Machine Learning in the Analysis of Solid Deformation, Fatigue and Fracture
Deformation, Fracture, and Fatigue
- 1st Edition - January 1, 2026
- Imprint: Elsevier
- Authors: Guozheng Kang, Qianhua Kan, Xu Zhang, Ya-Nan Hu, Xiangyu Li
- Language: English
- Paperback ISBN:9 7 8 - 0 - 4 4 3 - 4 4 6 1 5 - 3
- eBook ISBN:9 7 8 - 0 - 4 4 3 - 4 4 6 1 6 - 0
Machine Learning for Solid Mechanics fills a clear gap in literature by applying machine learning to deformation, fatigue, and fracture analysis in solid mechanics. The book’s… Read more
Purchase options
Machine Learning for Solid Mechanics fills a clear gap in literature by applying machine learning to deformation, fatigue, and fracture analysis in solid mechanics. The book’s focus on complex mechanisms and coupling phenomena, discussed with practical examples, makes it a valuable resource for advanced researchers. Practical examples and case studies enable readers to understand both the underlying engineering problems and the application of machine learning methods to enhance fatigue life prediction analysis for solid materials and structures.
- Provides a systematic summary of machine learning methods applied to solid deformation, fatigue and fracture analysis
- Fills a clear gap in the literature by applying machine learning to deformation, fatigue, and fracture analysis in solid mechanics
- Introduces the application of physics-informed machine learning in multiaxial fatigue life prediction
- Introduces the application of physics-informed machine learning in predicting the fatigue life of additively manufactured metallic metals
- Includes numerous practical examples and case studies and draws on the authors’ extensive experience in multiscale simulation of solid materials and fatigue life prediction
Researchers and post-graduate students in the fields of mechanics, mechanical engineering, civil engineering and aerospace engineering; engineering professionals
1: Introduction
1.1 Introduction
1.2 Brief introduction to machine learning
1.3 Application of machine learning in solid mechanics
1.3.1 Multiscale modeling
1.3.2 Fracture analysis
1.3.3 Fatigue life-prediction
1.3.4 Structure analysis
1.4 Arrangement of chapters References
2: Introduction to the algorithm and procedure of machine learning methods
2.1 Basic algorithm
2.1.1 Basic supervised learning algorithm
2.1.2 Neural network and deep learning
2.2 Procedure for machine learning methods
2.2.1 Data preparation
2.2.2 Model construction
2.2.3 Model assessment
2.3 Summary References
3: Machine learning based multiscale plasticity analysis
3.1 Machine learning based atomic simulations
3.1.1 Deep learning based potential
3.1.2 Analysis of the chemical order strengthening mechanism of alloys
3.2 Machine learning based discrete dislocation dynamics simulations
3.2.1 Compression of single crystal micro-column
3.2.2 Simulations and discussion
3.3 Machine learning based crystal plasticity finite element simulations
3.3.1 Parameter determination in crystal plasticity model
3.3.2 Results and discussion
3.4 Machine learning based constitutive models
3.4.1 Machine learning based strain rate-temperature coupled constitutive model
3.4.2 Machine learning based yielding function
3.5 Summary References
4: Machine learning based fracture analysis of solid materials
4.1 Prediction of crack source
4.1.1 Prediction of damage initiation in the grain boundary of magnesium alloy
4.1.2 Clarification of crack initiation source in the additive manufactured titanium alloy
4.2 Study of crack propagation
4.2.1 Prediction of the propagation rate of short crack
4.2.2 Prediction of crack propagation path
4.3 Study of fracture strength and fracture toughness
4.3.1 Prediction of fracture strength
4.3.2 Prediction of fracture toughness
4.4 Summary References
5: Machine learning based fatigue life prediction of solid materials
5.1 Neural network-based fatigue life prediction model
5.1.1 Full connected neural network-based fatigue life prediction model
5.1.2 Long short-term memory network based fatigue life-prediction model
5.1.3 Results and discussion
5.2 Self-attention mechanism based fatigue life prediction model
5.2.1 Self-attention machine learning method
5.2.2 Results and discussion
5.3 Physics-informed machine learning based fatigue life prediction model
5.3.1 Physics-informed machine learning method
5.3.2 Results and discussion
5.4 Domain knowledge induced symbolic regression based fatigue life prediction of additive manufactured metals
5.4.1 Establishment of dataset
5.4.2 Domain knowledge induced symbolic regression
5.4.3 Results and discussion
5.5 Summary References
6: Machine learning based solid structure analyses
6.1 Machine learning based deformation analysis of solid structures
6.1.1 Prediction of process induced deformation in the composites
6.1.2 Prediction of three-dimensional deformation in the stiffened plate
6.1.3 Physics-informed machine learning based prediction of beam buckling
6.2 Machine learning based fatigue analysis of engineering structures
6.2.1 Fatigue life prediction of notched specimen
6.2.2 Bending fatigue life prediction of thin film
6.2.3 Fatigue life prediction of high strength belt
6.3 Machine learning based fracture analysis of engineering structures
6.3.1 Crack propagation prediction of concrete
6.3.2 Clarification of fatigue crack propagation in metallic structures
6.3.3 Automatic assessment of fracture in steel structures References
1.1 Introduction
1.2 Brief introduction to machine learning
1.3 Application of machine learning in solid mechanics
