A system optimisation design approach to vehicle structure under frontal impact based on SVR of optimised hybrid kernel function

Abstract Frequent occurrences of road traffic accidents put forward more and more stringent requirements on the vehicle safety performance. To optimise the vehicle structure crashworthiness, the different optimisation design methods, including deterministic, reliability-based and robust optimisation, are performed simultaneously in this study. The support vector regression (SVR) model is employed to approximate responses between design variables and objectives, and the hybrid kernel function (HKF) is introduced to overcome the drawback of a single kernel function of SVR. Meanwhile, the particle swarm optimisation (PSO) algorithm is adopted to optimise HKF–SVR model parameters and improve the accuracy of the model. By combining the nondominated Sorting Genetic Algorithm II (NSGA-II) and the Monte Carlo Simulation (MCS), the proposed optimisation design approach is proven to be an efficient and systematic tool to guarantee the reliability and robustness of the vehicle structure safety design. These different optimisation design results are discussed and contrasted with initial design. The results show that the proposed approach not only improves the crashworthiness and lightweight of vehicle, but also increases the reliability and robustness of design parameters. Through reliable and robust optimisation, more conservative solutions can be generated.

[1]  Liu Weiguo,et al.  Reliability design optimization of vehicle front-end structure for pedestrian lower extremity protection under multiple impact cases , 2015 .

[2]  Enrico Zio,et al.  A particle swarm‐optimized support vector machine for reliability prediction , 2012, Qual. Reliab. Eng. Int..

[3]  Guangyao Li,et al.  Reliability-based multiobjective optimisation of vehicle bumper structure holes for the pedestrian flexible legform impact , 2016 .

[4]  Vladimir Vapnik,et al.  An overview of statistical learning theory , 1999, IEEE Trans. Neural Networks.

[5]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[6]  L. Gallimard,et al.  Coupling finite element and reliability analysis through proper generalized decomposition model reduction , 2013 .

[7]  Yu Zhang,et al.  Metamodeling development for reliability-based design optimization of automotive body structure , 2011, Comput. Ind..

[8]  Qing Li,et al.  A Comparative study on multiobjective reliable and robust optimization for crashworthiness design of vehicle structure , 2013 .

[9]  Jun Wang,et al.  A support vector machine with a hybrid kernel and minimal Vapnik-Chervonenkis dimension , 2004, IEEE Transactions on Knowledge and Data Engineering.

[10]  Yi Zhang,et al.  An Approximation Approach to General Robustness Assessment for Multidisciplinary Systems , 2010, J. Comput. Inf. Sci. Eng..

[11]  W. Tang,et al.  Support Vector Machine Based on Hybrid Kernel Function , 2012 .

[12]  Jianwei Lu,et al.  Reliability-based robust assessment for multiobjective optimization design of improving occupant restraint system performance , 2014, Comput. Ind..

[13]  Markus Lienkamp,et al.  Acceleration-based criterion for intrusions in frontal impacts , 2017 .

[14]  Dengfeng Wang,et al.  Structure-material-performance integration lightweight optimisation design for frontal bumper system , 2018 .

[15]  Ping Jiang,et al.  Crushing analysis and multiobjective optimization design for rectangular unequal triple-cell tubes subjected to axial loading , 2017 .

[16]  Zhao Lu,et al.  Non-Mercer hybrid kernel for linear programming support vector regression in nonlinear systems identification , 2009, Appl. Soft Comput..

[17]  M. Hohenbichler,et al.  Improvement Of Second‐Order Reliability Estimates by Importance Sampling , 1988 .

[18]  Wei Chen,et al.  Lightweight design of vehicle parameters under crashworthiness using conservative surrogates , 2013, Comput. Ind..

[19]  Andong Yin,et al.  Optimization design for foam-filled double cylindrical tubes under multiple lateral impacts , 2018, Advances in Mechanical Engineering.

[20]  Yong Zhang,et al.  Enhance crashworthiness of composite structures using gradient honeycomb material , 2018 .

[21]  M. Subramanian,et al.  New mass optimization technique to achieve low mass BIW designs using optimal material layout methodology on the frontal vehicle crash , 2016 .

[22]  Larsgunnar Nilsson,et al.  Robust optimization of front members in a full frontal car impact , 2013 .

[23]  Liang Xia,et al.  A system methodology for optimization design of the structural crashworthiness of a vehicle subjected to a high-speed frontal crash , 2017 .

[24]  M. Ramachandran,et al.  Application of multi-criteria decision making to sustainable energy planning--A review , 2004 .

[25]  Ning Wang,et al.  Impact characteristics and crashworthiness of multi-cell, square, thin-walled, structures under axial loads , 2017 .

[26]  Guangyao Li,et al.  Reliable optimisation design of vehicle structure crashworthiness under multiple impact cases , 2017 .

[27]  Ping Zhu,et al.  Metamodel-based lightweight design of B-pillar with TWB structure via support vector regression , 2010 .

[28]  Yang Zhang,et al.  Bi-objective variable selection for key quality characteristics selection based on a modified NSGA-II and the ideal point method , 2016, Comput. Ind..

[29]  Shifei Ding,et al.  A Novel Extreme Learning Machine Based on Hybrid Kernel Function , 2013, J. Comput..

[30]  Ren-Jye Yang,et al.  Design for six sigma through robust optimization , 2004 .

[31]  Guangyao Li,et al.  Crashworthiness design of vehicle by using multiobjective robust optimization , 2011 .

[32]  Qing Li,et al.  Multiobjective optimization for crash safety design of vehicles using stepwise regression model , 2008 .

[33]  Jianwei Lu,et al.  Reliability-based design optimization for vehicle occupant protection system based on ensemble of metamodels , 2015 .

[34]  Qiang Cheng,et al.  An Analytical Robust Design Optimization Methodology Based on Axiomatic Design Principles , 2014, Qual. Reliab. Eng. Int..

[35]  Xu Han,et al.  Multivariable crashworthiness optimization of vehicle body by unreplicated saturated factorial design , 2012 .

[36]  Aiguo Cheng,et al.  Bending analysis and design optimisation of tailor-rolled blank thin-walled structures with top-hat sections , 2017 .