锡基合金硬度偏最小二乘回归预测模型  

Prediction Model of Hardness of Sn Based Alloy by Partial Least Squares Regression

作　　者：李宽[1] 张长胜[1] 张汉平[1] 李川[1] 

机构地区：[1]昆明理工大学信息工程与自动化学院,云南昆明650500

出　　处：《软件》2017年第12期202-205,共4页Software

摘　　要：锡基合金具有摩擦系数小、硬度适中且韧性好等优点。其硬度由显微结构决定,因此,建立硬度与其微观结构间的定量相关模型,并分析其各相参数变化对硬度的影响,可以为研究新型合金和制定合金生产中的时效工艺提供参考和依据。基于锡基合金显微结构特点,通过提取合金金相特征参数,建立其硬度的关联预测模型。并通过实验数据分析了影响锡基合金硬度的因素及机理;对金相图做参数提取处理,用偏最小二乘回归分析对该参数进行硬度线性和非线性预测模型的构建。结果表明,该非线性偏最小二乘回归模型对锡基合金的硬度预测精度更高。The tin-based alloy has the advantages of small friction coefficient, moderate hardness and good toughness, etc. Its hardness depends on the microstructure. Therefore, the quantitative correlation model between the hardness and its microstructure is established, and the influence of the parameters on the hardness is analyzed to provide reference for the research and development of new alloy aging process in the production process of alloy. The correlation prediction model of hardness is established by extracting the metallurgical characteristic parameters of the alloy based on the microstructure characteristics of tin based alloy. The factors influencing the hardness of the tin-based alloy were analyzed by the experimental data. The parameters of the metallographic diagram were ex-tracted and the linearity and nonlinear prediction model were constructed by partial least squares regression analysis based on the parameters. The results show that the constructed nonlinear partial least squares regression model can predict the hardness of Sn based alloy effectively.

关 键 词：锡基合金 硬度 显微结构 偏最小二乘回归 预测模型 

分 类 号：TB3[一般工业技术—材料科学与工程]