基于多元回归的Fe-Ni-Cu-C低合金强度误差预测

Prediction of Strength Error in Fe-Ni-Cu-C Low Alloy Based on Multiple Regression

采用普通方法分析Fe-Ni-Cu-C合金中元素间相互作用时,若未考虑相互效应会导致预测精度偏低,鉴于此,提出多元化线性回归方法,目的在于减小预测误差。通过对多元回归概念的了解,进行模型相关性分析,确定影响Fe-Ni-Cu-C低合金抗拉强度的5项因素,建立多元线性回归模型,对比分析强度预测值和实测值,检验模型准确性。结果表明:基于多元线性回归的Fe-Ni-Cu-C低合金强度预测误差小,模型拟合效果良好,适用于复杂合金体系强度预测,预测结果可为材料强度特性研究及性能优化提供指导。

When analyzing the interaction between elements in Fe-Ni-Cu-C alloy using ordinary methods,if the interaction effect is not considered,it will lead to low prediction accuracy.In view of this,a diversified linear regression method is proposed to reduce prediction errors.By understanding the concept of multiple regression and conducting model correlation analysis,five factors affecting the tensile strength of Fe-Ni-Cu-C low alloy were identified.A multiple linear regression model was established to compare and analyze the predicted strength values with the measured values,and the accuracy of the model was tested.The results show that the strength prediction error of Fe-Ni-Cu-C low alloy based on multiple linear regression is small,the model fitting effect is good,and it is suitable for predicting the strength of complex alloy systems.The prediction results can provide guidance for the study of material strength characteristics and performance optimization.