摘要
基于大数据分析的方法,以实测数据为基础,采用SPSS软件对345 MPa级H型钢生产过程中的冶炼和轧制工序因素进行偏相关分析和因子分析,确定了影响产品性能的主要和次要影响因素。利用多元线性回归方法,分析了各因素与屈服强度、抗拉强度、断后伸长率的关系,得出各因素对性能的影响,并分别建立了回归模型。通过生产实测数据对回归模型进行验证,模型计算结果与实测数据的相对误差在±10%内的比例达97.07%以上。
Based on the measured data and using SPSS software,partial correlation analysis and factor analysis were carried out to determine the main and secondary factors affecting the performance of 345 MPa grade H-beam.Multivariate linear regression method was used to analyze the relationship between each factor and yield strength,tensile strength and elongation after fracture,and the influence of each factor on the performance was obtained.The regression models were established respectively.The regression equation is verified by the measured data of actual production.The results show that the relative error rate between the predicted results and the measured data is within±10%,which proportion is above 97.07%.
作者
付常伟
FU Chang-wei(Technology Center,Laiwu Branch,Shandong Iron and Steel Co.,Ltd.,Laiwu 271104,China)
出处
《轧钢》
2020年第2期83-88,共6页
Steel Rolling
关键词
H型钢
大数据分析
多元回归分析
力学性能
H-beam
big data analysis
multiple regression analysis
mechanical property