Skip to main content

Advertisement

SpringerLink
Log in

Machine learning-based crashworthiness optimization for the square cone energy-absorbing structure of the subway vehicle

  • Industrial Application Paper
  • Published:
Structural and Multidisciplinary Optimization Aims and scope Submit manuscript

Abstract

This paper presents a novel framework for predicting the crashworthiness of a square cone energy-absorbing (SCEA) structure using a machine-learning method. The structure consists of an anti-creep, a thin-walled structure with nonuniform thickness, diaphragms, two types of aluminum honeycombs and a guide rail. The finite element model of SCEA structure was established and validated by full-scale experimental test. Taking the thicknesses of thin walls (TA and TB) and diaphragms (Tgb), strengths of honeycombs (δA and δB) as parametric variables, the parameters of SCEA structure were changed based on a virtual design of experiments (DOE) to generate training data and test data. To improve the crashworthiness of SCEA structure, the structural parameters were employed as input data, four machine learning models were utilized to predict the energy-absorbing characteristic curve of the SCEA structure, and the prediction accuracy of different models was compared and analyzed. According to the results of comparison, the Gate Recurrent Unit (GRU) model was chosen to predict the structural energy-absorbing characteristics, also employed as the input of optimization. The energy absorption (EA) and initial peak crushing force (PCF) were adopted as objectives, and the global response surface method (GRSM) was employed as the optimization algorithm. The results showed that the optimal solution was obtained as PCF = 618.41 kN and EA = 297.99 kJ when TA = 2.1 mm, TB = 2.9 mm, Tgb = 2.4 mm, δA = 5.99 MPa and δB = 4.82 MPa. The machine learning method offers engineers and scientists a potential tool to accelerate the design and optimization of SCEA structures for rail vehicles.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18

Similar content being viewed by others

References

  • Altin M, Guler MA, Mert SK (2017) The effect of percent foam fill ratio on the energy absorption capacity of axially compressed thin-walled multi-cell square and circular tubes. Int J Mech Sci 131:368–379

    Google Scholar 

  • Ambrósio J, Carvalho M, Milho J, Escalante S, Martín R (2021) A validated railway vehicle interior layout with multibody dummies and finite element seats models for crash analysis. Multibody Syst Dyn 54(2):179–212

    MathSciNet  MATH  Google Scholar 

  • ASME RT-2-2014 (2014) Safety standard for structural requirements for heavy rail transit vehicles. The American Society of Mechanical Engineers

  • Baharudin ME, Rouvinen A, Korkealaakso P, Mikkola A (2014) Real-time multibody application for tree harvester truck simulator. Proc Inst Mech Eng K 228(2):182–198

    Google Scholar 

  • Baykasoglu C, Sunbuloglu E, Bozdag SE, Aruk F, Toprak T, Mugan A (2011) Railroad passenger car collision analysis and modifications for improved crashworthiness. Int J Crashworthiness 16(3):319–329

    Google Scholar 

  • Bengio Y, Simard P, Frasconi P (1994) Learning long-term dependencies with gradient descent is difficult. IEEE Trans Neural Netw 5:157–166

    Google Scholar 

  • Chen TT, Zhang Y, Lin JM, Lu Y (2019) Theoretical analysis and crashworthiness optimization of hybrid multi-cell structures. Thin-Walled Struct 142:116–131

    Google Scholar 

  • Dehnaw AM, Manie YC, Chen YY, Chiu PH, Huang HW, Chen GW, Peng PC (2020) Design reliable bus structure distributed fiber Bragg grating sensor network using gated recurrent unit network. Sensors 20(24):7355

    Google Scholar 

  • Duddeck F, Hunkeler S, Lozano P, Wehrle E, Zeng D (2016) Topology optimization for crashworthiness of thin-walled structures under axial impact using hybrid cellular automata. Struct Multidisc Optim 54(3):415–428

    Google Scholar 

  • EN15227:2020 (2020) Railway applications—crashworthiness requirements for rail vehicles. European Committee for Standardization, London

    Google Scholar 

  • Gallardo-Antolin A, Montero JM (2021) Detecting deception from gaze and speech using a multimodal attention LSTM-based framework. Appl Sci 11(14):6393

    Google Scholar 

  • Graves A, Mohamed AR, Hinton G (2013) Speech recognition with deep recurrent neural networks. In: IEEE international conference on acoustics, speech and signal processing, Canada, 26–31. pp 6645–6649

  • Greff K, Srivastava RK, Koutnik J, Steunebrink BR, Schmidhuber J (2017) LSTM: a search space odyssey. IEEE Trans Neural Netw Learn Syst 28(10):2222–2232

    MathSciNet  Google Scholar 

  • Guan WY, Gao GJ, Li J, Yu Y (2018) Crushing analysis and multi-objective optimization of a cutting aluminium tube absorber for railway vehicles under quasi-static loading. Thin-Walled Struct 123:395–408

    Google Scholar 

  • Guan WY, Gao GJ, Yu Y, Zhuo TY (2020) Crashworthiness analysis and multi-objective optimization of expanding circular tube energy absorbers with cylindrical anti-clamber under eccentric loading for subway vehicles. Struct Multidisc Optim 61(4):1711–1729

    Google Scholar 

  • Haghshenas M, Wood JT, Klassen RJ (2012) Investigation of strain-hardening rate on splined mandrel flow forming of 5052 and 6061 aluminum alloys. Mater Sci Eng 532:287–294

    Google Scholar 

  • Hengstler M, Enkel E, Duelli S (2015) Applied artificial intelligence and trust—the case of autonomous vehicles and medical assistance devices. Technol Forecast Soc Change 105:105–120

    Google Scholar 

  • Hochreiter JS (1997) Long short-term memory. Neural Comput 9(8):1735–1780

    Google Scholar 

  • Hong W, Fan H, Xia Z, Jin F, Zhou Q, Fang D (2014) Axial crushing behaviors of multi-cell tubes with triangular lattices. Int J Impact Eng 63:106–117

    Google Scholar 

  • Islam A, Chang K (2021) Real-time AI-based informational decision-making support system utilizing dynamic text sources. Appl Sci 11(13):6237

    Google Scholar 

  • Jacobsen K, Tyrell D, Perlman B (2004) Impact test of a crash-energy management passenger rail car. In: ASME/IEEE joint rail conference. Baltimore, pp 19–26

  • Jang HJ, Shin KB, Han SH (2012) Numerical study on crashworthiness assessment and improvement of composite carbody structures of tilting train using hybrid finite element model. Adv Compos Mater 21(5–6):371–388

    Google Scholar 

  • Jung J, Yoon K, Lee PS (2020) Deep learned finite elements. Comput Methods Appl Mech Eng 372(1):113401

    MathSciNet  MATH  Google Scholar 

  • Kang H, Kim J (2020) Damage mitigation of a steel column subjected to automobile collision using a honeycomb panel. J Perform Constr Facil 34(1):04019107

    MathSciNet  Google Scholar 

  • Kingma DP, Ba J (2014) Adam: A method for stochastic optimization. arXiv, 1412.6980

  • Kohar CP, Connolly DS, Liusko T, Inal K (2020) Using artificial intelligence to aid vehicle lightweighting in crashworthiness with aluminum. In: 17th international conference on aluminium alloys. Grenoble, France, p 01006

  • Kohar CP, Greve L, Eller TK, Connolly DS, Inal K (2021) A machine learning framework for accelerating the design process using CAE simulations: an application to finite element analysis in structural crashworthiness. Comput Methods Appl Mech Eng 385:114008

    MathSciNet  MATH  Google Scholar 

  • Levenberg K (1944) A method for the solution of certain non-linear problems in least squares. Q Appl Math 2(2):164–168

    MathSciNet  MATH  Google Scholar 

  • Li GY, Zhang ZS, Sun GY, Xu FX, Huang XD (2014) Crushing analysis and multi-objective optimization for functionally graded foam-filled tubes under multiple load cases. Int J Mech Sci 89:439–452

