实验设计及kriging响应面在优化设计中的应用  

Experimental Design and Response Surface of Kriging in the Application of the Optimization Design

作　　者：徐兴伟[1] 胡晓兵[1] 武韶敏 赵清祥[1] 

机构地区：[1]四川大学制造科学与工程学院,成都610065

出　　处：《组合机床与自动化加工技术》2017年第1期62-65,69,共5页Modular Machine Tool & Automatic Manufacturing Technique

基　　金：四川省科技计划项目(2015GZ0032;2016GZ0169)

摘　　要：为了减轻结构自重,需对结构进行优化设计。而复杂工程优化问题中,设计变量多且多属于非线性问题,所以对工程优化问题存在着计算时间长、优化效率低且准确性难以判断等特点。将代理模型引入在优化设计中,并通过实验设计方法得到实验设计点,根据实验设计点建立Kriging响应面,对Kriging响应面模型进行优化设计。得出该方法对结构优化设计有很显著的效果。最后以门式起重机主梁为例,建立对应的Kriging响应面进行优化设计,使用该方法优化后,其门式起重机主梁自重减轻了20%,并采用有限元方法验证了结果的准确性。对研究轻量化设计有着重要的参考及借鉴意义。to reduce the weight of structure,we need to do structure optimization . but design variables are much and generally belong to nonlinear problem on complex engineering optimization problems. so there are many problems such as long computing time, low efficiency and accuracy for optimization and it is difficult to evaluate the consequences, etc. Introduce surrogate model in optimization design to establish Kriging re-sponse surface model through experimental design point and optimize Kriging response surface model. It is concluded that the method have a significant effect on structure optimization design. Finally establish Kriging response surface model for gantry crane. The weight of the structure are reduced by 25% after using Kriging response surface model in optimization design. the accuracy of the results is verified by finite element meth-od. it has an important reference structure optimization.

关 键 词：KRIGING 优化设计 代理模型 实验设计 

分 类 号：TH122[机械工程—机械设计及理论] TG68[金属学及工艺—金属切削加工及机床]