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

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(R^(2))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。

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(R^(2))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(R^(2))is close to 1.The predictions are accurate.