    Google Scholar 

  • Li ZB, Chen R, Lu FY (2018) Comparative analysis of crashworthiness of empty and foam-filled thin-walled tubes. Thin-Walled Struct 124:343–349

    Google Scholar 

  • Liu Q, Xy Xu, Ma JB, Wang JS, Shi Y, Hui D (2017) Lateral crushing and bending responses of CFRP square tube filled with aluminum honeycomb. Composites B 118:104–115

    Google Scholar 

  • Mahjoub S, Chrifi-Alaoui L, Marhic B, Delahoche L (2022) Predicting energy consumption using LSTM, multi-layer GRU and Drop-GRU neural networks. Sensors 22(11):4062

    Google Scholar 

  • Marquardt D (1963) An algorithm for least-squared estimation of non linear parameters. J Soc Ind Appl Math 11(2):431–441

    MATH  Google Scholar 

  • Meiring GAM, Myburgh HC (2015) A review of intelligent driving style analysis systems and related artificial intelligence algorithms. Sensors 15(12):30653–30682

    Google Scholar 

  • Pandya KS, Roth CC, Mohr D (2020) Strain rate and temperature dependent fracture of aluminum alloy 7075: experiments and neural network modeling. Int J Plast 135(5):102788

    Google Scholar 

  • Pang T, Zheng G, Fang JG, Dong R, Sun GY (2019) Energy absorption mechanism of axially-varying thickness (AVT) multicell thin-walled structures under out-of-plane loading. Eng Struct 196:109130

    Google Scholar 

  • Peng Y, Deng WY, Xu P, Yao SG (2015) Study on the collision performance of a composite energy-absorbing structure for subway vehicles. Thin-Walled Struct 94:663–672

    Google Scholar 

  • Peng Y, Wang SM, Yao S, Xu P (2017) Crashworthiness analysis and optimization of a cutting-style energy absorbing structure for subway vehicles. Thin-Walled Struct 120:225–235

    Google Scholar 

  • Rad MA, Khalkhali A (2018) Crashworthiness multi-objective optimization of the thin-walled tubes under probabilistic 3D oblique load. Mater Des 156:538–557

    Google Scholar 

  • Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323(6088):533–536

  • Sak H, Senior A, Beaufays F (2014) Long short-term memory recurrent neural network architectures for large scale acoustic modeling. In: Proceedings of the annual conference of the International Speech Communication Association, 14–18. Singapore, pp 338–342

  • Song XG, Sun GY, Li GY, Gao WZ, Li Q (2012) Crashworthiness optimization of foam-filled tapered thin-walled structure using multiple surrogate models. Struct Multidisc Optim 47(2):221–231

    MathSciNet  MATH  Google Scholar 

  • Sun FF, Lai CL, Fan HL (2016a) In-plane compression behavior and energy absorption of hierarchical triangular lattice structures. Mater Des 100:280–290

    Google Scholar 

  • Sun FF, Lai CL, Fan HL, Fang DN (2016b) Crushing mechanism of hierarchical lattice structure. Mech Mater 97:164–183

    Google Scholar 

  • Sun GY, Chen DD, Wang HX, Hazell PJ, Li Q (2018a) High-velocity impact behaviour of aluminium honeycomb sandwich panels with different structural configurations. Int J Impact Eng 122:119–136

    Google Scholar 

  • Sun GY, Li SF, Li GY, Li Q (2018b) On crashing behaviors of aluminium/CFRP tubes subjected to axial and oblique loading: an experimental study. Composites B 145:47–56

    Google Scholar 

  • Tao Q, Liu F, Li Y, Sidorov D (2019) Air pollution forecasting using a deep learning model based on 1D convnets and bidirectional GRU. IEEE Access 7:76690–76698

    Google Scholar 

  • Tyrell D, Severson K, Perlman AB (2000) Rail passenger equipment crashworthiness testing requirements and implementation. Rail Transp 19:67–76

  • Vinayagar K, Kumar AS (2017) Crashworthiness analysis of double section bi-tubular thin-walled structures. Thin-Walled Struct 112:184–193

