• 论文 •    

基于高斯过程元模型的产品设计时间估计方法

张昆仑,刘新亮,郭波   

  1. 1.国防科学技术大学 信息系统与管理学院,湖南长沙410073;2.后勤指挥学院,北京100858
  • 出版日期:2011-01-15 发布日期:2011-01-25

Time estimation method for product design based on Gaussian process meta-model

ZHANG Kun-lun, LIU Xin-liang, GUO Bo   

  1. 1.College of Information Systems & Management, National University of Defense Technology, Changsha 410073, China;2.The Logistics Command Academy, Beijing 100858, China
  • Online:2011-01-15 Published:2011-01-25

摘要: 为更精确地预测产品设计时间,将高斯过程元模型建模方法应用于产品设计时间估计中,介绍了高斯过程元模型的建模原理。考虑产品设计时间影响因素中存在语言型变量的问题,利用Hausdorff距离辅助构造高斯过程建模中的相关矩阵,通过算例分析证明高斯过程元模型优于已有的两种模糊神经网络模型。

关键词: 元模型, 高斯过程元模型, 产品设计, 时间估计, Hausdorff距离

Abstract: To estimate the product design time more precisely, the modeling methodology of Gaussian process meta-model was applied to estimate the product design time. The modeling principles of Gaussian process meta-model were firstly introduced. Since there were linguistic variables among the input data in time estimation of product design, Hausdorff distance was applied to assist the construction of relevant matrix in Gaussian Process modeling. The example analysis illustrated that Gaussian Process meta-model was superior to the existing two fuzzy neural network models.

Key words: meta-model, Gaussian Process meta-model, product design, time estimate, Hausdorff distance

中图分类号: