汽车工程

汽车工程 ›› 2020, Vol. 42 ›› Issue (4): 462-467.doi: 10.19562/j.chinasae.qcgc.2020.04.007

• • 上一篇    下一篇

基于PSO-SVR近似模型的乘员约束系统稳健性优化*

张海洋1, 胡帅帅1, 周大永1, 高剑武3, 谷先广2,3   

  1. 1.浙江吉利汽车研究院有限公司,浙江省汽车安全技术研究重点实验室,杭州 311228;
    2.太航常青汽车安全系统(苏州)股份有限公司,苏州 215100;
    3.合肥工业大学汽车与交通工程学院,合肥 230009)
  • 出版日期:2020-04-25 发布日期:2020-05-12
  • 通讯作者: 谷先广,副教授,硕士生导师,E-mail:gxghfut@163.com
  • 基金资助:
    *中国博士后基金(2018M640524)和浙江省汽车安全技术研究重点实验室开放基金(2009E10013)资助

Robust Optimization of Occupant Restraint SystemBased on PSO-SVR Approximation Model

Zhang Haiyang1, Hu Shuaishuai1, Zhou Dayong1, Gao Jianwu3 & Gu Xianguang2,3   

  1. 1.Geely Automobile Research Institute, Zhejiang Key Laboratory of Automobile Safety Technology, Hangzhou 311228;
    2.Taihang Changqing Automobile Safety System (Suzhou) Co., Ltd., Suzhou 215100;
    3.School of Automobile and Transportation Engineering, Hefei University of Technology, Hefei 230009
  • Online:2020-04-25 Published:2020-05-12

PDF (PC)

433

赞

摘要： 综合运用近似模型参数优化技术和稳健性优化方法对汽车乘员约束系统进行优化。通过全局灵敏度分析,选出对加权伤害准则(weighted injury criterion, WIC)影响大的参数;采用粒子群优化(PSO)算法对支持向量回归(SVR)模型参数和核函数参数进行优化,建立高精度的PSO-SVR近似模型;在确定性优化的基础上进行基于蒙特卡罗抽样的稳健性优化。结果表明:优化后乘员约束系统性能得到明显提升且兼顾了稳健性。

关键词: 乘员约束系统, 灵敏度分析, 粒子群优化, 支持向量回归, 稳健性优化

Abstract: By comprehensively utilizing the parameter optimization technique for approximate model and robust optimization method, vehicle occupant restraint system is optimized. The parameters having significant effects on weighted injury criterion (WIC) are selected by global sensitivity analysis. The parameters of support vector regression (SVR) model and kernel function are optimized by using particle swarm optimization (PSO) algorithm, and a high accuracy PSO-SVR approximation model is established. On the basis of deterministic optimization, robust optimization based on Monte Carlo sampling is also carried out. The results show that after optimization the performances of occupant restraint system are apparently enhanced with good robustness

Key words: occupant restraint system, sensitivity analysis, PSO, SVR, robust optimization