    Google Scholar 

  • Wang WB, Ren LH, Zhou HC, Hecht M (2012) Energy absorption configuration of crashworthy metro train. Adv Mater Res 466:724–728

    Google Scholar 

  • Wang ZG, Tian HQ, Lu ZJ, Zhou W (2014) High-speed axial impact of aluminum honeycomb—experiments and simulations. Composites B 56:1–8

  • Wang ZG, Li ZD, Xiong WW (2019) Numerical study on three-point bending behavior of honeycomb sandwich with ceramic tile. Composites B 167:63–70

    Google Scholar 

  • Wang C, Xu LY, Fan JS (2020) A general deep learning framework for history-dependent response prediction based on UA-Seq2Seq model. Comput Methods Appl Mech Eng 372:113357

    MathSciNet  MATH  Google Scholar 

  • Wei L, Zhang LL, Tong X, Cui K (2021) Crashworthiness study of a subway vehicle collision accident based on finite-element methods. Int J Crashworthiness 26(2):159–170

    Google Scholar 

  • Wierzbicki TA (1983) On the crushing mechanics of thin-walled structures. J Appl Mech 50(4a):727–734

    MATH  Google Scholar 

  • Wu SY, Sun GY, Wu X, Li GY, Li Q (2017) Crashworthiness analysis and optimization of Fourier varying section tubes. Int J Non-Linear Mech 92:41–58

    Google Scholar 

  • Xiao YY, Yin HF, Fang HB, Wen GL (2016) Crashworthiness design of horsetail-bionic thin-walled structures under axial dynamic loading. Int J Mech Mater Des 12(4):563–576

    Google Scholar 

  • Xie SC, Zhou H (2014) Multi-objective optimisation of a vehicle energy absorption structure based on surrogate model. J Cent South Univ 21(6):2539–2546

    Google Scholar 

  • Xu P, Yang CX, Peng Y, Yao SG, Xing J, Li BH (2016) Cut-out grooves optimization to improve crashworthiness of a gradual energy-absorbing structure for subway vehicles. Mater Des 103:132–143

    Google Scholar 

  • Xu P, Lu S, Yan KB, Yao SG (2019) Energy absorption design study of subway vehicles based on a scaled equivalent model test. Proc Inst Mech Eng F 233(1):3–15

    Google Scholar 

  • Xu JM, Wang J, Wang P, Chen JY, Gao Y, Chen R, Xie KZ (2020) Study on the derailment behaviour of a railway wheelset with solid axles in a railway turnout. Veh Syst Dyn 58(1):123–143

    Google Scholar 

  • Yang CX, Xu P, Yao SG, Xie SC, Li QM, Peng Y (2018) Optimization of honeycomb strength assignment for a composite energy-absorbing structure. Thin-Walled Struct 127:741–755

    Google Scholar 

  • Yang CX, Meng K, Yang LT, Guo WN, Xu P, Zhou ST (2023) Transfer learning-based crashworthiness prediction for the composite structure of a subway vehicle. Int J Mech Sci. https://doi.org/10.1016/j.ijmecsci.2023.108244

    Article  Google Scholar 

  • Yao SG, Yan KB, Lu SS, Xu P (2018a) Prediction and application of energy absorption characteristics of thin-walled circular tubes based on dimensional analysis. Thin-Walled Struct 130:505–519

    Google Scholar 

  • Yao SG, Li ZX, Yan JL, Xu P, Peng Y (2018b) Analysis and parameters optimization of an expanding energy-absorbing structure for a rail vehicle coupler. Thin-Walled Struct 125:129–139

    Google Scholar 

  • Yao SG, Yan KB, Lu SS, Xu P (2019) Equivalence study involving rail vehicle collision test conditions. Proc Inst Mech Eng F 233(1):73–89

    Google Scholar 

  • Yin HF, Wen GL, Liu ZB, Qing QX (2014) Crashworthiness optimization design for foam-filled multi-cell thin-walled structures. Thin-Walled Struct 75:8–17

