摘要
由实验测得专家经验测点的温度与热形变误差量,通过模糊聚类的分析方法找出影响误差精度的主要温度测点,分别利用多元线性回归的分析方法和遗传算法优化BP神经网络法建立热变形误差的数学模型,将两种方式进行对比分析哪种方式更优。
Measure the temperature and thermal deformation errors of expert experience measurement points by experiment,find the main impact error precision of measuring temperature points,by the way of fuzzy clustering analysis.Using multivariate linear regression analysis method and the genetic algorithm to optimize the BP neural network to establish the mathematical model of the thermal deformation of error.Finally,compare two ways to find which is better.
出处
《制造技术与机床》
CSCD
北大核心
2011年第2期52-55,共4页
Manufacturing Technology & Machine Tool
基金
863项目资金支持:"固定工作台式五轴联动精密数控电火花成形加工机床"子项目(2009AA044202)
关键词
温度测点选择
模糊聚类分析
多元线性回归
遗传算法
BP神经网络
Temperature Measurement Point＇s Selection
Fuzzy Clustering Analysis
Multivariate Linear Regression
Genetic Algorithm
BP Neural Network
