一重技术2024,Issue(6) :66-70.DOI:10.3969/j.issn.1673-3355.2024.06.019

基于Kriging的检验质量释放残余速度预测

Prediction of Residual Velocity of Inspection Mass Release Based on Kriging

王日龙 刘博林
一重技术2024,Issue(6) :66-70.DOI:10.3969/j.issn.1673-3355.2024.06.019

基于Kriging的检验质量释放残余速度预测

Prediction of Residual Velocity of Inspection Mass Release Based on Kriging

王日龙 1刘博林1
扫码查看

作者信息

  • 1. 沈阳理工大学机械工程学院,辽宁 沈阳 110159
  • 折叠

摘要

针对空间惯性传感器检验质量释放残余速度,提出一种基于Kriging代理模型的预测方法,分别采用Kriging代理模型,RBF代理模型及SVM代理模型对试验数据进行拟合,并以相关系数R为模型精度指标对三种代理模型进行评价.通过对比得出Kriging代理模型对捕获定位释放机构检验质量释放残余速度的预测精度最高.

Abstract

In view of the residual velocity of inspection mass release of the spatial inertial sensor,a prediction method based on Kriging surrogate model is proposed.The Kriging surrogate model,RBF surrogate model and SVM surrogate model are respectively applied for test data fitting,and the correlation coefficient R is adopted as the indicator of model accuracy for evaluation of these 3 kinds of surrogate models.Through comparison,it is found that the Kriging surrogate model has the highest prediction accuracy for residual velocity of inspection mass release of the grabbing positioning and release mechanism.

关键词

残余速度/代理模型/Kriging/预测精度

Key words

Residual velocity/surrogate model/Kriging/prediction accuracy

引用本文复制引用

出版年

2024
一重技术
一重集团大连设计研究院有限公司

一重技术

影响因子:0.142
ISSN:1673-3355
段落导航相关论文