    Google Scholar 

  • Zarzycki K, Lawrynczuk M (2021) LSTM and GRU neural networks as models of dynamical processes used in predictive control: a comparison of models developed for two chemical reactors sensors. Sensors 21(16):5625

    Google Scholar 

  • Zhang ZH, Liu ST, Tang ZL (2009) Crashworthiness investigation of kagome honeycomb sandwich cylindrical column under axial crushing loads. Thin-Walled Struct 48(1):9–18

    Google Scholar 

  • Zhang Y, Xu X, Wang J, Tt C, Wang CH (2019) Crushing analysis for novel bio-inspired hierarchical circular structures subjected to axial load. Int J Mech Sci 140:407–431

    Google Scholar 

  • Zhao R, Wang DZ, Yan RQ, Mao KZ, Shen F, Wang JJ (2018) Machine health monitoring using local feature-based gated recurrent unit networks. IEEE Trans Ind Electron 65(2):1539–1548

    Google Scholar 

  • Zhou H, Xu P, Xie SC (2017) Composite energy-absorbing structures combining thin-walled metal and honeycomb structures. Proc Inst Mech Eng F 231(4):394–405

    Google Scholar 

Download references

Acknowledgements

The authors would like to acknowledge the financial support from the Hunan Provincial Natural Science Foundation of China (No. 2022JJ40619, 2023JJ20074), the Fundamental Research Funds for the Central Universities of Central South University (No. 512340040, 202044019), the Young Elite Scientists Sponsorship Program by CAST (No. 2022QNRC001), the Changsha Municipal Natural Science Foundation (No. kq2202102), the National Key Research and Development Program of China (No. 2021YFB3703801), and the open project of Key Laboratory of Conveyance and Equipment of Ministry of Education, East China Jiaotong University (No. KLCE2022-06).

Funding

The authors would like to acknowledge the financial support from the Hunan Provincial Natural Science Foundation of China (No. 2022JJ40619, 2023JJ20074), the Fundamental Research Funds for the Central Universities of Central South University (No. 512340040, 202044019), the Young Elite Scientists Sponsorship Program by CAST (No. 2022QNRC001), the Changsha Municipal Natural Science Foundation (No. kq2202102), the National Key Research and Development Program of China (No. 2021YFB3703801), and the open project of Key Laboratory of Conveyance and Equipment of Ministry of Education, East China Jiaotong University (No. KLCE2022-06).

Author information

Authors and Affiliations

  1. Key Laboratory for Track Traffic Safety of Ministry of Education, Central South University, Changsha, 410075, China

    Weinian Guo, Ping Xu, Chengxing Yang, Liting Yang & Shuguang Yao

  2. Joint International Research Laboratory of Key Technology for Rail Traffic Safety, Central South University, Changsha, 410075, China

    Weinian Guo, Ping Xu, Chengxing Yang, Liting Yang & Shuguang Yao

  3. National & Local Joint Engineering Research Center of Safety Technology for Rail Vehicle, Central South University, Changsha, 410075, China

    Weinian Guo, Ping Xu, Chengxing Yang, Liting Yang & Shuguang Yao

  4. Key Laboratory of Conveyance and Equipment of Ministry of Education, East China Jiaotong University, Nanchang, 330013, China

    Chengxing Yang

  5. China Academy of Railway Sciences Co., Ltd, CARS (Beijing) Railway Equipment Technology Co., Ltd, Beijing, 102202, China

    Jingpu Guo

Authors
  1. Weinian Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ping Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Chengxing Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jingpu Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Liting Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Shuguang Yao
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Chengxing Yang.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Replication of results

The data used to support the findings of this study are available from the corresponding author upon request.

Additional information

Responsible Editor: Axel Schumacher

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Guo, W., Xu, P., Yang, C. et al. Machine learning-based crashworthiness optimization for the square cone energy-absorbing structure of the subway vehicle. Struct Multidisc Optim 66, 182 (2023). https://doi.org/10.1007/s00158-023-03629-2

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s00158-023-03629-2

Keywords

Search

Navigation