☆ 4.1 Article

Creep Life Predictions by Machine Learning Methods for Ferritic Heat Resistant Steels

TETSU TO HAGANE-JOURNAL OF THE IRON AND STEEL INSTITUTE OF JAPAN (2022)

A machine learning aided interpretable model for rupture strength prediction in Fe-based martensitic and austenitic alloys

Osman Mamun et al.

Summary: This article focuses on parameterizing the creep rupture strength of 9-12% Cr FMA and austenitic stainless steel, achieving high predictive performance through a gradient boosting machine model. The Shapley value analysis is used to compute feature importance and understand the complex interplay of different features.

SCIENTIFIC REPORTS (2021)

添加到收藏夹

Article Materials Science, Multidisciplinary

A machine-learning approach to predict creep properties of Cr-Mo steel with time-temperature parameters

Jiaqi Wang et al.

Summary: The study explores the idea of using machine learning to predict the creep life of Cr-Mo steel by transforming creep life into time-temperature parameters, which improved prediction accuracy. Random forest had the best accuracy and robustness when predicting creep life using Manson-Succop parameter as the target feature, providing new insights for analyzing the main influencing features to creep property of Cr-Mo steel.

JOURNAL OF MATERIALS RESEARCH AND TECHNOLOGY-JMR&T (2021)

添加到收藏夹

Article Materials Science, Multidisciplinary

Machine learning augmented predictive and generative model for rupture life in ferritic and austenitic steels

Osman Mamun et al.

Summary: In this study, a direct rupture life parameterization using a gradient boosting algorithm was shown to effectively train machine learning models for highly accurate prediction of rupture life in various alloys. The Shapley value was utilized to quantify feature importance, making the model interpretable by identifying the impact of different features on performance. Additionally, a generative model based on a variational autoencoder was used to sample hypothetical synthetic candidate alloys from the learned joint distribution.

NPJ MATERIALS DEGRADATION (2021)

添加到收藏夹

Article Materials Science, Multidisciplinary

Mapping Multivariate Influence of Alloying Elements on Creep Behavior for Design of New Martensitic Steels

Amit K. Verma et al.

METALLURGICAL AND MATERIALS TRANSACTIONS A-PHYSICAL METALLURGY AND MATERIALS SCIENCE (2019)

添加到收藏夹

Review Materials Science, Multidisciplinary

Catalog of NIMS creep data sheets

Kota Sawada et al.

SCIENCE AND TECHNOLOGY OF ADVANCED MATERIALS (2019)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

ranger: A Fast Implementation of Random Forests for High Dimensional Data in C plus plus and R

Marvin N. Wright et al.

JOURNAL OF STATISTICAL SOFTWARE (2017)

添加到收藏夹

Creep Life Predictions by Machine Learning Methods for Ferritic Heat Resistant Steels

相关参考文献

A machine learning aided interpretable model for rupture strength prediction in Fe-based martensitic and austenitic alloys

A machine-learning approach to predict creep properties of Cr-Mo steel with time-temperature parameters

Machine learning augmented predictive and generative model for rupture life in ferritic and austenitic steels

Mapping Multivariate Influence of Alloying Elements on Creep Behavior for Design of New Martensitic Steels

Catalog of NIMS creep data sheets

ranger: A Fast Implementation of Random Forests for High Dimensional Data in C plus plus and R

导出引文

分享论文