[1]刘芳宁,王越,孙瑞侠.针对高温合金微观组织-拉伸性能关系的机器学习预测模型[J].中国材料进展,2022,41(11):938-946.[doi:10.7502/j.issn.1674-3962.202101024]
　LIU Fangning,WANG Yue,SUN Ruixia.Machine Learning Prediction Model for Microstructure-Tensile Properties Relationship of Superalloys[J].MATERIALS CHINA,2022,41(11):938-946.[doi:10.7502/j.issn.1674-3962.202101024]
点击复制

针对高温合金微观组织-拉伸性能关系的机器学习预测模型()
分享到：

中国材料进展[ISSN:1674-3962/CN:61-1473/TG]

卷:
41
期数:
2022年第11期
页码:
938-946
栏目:
出版日期:
2022-11-30

文章信息/Info

Title:
Machine Learning Prediction Model for Microstructure-Tensile Properties Relationship of Superalloys
文章编号:
1674-3962(2022)11-0938-09
作者:
刘芳宁; 王越; 孙瑞侠
（中国航发北京航空材料研究院，北京 100095）
Author(s):
LIU Fangning;  WANG Yue;  SUN Ruixia
(AECC Beijing Institute of Aeronautical Materials, Beijing 100095, China)
关键词:
机器学习; 相含量; 力学性能; 高温合金; 材料科学
Keywords:
machine learning;  phase content;  mechanical properties;  superalloy;  material science
分类号:
TP181；TG132.3+3
DOI:
10.7502/j.issn.1674-3962.202101024
文献标志码:
A
摘要:
采用传统“试错法”揭示高温合金微观组织和性能之间的关系具有成本高、周期长等特点，难以满足材料设计、研发和应用的快速发展。以高温合金K4169为基础，采用机器学习的方法建立了材料微观组织和力学性能之间关系的模型。首先设计实验，通过改变合金成分和热处理制度，获取了70组微观组织变化数据；其次通过室温和高温拉伸实验对不同微观组织的合金力学性能进行测量，分析了成分和热处理制度变化对合金室温、高温力学性能的影响；最后分别采用支持向量回归、随机森林回归、K最近邻回归、多层感知器4种算法建立预测模型，预测了微观组织中γ相、γ′相、γ″相、δ相、Laves相和碳化物含量对合金室温、高温拉伸性能的影响，并采用交叉验证的方式验证了模型的准确性。结果表明，多层感知器模型对合金室温拉伸强度的预测结果均方误差为0.17、平均绝对误差为0.32、相关系数为0.95、决定系数为0.85，对合金高温拉伸强度的预测结果均方误差为0.14、平均绝对误差为0.29、相关系数为0.97、决定系数为0.91，与其余3种算法建立的模型相比，多层感知器模型的预测结果更准确。
Abstract:
The traditional “trial-and-error” method is used to reveal the relationship between microstructure and properties of superalloys, which is difficult to meet the rapid development of material design, research and development and application due to its high cost and long cycle. In this paper, a model for the relationship between microstructure and properties of superalloy K4169 was established by machine learning. Firstly, 70 groups of microstructures were obtained by changing the alloy composition and heat treatment system. Secondly, the mechanical properties of the alloys were measured by tensile experiments at room temperature and high temperature, and the effects of composition and heat treatment on the mechanical properties were analyzed. Finally, support vector machine regression (SVR), random forest regression (RFR), K-nearest neighbor node regression (KNR) and multi-layer perceptron (MLP) were used to establish prediction models to predict the effects of γ phase, γ′ phase, γ″ phase, δ phase, Laves phase and carbide content on tensile properties at room and high temperature. The accuracy of the model was verified by cross validation. The results show that the mean squared error of the MLP model for the prediction result of the alloy room temperature tensile strength is 0.17, the mean absolute error is 0.32, the correlation coefficient is 0.95, and the decision coefficient is 0.85.And the mean squared error for the alloy high-temperature tensile strength is 0.14, the mean absolute error is 0.29, the correlation coefficient is 0.97, and the decision coefficient is 0.91.Compared with the other three models, the prediction results of MLP are more accurate.

备注/Memo

备注/Memo:
收稿日期：2021-01-29 修回日期：2021-03-29 基金项目：国防科工局基础性军工科研院所稳定支持项目（KZ0C191707）第一作者：刘芳宁，女，1991年生，工程师， Email：lfn2015@163.com
更新日期/Last Update: 2022-10-26