摘要
根据182组实测焊缝金属奥氏体分解温度值,分别采用线性回归方法、非线性回归方法和人工神经网络技术建立了奥氏体分解温度的预测公式或模型。结果表明:线性回归公式难以准确体现各因素与奥氏体分解温度之间的关系,引入Mo指数和ln(t8/3)函数,预测精度有所提高;考虑了各因素之间交互作用的神经网络模型预测精度高于线性和非线性回归公式的,更适合于奥氏体分解温度预测研究。
Based on 182 experimental data of austenite decomposition temperature, the formulas or models of austenite decomposition temperature are established by linear regression method, nonlinear regression method and artificial neural network respectively. The results show that linear regression formula cannol exactly express the relalionship between factors and austenite deeomposition temperature, with molybdemlm exponential and ln（t8/3 ） function were introduced, precision of the formula increased ; the neural network model takes the interaction of factors into account, which predict more accurately than by linear anti nonlinear regression tormulas, and is more applicable for the research of predicting austenite decomposition temperature.
出处
《材料开发与应用》
CAS
2015年第2期32-36,共5页
Development and Application of Materials
关键词
奥氏体分解温度
线性回归
非线性回归
神经网络
austenite decomposition temperature
linear regression
nonlinear regression
neural network
