Creep–Fatigue Life Prediction of GH4169 Specimens Under Uniaxial and Multiaxial Conditions by Integrating Continuum Damage Mechanics and Machine Learning

ABSTRACT Creep–fatigue interactions in aeroengine hot‐section components present significant challenges for life design and structural integrity assessment. This study proposes a framework integrating continuum damage mechanics (CDM) with machine learning (ML) to predict the creep–fatigue life of GH4169 specimens under both uniaxial and multiaxial conditions at 650°C. CDM simulations incorporating a multiaxial ductility factor generate a physics‐informed dataset covering different strain ranges, hold times, and stress states for smooth and hole specimens. Artificial neural network, random forest, and support vector machine (SVM) models are developed for crack initiation life prediction and validated against experimental data. The SVM model provides the best predictive performance. Based on the trained SVM model, the nonlinear degradation of creep–fatigue life and its strong sensitivity to hold time, particularly in hole specimens, are further analyzed. This approach provides an efficient and practical methodology for creep–fatigue life assessment of GH4169 components under complex stress states.

Authors

Institutions

Publication Details

Journal
Fatigue & Fracture of Engineering Materials & Structures
Published
2026-11-13
DOI
https://doi.org/10.1111/ffe.70531
Primary Topic
High Temperature Alloys and Creep
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Creep–Fatigue Life Prediction of GH4169 Specimens Under Uniaxial and Multiaxial Conditions by Integrating Continuum Damage Mechanics and Machine Learning

Jian‐Feng Wen, Xiancheng Zhang, Ting Ye, Wei Zeng et al.
Fatigue & Fracture of Engineering Materials & Structures
High Temperature Alloys and Creep
article

Creep–Fatigue Life Prediction of GH4169 Specimens Under Uniaxial and Multiaxial Conditions by Integrating Continuum Damage Mechanics and Machine Learning

Jian‐Feng Wen, Xiancheng Zhang, Ting Ye, Wei Zeng, Kai Yang, Shan‐Tung Tu, Hua‐Yan Hu, Jia‐Ning Liu, Cheng‐Cheng Zhang, Zhong‐Lun Dai
article en

Abstract

ABSTRACT Creep–fatigue interactions in aeroengine hot‐section components present significant challenges for life design and structural integrity assessment. This study proposes a framework integrating continuum damage mechanics (CDM) with machine learning (ML) to predict the creep–fatigue life of GH4169 specimens under both uniaxial and multiaxial conditions at 650°C. CDM simulations incorporating a multiaxial ductility factor generate a physics‐informed dataset covering different strain ranges, hold times, and stress states for smooth and hole specimens. Artificial neural network, random forest, and support vector machine (SVM) models are developed for crack initiation life prediction and validated against experimental data. The SVM model provides the best predictive performance. Based on the trained SVM model, the nonlinear degradation of creep–fatigue life and its strong sensitivity to hold time, particularly in hole specimens, are further analyzed. This approach provides an efficient and practical methodology for creep–fatigue life assessment of GH4169 components under complex stress states.

Fatigue & Fracture of Engineering Materials & Structures
Commercial Aircraft Corporation of China (China) (CN), East China University of Science and Technology (CN), Longyan University (CN)
National Natural Science Foundation of China, National Key Research and Development Program of China
Industry, innovation and infrastructure
High Temperature Alloys and Creep
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon