Skip to main content
SpringerLink
Log in

Artificial neural network metamodeling-based design optimization of a continuous motorcyclists protection barrier system

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

Abstract

Longitudinal barriers are considered as passive safety systems designed to shield hazards located at roadsides against motor vehicle impacts. Since these barriers are manmade obstacles, they also pose a threat to drivers using the road. Recent motorcyclist accidents with longitudinal barriers have proven that a particular barrier successfully protecting vehicle occupants may wound or kill motorcyclists due to its components. For this reason, sharp and blunt edges in steel longitudinal barrier parts, such as posts are usually shielded against contact from unprotected motorcyclists during a high-speed impact event. In recent years, more longitudinal barriers have been designed with motorcyclists in mind and these motorcycle protection barriers have become wide spread especially on urban high-speed roads. However, since the development of these barriers are fairly new compared to conventional longitudinal barriers, there is limited guidance on their design criteria, such as thickness, geometry, connections. For this purpose, this paper intends to provide an artificial neural network metamodeling-based design optimization methodology to an existing continuous motorcycle protection barrier design to make it more competitive in terms of weight and thus, cost. As a result of this study, the optimized barrier has become 34% more economical compared to its original design while its protection level remained intact.

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
Fig. 19

Similar content being viewed by others

Abbreviations

ANN:

Artificial neural network

APE:

Absolute percentage error

ATD:

Anthropomorphic test device

CMPS:

Continuous motorcycle protection system

CEN/TS17342:

European norm of motorcycle road restraint systems

DOE:

Design of experiment

EN1317:

European norm of road restraint systems

EPS:

Expanded polystyrene foam

FEA:

Finite element analysis

FEM:

Finite element model

FFD:

Full-factorial design

GA:

Genetic algorithm

HIC:

Head injury criteria

LS-DYNA:

Livermore software open code 3D finite element program

MAPE:

Mean absolute percentage error

MASH:

Manual for assessing safety hardware

MPS:

Motorcyclist protection system

SBDO:

Simulation based design optimization

References

  • AASHTO MASH-1 (2009) Manual for assessing safety hardware (MASH), 1st edn. American Association of State Highway Transportation Officials, Washington, USA, Washington (DC)

    Google Scholar 

  • Al-Mahasneh AJ, Anavatti SG and Garratt MA (2018) The development of neural networks applications from perceptron to deep learning. International Conference on Advanced Mechatronics, Intelligent Manufacture, and Industrial Automation (ICAMIMIA), pp 1–6. https://doi.org/10.1109/ICAMIMIA.2017.8387619

  • Alrashydah EI, Abo-Qudais SA (2018) Modeling of creep compliance behavior in asphalt mixes using multiple regression and artificial neural networks. Constr Build Mater 159:635–641. https://doi.org/10.1016/j.conbuildmat.2017.10.132

    Article  Google Scholar 

  • Atahan AO (2002) Finite element simulation of a strong-post W-beam guardrail system. SIMULATION 78(10):587–599

    Article  Google Scholar 

  • Atahan AO (2003) Impact behaviour of G2 steel weak-post W-beam guardrail on nonlevel terrain. Int J Heavy Veh Syst 10(3):209–223

    Article  Google Scholar 

  • Atahan AO, Cansiz OF (2005a) Impact analysis of a vertical flared back bridge rail-to-guardrail transition structure using simulation. Finite Elem Anal Des 41:371–396

    Article  Google Scholar 

  • Atahan AO, Cansiz OF (2005b) Improvements to G4 (RW) strong-post round-wood, W beam guardrail system. J Transp Eng 131(1):63–73

    Article  Google Scholar 

  • Atahan AO, Arslan T (2012) Collision behaviour of double W-beam transition. Int J Heavy Veh Syst 19(1):76–91

    Article  Google Scholar 

  • Atahan AO, Erdem MM (2016) Evaluation of 12 m long turned down guardrail end terminal using full-scale crash testing and simulation. Lat Am J Solids Struct 13(16):3107–3125

    Article  Google Scholar 

  • Atahan AO, Yucel AO, Erdem MM (2014) Crash testing and evaluation of a new generation L1 containment level guardrail. Eng Fail Anal 38:25–37

    Article  Google Scholar 

  • Atahan AO, Hiekmann JM, Himpe J, Marra J (2018) Development of a continuous motorcycle protection barrier system using computer simulation and full-scale crash testing. Accid Anal Prev 116(2018):103–115

    Article  Google Scholar 

  • Bambach M, Grzebieta R (2014) Motorcycle crashes into roadside barriers stage 4: Protecting motorcyclists in collisions with roadside barriers. Research Report

  • Bektas E, Broermann K, Pećanac G, Rzepka S, Silber C, Wunderle B (2017) Robust design optimization: on methodology and short review. In: 2017 18th international conference on thermal, mechanical and multi-physics simulation and experiments in microelectronics and microsystems, EuroSimE, pp 1–7. https://doi.org/10.1109/EuroSimE.2017.7926290

  • Bosch van den H (2006) Crash helmet testing and design specifications. Technische Universiteit Eindhoven, Eindhoven. https://doi.org/10.6100/IR613094

    Book  Google Scholar 

  • Buth CE, Bullard DL, Menges WL (2006) NCHRP report 350 test 3–11 of the long-span guardrail with 5.7 m clear span and nested W-beams over 11.4 m. Report 405160-1-1. Texas Transportation Institute, College Station

  • Cansiz OF, Atahan AO (2006) Crash test simulation of a modified thrie-beam high containment level guardrail under NCHRP report 350 TL 4–12 conditions. Int J Heavy Veh Syst 13:2–18

    Article  Google Scholar 

  • CEN/TS 17342:2019. Road restraint systems. Motorcycle road restraint systems which reduce the impact severity of motorcyclist collisions with safety barriers. European Committee for Standardization

  • Committee on Guardrails and Guide Posts (1962) Proposed full-scale testing procedures for guardrails. Highway research correlation service circular 482. Highway Research Board, Washington (DC)

  • Consolazio GR, Chung JH, Gurley KR (2003) Impact simulation and full scale crash testing of a low profile concrete work zone barrier. Comput Struct 81:1359–1374

    Article  Google Scholar 

  • CSI (2014) Pass + Co continuous motorcycle protection system TM 1.60 Case test report. CSI-SPA, Milano IT (No. 0044/ME/HRB/14)

  • CSI (2015) Pass + Co continuous motorcycle protection system TM 3.60 Case test report. CSI-SPA, Milano IT (No. 0039/ME/HRB/15)

  • Davids WG, Botting JK, Peterson M (2006) Development and structural testing of a composite-reinforced timber highway guardrail. Constr Build Mater 20:733–743

    Article  Google Scholar 

  • Deck C, Willinger R, Baumgartner D and Meyer F (2003) Helmet optimisation against biomechanical criteria. In: IRCOBI Conference, pp 351–352

  • Draper NR, Smith H (2014) Applied regression analysis, 3rd edn. Wiley, New York

    MATH  Google Scholar 

  • EN 1317-1:2010. Road restraint systems. Terminology and general criteria for test methods. European Committee for Standardization

  • EN 1317-2:2010. Road restraint systems. Performance classes, impact test acceptance criteria and test methods for safety barriers including vehicle parapets. European Committee for Standardization

  • Faller RK, Polivka KA, Kuipers BD, Bielenberg RW, Reid JD, Rohde JR, Sicking DL (2004) Midwest guardrail system for standard and special applications. Transp Res Rec 1890(1):19–33

    Article  Google Scholar 

  • Faller RK, Sicking DL, Bielenberg RW, Rohde JR, Polivka KA, Reid JD (2007) Performance of steel-post, W-beam guardrail systems. Transp Res Rec 2025:18–33

    Article  Google Scholar 

  • Faller RK, Reid JD, Kretschmann D, Hascall J, Sicking DL (2009) Midwest guardrail system with round timber posts. Transp Res Rec 2120:47–59

    Article  Google Scholar 

  • Fang H, Horstemeyer MF (2006) Global response approximation with radial basis functions. Eng Optim 38(4):407–424

    Article  MathSciNet  Google Scholar 

  • Fang H, Wang Q, Weggel DC (2015) Crash analysis and evaluation of cable median barriers on sloped medians using an efficient finite element model. Adv Eng Softw 82:1–13

    Article  Google Scholar 

  • Fang J, Sun G, Qiu N, Kim NH, Li Q (2017a) On design optimization for structural crashworthiness and its state of the art. Struct Multidisc Optim 55:1091–1119. https://doi.org/10.1007/s00158-016-1579-y

    Article  MathSciNet  Google Scholar 

  • Fang Y, Zhan Z, Yang J, Liu X (2017b) A mixed-kernel-based support vector regression model for automotive body design optimization under uncertainty. ASCE-ASME J Risk Uncertain Eng Syst B 3:1–12. https://doi.org/10.1115/1.4036990

    Article  Google Scholar 

  • Feng Y, Cui N, Gong D, Zhang Q, Zhao L (2017) Evaluation of random forests and generalized regression neural networks for daily reference evapotranspiration modelling. Agric Water Manage 193:163–173. https://doi.org/10.1016/j.agwat.2017.08.003

    Article  Google Scholar 

  • Forrester AIJ, Sobester A, Keane AJ (2007) Multi-fidelity optimization via surrogate modeling. Proc R Soc Lond A 463(2088):3251–3269

    MathSciNet  MATH  Google Scholar 

  • Garcia D, Bidal S (2008) APROSYS SP4; guidelines for a new European standard proposal for impacts of motorcyclists vs. road infrastructure. APROSYS Project FINAL-AP-SP42-04

  • Ghajari M, Caserta DG, Galvanetto U (2010). Comparison of safety helmet testing standards. European Commission Dg Research, Project: MRTN-CT-2006-035965 MYMOSA

  • Girosi F (1998) An equivalence between sparse approximation and support vector machines. Neural Comput 10(6):1455–1480

    Article  Google Scholar 

  • Goel T, Haftka RT, Shyy W, Queipo NV (2007) Ensemble of surrogates. Struct Multidisc Optim 33(3):199–216

    Article  Google Scholar 

  • Gorissen D, Couckuyt I, Demeester P, Dhaene T, Crombecq K (2010) A surrogate modeling and adaptive sampling toolbox for computer based design. J Mach Learn Res 11(1):2051–2055

    Google Scholar 

  • Hou S, Zheng Y, Xie J, Han X (2013) Optimization design of NJ shaped guardrail based on collision safety consideration. Int J Comput Methods 11:1350083–1-1350083–20

    Google Scholar 

  • Hou S, Tan W, Zheng Y, Han X, Li Q (2014) Optimization design of corrugated beam guardrail based on RBF-MQ surrogate model and collision safety consideration. Adv Eng Softw 78:28–40

    Article  Google Scholar 

  • Ju C, Bibaut A, van der Laan M (2018) The relative performance of ensemble methods with deep convolutional neural networks for image classification. J Appl Stat 45:2800–2818. https://doi.org/10.1080/02664763.2018.1441383

    Article  MathSciNet  Google Scholar 

  • Li C, Kim IY (2015) Lightweight optimal design of a rear bumper system based on surrogate models. No. 2015-01-1362. SAE technical paper. https://doi.org/10.4271/2015-01-1362

  • LSTC (2014) User manual of LS-DYNA, 3 dimensional finite element analysis program. Livermore Software Corporation, Livermore

    Google Scholar 

  • Mantaras DA, Luque P (2015) Assessing motorcyclist protection systems using finite element simulation. Int J Simul Model 14:110–120

    Article  Google Scholar 

  • Matheron G (1963) Principles of geostatistics. Econ Geol 58(8):1246–1266

    Article  Google Scholar 

  • MATLAB (2017) Matlab and statistics toolbox release (2017b). The MathWorks, Inc., Natick

  • Meng Z, Zhang D, Li G, Yu B (2019) An importance learning method for non-probabilistic reliability analysis and optimization. Struct Multidisc Optim 59:1255–1271. https://doi.org/10.1007/s00158-018-2128-7

    Article  Google Scholar 

  • Nasser IM, Abu-Naser SS (2019) Predicting tumor category using artificial neural networks. Int J Acad Heal Med Res 3:1–7

    Google Scholar 

  • Ong YS, Nair PB, Keane AJ, Wong KW (2005) Surrogate assisted evolutionary optimization frameworks for high-fidelity engineering design problems. Knowledge incorporation in evolutionary computation. Springer, Berlin, pp 307–331

    Chapter  Google Scholar 

  • Ozcanan S, Atahan AO (2019) RBF surrogate model and EN1317 collision safety-based optimization of two guardrails. Struct Multidisc Optim 60:343–362. https://doi.org/10.1007/s00158-019-02203-z

    Article  Google Scholar 

  • Peri D, Campana EF (2005) High-fidelity models and multiobjective global optimization algorithms in simulation-based design. J Ship Res 49(3):159–175

    Article  Google Scholar 

  • Plaxico CA, Ray MH, Hiranmayee K (2000) Comparison of the impact performance of the G4 1W) and G4 (2W) guardrail systems: comparison under NCHRP report 350 test 3–11conditions. Transp Res Rec 1720:7–18

    Article  Google Scholar 

  • Plaxico CA, Kennedy JC, Miele CR (2006) Development of an NCHRP report 350 TL-3 New Jersey shape 50-inch portable concrete barrier. Final report FHWA/OH- 2006/16. Ohio Department of Transportation, Ohio, USA

  • Queipo NV, Haftka RT, Shyy W, Goel T, Vaidyanathan R, Tucker PK (2005) Surrogate-based analysis and optimization. Prog Aerosp Sci 41(1):1–28

    Article  Google Scholar 

  • Ray MH, Patzner GS (1997) Finite-element model of modified eccentric loader terminal (MELT). Transp Res Rec. https://doi.org/10.3141/1599-02

    Article  Google Scholar 

  • Ray MH, Engstrand K, Plaxico CA, McGinnis R (2001) Improvements to the weak-post W-beam guardrail. Transp Res Rec 1743(1):88–96

    Article  Google Scholar 

  • Reid JD, Sicking DL, Faller RK, Pfeifer B (1997) Development of a new guardrail system. Transp Res Rec 1599(1):72–80

    Article  Google Scholar 

  • Ren Z, Vesenjak M (2005) Computational and experimental crash analysis of the road safety barrier. Eng Fail Anal 12:963–973

    Article  Google Scholar 

  • Ruiz DG, Magallón BP, Peldschus S, Schuller E, Gallo AM, Bidal S (2010) Overview on the development of a test standard for the evaluation of motorcyclists’ impacts on road infrastructure elements. Int J Crashworth 15:1–15. https://doi.org/10.1080/13588260902956070

    Article  Google Scholar 

  • Sacks J, Schiller SB, Welch WJ (1989a) Designs for computer experiments. Technometrics 31(1):41–47

    Article  MathSciNet  Google Scholar 

  • Sacks J, Welch WJ, Mitchell TJ, Wynn HP (1989b) Design and analysis of computer experiments. Stat Sci 4(4):409–423

    MathSciNet  MATH  Google Scholar 

  • Sicking DL (1995) Applications of simulation in design and analysis of roadside safety features. Transportation research circular 435, TRB, National Research Council, Washington DC

  • Sicking DL, Reid JD, Rohde JR (2002) Development of the midwest guardrail system. Transp Res Rec 1797:44–52

    Article  Google Scholar 

  • Soltani M, Moghaddam TB, Karim MR, Sulong NH (2013) The safety performance of guardrail systems: review and analysis of crash tests data. Int J Crashworth 18:530–543

    Article  Google Scholar 

  • Song X, Sun G, Li G, Gao W, Li Q (2013) Crashworthiness optimization of foam-filled tapered thin-walled structure using multiple surrogate models. Struct Multidisc Optim 47(2):221–231

    Article  MathSciNet  MATH  Google Scholar 

  • Sun W, Yan X, Gao F (2018) Analysis of frequency-domain vibration response of thin plate attached with viscoelastic free layer damping. Mech Based Des Struct Mach 46:209–224. https://doi.org/10.1080/15397734.2017.1327359

    Article  Google Scholar 

  • Teng TL, Liang CL, Nguyen VH (2013) Development and validation of finite element model of helmet impact test. Proc Inst Mech Eng L 227:82–88. https://doi.org/10.1177/1464420712451806

    Article  Google Scholar 

  • Tyrell DC, Severson KJ, Marquis BP (1995) Analysis of occupant protection strategies in train collisions. Am Soc Mech Eng Appl Mech Div AMD 210:539–557

    Google Scholar 

  • Vapnik VN (1998) Statistical learning theory. Wiley, New York

    MATH  Google Scholar 

  • Wang GG, Shan S (2007) Review of metamodeling techniques in support of engineering design optimization. J Mech Des Trans ASME 129:370–380. https://doi.org/10.1115/1.2429697

    Article  Google Scholar 

  • Xia L, Liu W, Lv X, Gu X (2018) A system methodology for optimization design of the structural crashworthiness of a vehicle subjected to a high-speed frontal crash. Eng Optim 50:634–650. https://doi.org/10.1080/0305215X.2017.1334774

    Article  MathSciNet  Google Scholar 

  • Yang J, Zhan Z, Zheng K, Hu J, Zheng L (2016) Enhanced similarity-based metamodel updating strategy for reliability-based design optimization. Eng Optim 48(12):2026–2045

    Article  MathSciNet  Google Scholar 

  • Yegnanarayana B (2009) Artificial neural networks. Prentice-Hall of India, New Delhi

  • Yin H, Fang H, Wang Q, Wen G (2016) Design optimization of a MASH TL-3 concrete barrier using RBF-based metamodels and nonlinear finite element simulations. Eng Struct. https://doi.org/10.1016/j.engstruct.2016.02.009

    Article  Google Scholar 

  • Yin H, Xiao Y, Wen G, Fang H (2017) Design optimization of a new W-beam guardrail for enhanced highway safety performance. Adv Eng Softw 112:154–164

    Article  Google Scholar 

  • Zhang J, Chowdhury S, Messac A (2012) An adaptive hybrid surrogate model. Struct Multidisc Optim 46(2):223–238

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Borçelik Çelik San. ve Tic. A.Ş., Ata Mh. 125. Sk. No:1, Gemlik, 16601, Bursa, Turkey

    İlhan Yılmaz & İbrahim Yelek

  2. Department of Civil Engineering, Sirnak University, M. Emin Acar Campus, 73000, Sirnak, Turkey

    Sedat Özcanan

  3. Department of Civil Engineering, İstanbul Technical University, Ayazağa Campus, 34469, İstanbul, Turkey

    Ali Osman Atahan

  4. Pass+Co Road Restraint Systems, Seigen, Germany

    J. Marten Hiekmann

Authors
  1. İlhan Yılmaz
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. İbrahim Yelek
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sedat Özcanan
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ali Osman Atahan
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. J. Marten Hiekmann
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to İlhan Yılmaz.

Ethics declarations

Conflict of interest

On behalf of all authors, the corresponding author states that there is no conflict of interest.

Replication of results

The data and codes will be available once requested.

Additional information

Responsible Editor: Gengdong Cheng

Publisher's Note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yılmaz, İ., Yelek, İ., Özcanan, S. et al. Artificial neural network metamodeling-based design optimization of a continuous motorcyclists protection barrier system. Struct Multidisc Optim 64, 4305–4323 (2021). https://doi.org/10.1007/s00158-021-03080-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00158-021-03080-1

Keywords

Search

Navigation