基于支持向量机回归算法的对接接头固有应变预测
Inherent Strain Prediction of Butt Joints Based on Support Vector Machine Regression Algorithm
康俊涛 1韦朝校1
作者信息
- 1. 武汉理工大学土木工程与建筑学院,武汉 430070
- 折叠
摘要
为了提高对接接头固有应变的获取效率,进行了41组对接接头数值模拟实验,获取了实验的固有应变值,并基于实验数据,利用机器学习方法可以高效处理数据的优点,采用支持向量机回归(SVR)算法对对接接头的横向和纵向固有应变值进行了预测.采用均方根误差(RMSE),平均绝对百分比误差(MAPE)和决定系数(R2)对预测模型进行了评估.结果表明,预测模型的均方根误差和平均绝对百分比误差都很小,决定系数都接近于1,预测的结果很精准.
Abstract
In order to improve the efficiency of obtaining the inherent strains of butt joints,41 sets of numerical simula-tion experiments of butt joints were carried out to obtain the experimental inherent strain values,and based on the experi-mental data,the transverse and longitudinal inherent strain values of butt joints were predicted by the support vector ma-chine regression(SVR)algorithm using the advantages of machine learning methods that can process the data efficiently.Moreover,the root mean square error(RMSE),mean absolute percentage error(MAPE)and coefficient of determination(R2)were used to evaluate the prediction model.The results show that the root mean square error(RMSE)and the mean absolute percentage error(MAPE)of the prediction model are small,and the coefficient of determination(R2)is close to 1.The predictions are accurate.
关键词
焊接变形/固有应变法/支持向量机回归/对接接头Key words
welding deformation/inherent strain method/support vector machine regression/butt joints引用本文复制引用
出版年
2024
NETL
NSTL
万方数据