摘要
采用拉丁方试验设计方法对汽车侧围关键吸能部件的材料和板料厚度进行了多参数空间的样本数据设计,结合近似技术和多目标遗传算法,提出了一种基于BP神经网络模型的侧碰多目标优化方法。研究结果表明:该方法在满足侧碰法规GB20071的基础上,既能提高侧围结构对乘员的保护性能,又能实现其轻量化目标;BP神经网络模型的精度和效率较好地满足了工程要求。
The sampling data of thickness and material of automobile＇s side body key Absorbing energy parts were obtained by the latin experimental design method.By combining approximate technology and multi-objective genetic algorithm,a multi-objective optimization method of side impact structure was established based on BP network model.The results show that： this method meets the requirements of GB20071,it improves the side structure＇s occupant protection capability,and achieves the lightweight objective,the accuracy and efficiency of BP network model meet the requirements of engineering design.
出处
《中国机械工程》
EI
CAS
CSCD
北大核心
2012年第17期2122-2127,共6页
China Mechanical Engineering
基金
湖南大学汽车车身先进设计制造国家重点实验室自主研究课题资助项目(60870002)
噪声振动和安全技术国家重点汽车实验室2011年度开放基金资助项目(NVHSKL-201103)
关键词
轻量化
拉丁方试验设计
近似技术
BP神经网络
多目标遗传算法
lightweight
latin experimental design
approximate technology
BP network
multi-objective genetic algorithm
