牵引车架结构强度优化设计与仿真  

Multi-objective optimization of semi-trailer frame based on RBNN

作　　者：李伟平[1] 陶祺臻 张宝珍[1] 孔剑[1] 

机构地区：[1]湖南大学汽车车身先进设计制造国家重点实验室,长沙410082

出　　处：《现代制造工程》2016年第7期67-71,113,共6页Modern Manufacturing Engineering

基　　金：国家高技术研究发展计划(863计划)资助项目(2012AA111802)

摘　　要：为了实现牵引车车架结构强度优化,采用近似模型-多目标优化算法组合方法。首先,用非线性有限元分析方法对车架的强度进行分析。由于构建的有限元模型较复杂,非线性强,故采用非线性映射能力强的径向基神经网络构建近似模型,然后利用粒子群多目标优化算法对其优化。与优化前的车架进行对比,优化后车架的应力值和质量得到明显改善,验证了方法的可行性,并为今后牵引车架的结构优化设计提供了借鉴。To realize the optimization of the strength of the semi-trailer frame, adopt the method which combine approximate model with multi-objective optimization. First of all, the nonlinear finite element analysis methodology was utilized to analysis the strength of the semi-trailer frame. Additionally, due to the finite element model established is more complex, and strong nonlinear, Radial Basis Neural Network（RBNN） which have nonlinear mapping ability was used to construct approximate model. Finally, adopt Multi-Objective Particle Swarm Optimization algorithm（MOPSO） to optimize the semi-trailer frame. The optimization results show that, compared with the original, the stress and weight of the optimized frame can be improved obviously, verifying the feasibility of the method. And it provides a reference for the structure optimization design of semi-trailer frame in the future.

关 键 词：车架 粒子群算法 近似模型 多目标优化 

分 类 号：U462.3[机械工程—车辆工程]