1.3.1 Multiscale modeling
1.3.2 Fracture analysis
1.3.3 Fatigue life-prediction
1.3.4 Structure analysis
1.4 Arrangement of chapters References
2: Introduction to the algorithm and procedure of machine learning methods
2.1 Basic algorithm
2.1.1 Basic supervised learning algorithm
2.1.2 Neural network and deep learning
2.2 Procedure for machine learning methods
2.2.1 Data preparation
2.2.2 Model construction
2.2.3 Model assessment
2.3 Summary References
3: Machine learning based multiscale plasticity analysis
3.1 Machine learning based atomic simulations
3.1.1 Deep learning based potential
3.1.2 Analysis of the chemical order strengthening mechanism of alloys
3.2 Machine learning based discrete dislocation dynamics simulations
3.2.1 Compression of single crystal micro-column
3.2.2 Simulations and discussion
3.3 Machine learning based crystal plasticity finite element simulations
3.3.1 Parameter determination in crystal plasticity model
3.3.2 Results and discussion
3.4 Machine learning based constitutive models
3.4.1 Machine learning based strain rate-temperature coupled constitutive model
3.4.2 Machine learning based yielding function
3.5 Summary References
4: Machine learning based fracture analysis of solid materials
4.1 Prediction of crack source
4.1.1 Prediction of damage initiation in the grain boundary of magnesium alloy
4.1.2 Clarification of crack initiation source in the additive manufactured titanium alloy
4.2 Study of crack propagation
4.2.1 Prediction of the propagation rate of short crack
4.2.2 Prediction of crack propagation path
4.3 Study of fracture strength and fracture toughness
4.3.1 Prediction of fracture strength
4.3.2 Prediction of fracture toughness
4.4 Summary References
5: Machine learning based fatigue life prediction of solid materials
5.1 Neural network-based fatigue life prediction model
5.1.1 Full connected neural network-based fatigue life prediction model
5.1.2 Long short-term memory network based fatigue life-prediction model
5.1.3 Results and discussion
5.2 Self-attention mechanism based fatigue life prediction model
5.2.1 Self-attention machine learning method
5.2.2 Results and discussion
5.3 Physics-informed machine learning based fatigue life prediction model
5.3.1 Physics-informed machine learning method
5.3.2 Results and discussion
5.4 Domain knowledge induced symbolic regression based fatigue life prediction of additive manufactured metals
5.4.1 Establishment of dataset
5.4.2 Domain knowledge induced symbolic regression
5.4.3 Results and discussion
5.5 Summary References
6: Machine learning based solid structure analyses
6.1 Machine learning based deformation analysis of solid structures
6.1.1 Prediction of process induced deformation in the composites
6.1.2 Prediction of three-dimensional deformation in the stiffened plate
6.1.3 Physics-informed machine learning based prediction of beam buckling
6.2 Machine learning based fatigue analysis of engineering structures
6.2.1 Fatigue life prediction of notched specimen
6.2.2 Bending fatigue life prediction of thin film
6.2.3 Fatigue life prediction of high strength belt
6.3 Machine learning based fracture analysis of engineering structures
6.3.1 Crack propagation prediction of concrete
6.3.2 Clarification of fatigue crack propagation in metallic structures
6.3.3 Automatic assessment of fracture in steel structures References
- Edition: 1
- Published: January 1, 2026
- Imprint: Elsevier
- Language: English
GK
Guozheng Kang
Guozheng Kang is Chair and Professor of Mechanics at Southwest Jiaotong University, China. He is also vice president of Southwest Jiaotong University. His research activities focus on cyclic plasticity and visco-plasticity, fatigue failure and life prediction, low-cycle fatigue, multiaxial fatigue, fretting fatigue, rolling contact fatigue and ratcheting-fatigue interaction for metallic and polymeric materials, as well as the thermo-mechanical fatigue of shape memory alloys. He has been the author/co-author of more than 400 research publications in refereed international journals and conference proceedings
Affiliations and expertise
Southwest Jiaotong University, ChinaQK
Qianhua Kan
Dr Xu Zhang is a Professor at Southwest Jiaotong University, China, and Doctoral Supervisor. He was selected for the National High-Level Young Talent Program (in 2022) and is a Humboldt Fellow. He is also a recipient of the International Journal of Plasticity Young Researcher Award. His research primarily focuses on multiscale mechanics of advanced metallic materials. He has published over 90 SCI papers
Affiliations and expertise
Southwest Jiaotong University, ChinaXZ
Xu Zhang
Dr Xu Zhang is a Professor at Southwest Jiaotong University, and Doctoral Supervisor. He was selected for the National High-Level Young Talent Program (in 2022) and is a Humboldt Fellow. He is also a recipient of the International Journal of Plasticity Young Researcher Award. His research primarily focuses on multiscale mechanics of advanced metallic materials. He has published over 90 SCI papers
Affiliations and expertise
Southwest Jiaotong University, ChinaYH
Ya-Nan Hu
Dr Ya-Nan Hu is an Associate Professor at Southwest Jiaotong University. Dr Hu’s research focuses on the fatigue and fracture behavior of welding and additive manufacturing materials, as well as in situ characterization of material fatigue damage behavior using advanced synchrotron radiation. As the first author or corresponding author, she has published over 20 papers
Affiliations and expertise
Southwest Jiaotong University, China