotive front side rail based on robust optimisation[J]. Thin-Walled Structures, 2007, 45(7/8): 670.
    [40] ZHANG Y, XU X, SUN G Y, et al. Nondeterministic optimization of tapered sandwich column for crashworthiness[J]. Thin-Walled Structures, 2018, 122:193.
    [41] KINGMA D P, BA J. Adam: a method for stochastic optimization [J]. arXiv preprint, 2014, arXiv: 1412.6980.
    相似文献
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

贺宏伟,余海燕,高泽,饶卫雄.基于机器学习的汽车吸能结构耐撞性智能预测方法[J].同济大学学报(自然科学版),2024,52(S1):29~38

复制
分享
文章指标
  • 点击次数:19
  • 下载次数: 56
  • HTML阅读次数: 3
  • 引用次数: 0
历史
  • 收稿日期:2023-12-01
  • 在线发布日期: 2024-11-20
文章二维码