铸造2025，Vol.74Issue(7)：905-914,10.
基于人工神经网络的镍基单晶高温合金蠕变寿命预测模型及应用
Creep Life Prediction Model of Nickel-Based Single Crystal Superalloy Based on Artificial Neural Network and Its Application
李春雨 1刘纪德 2张文颖 1王家健 2朱崇伟 2李金国2
作者信息
- 1. 东北大学材料科学与工程学院,辽宁沈阳 110004||中国科学院金属研究所,辽宁沈阳 110000
- 2. 中国科学院金属研究所,辽宁沈阳 110000
- 折叠
摘要
Abstract
Nickel-based single crystal superalloys are widely used in hot-end components of aeroengines due to their superior high temperature strength.Creep life is an important indicator to measure the performance of single crystal superalloys.This study performed the creep life prediction of superalloy through the establishment of ANN machine learning model.The parameters of microstructure were applied to increase the accuracy,which reduced the overfitting tendency and improved the generalization ability of the model.The model was utilized to optimize the DD4500 alloy composition through inverse design,resulting in a significant improvement in the creep life of the newly designed alloy compared to the original alloy.This success further validates the effectiveness of applying machine learning techniques in materials science.关键词
镍基单晶高温合金/蠕变寿命预测/机器学习/ANN模型Key words
nickel-based single crystal superalloy/creep life prediction/machine learning/ANN model分类
矿业与冶金引用本文复制引用
李春雨,刘纪德,张文颖,王家健,朱崇伟,李金国..基于人工神经网络的镍基单晶高温合金蠕变寿命预测模型及应用[J].铸造,2025,74(7):905-914,10.
