人工神经网络
克里金
航程(航空)
回归
合金
马氏体
高斯分布
大气温度范围
学位(音乐)
应用数学
热力学
理论(学习稳定性)
过程(计算)
算法
冶金
数学
统计物理学
材料科学
计算机科学
人工智能
物理
机器学习
化学
统计
计算化学
操作系统
复合材料
微观结构
声学
出处
期刊:Simulation
[SAGE]
日期:2021-03-01
卷期号:97 (6): 383-425
被引量:8
标识
DOI:10.1177/0037549721995574
摘要
Empirical equations, thermodynamics frameworks, and neural network modeling have been developed to predict steel martensite start temperature, [Formula: see text], but they might not tend to generalize well when composition includes a wide range of alloying elements. In this study, we develop the Gaussian process regression (GPR) model to shed light on the relationship between alloying elements and [Formula: see text] temperature for steels. A total of 1119 steels with [Formula: see text] ranging from 153 K to 938 K are examined. The model has a high degree of accuracy and stability, contributing to fast low-cost [Formula: see text] temperature estimations.
科研通智能强力驱动
Strongly Powered by AbleSci AI