A deep neural network approach combined with Findley parameter to predict fretting fatigue crack initiation lifetime
Source abstract
Abstract
In the aviation field, the crack initiation stage could be the dominant one of the whole damage failure process of components subjecting to fretting fatigue. Thus, getting an accurate prediction of the crack initiation lifetime become an important topic in research of fretting fatigue problems. In this work, a new prediction method for fretting fatigue crack initiation lifetime is proposed, which is based on Deep Neural Network (DNN), Findley Parameter (FP) and Finite Element Method (FEM). Input features are shear stress amplitude and maximum normal stress in the critical plane, and crack initiation lifetime is set as the output target. Dropout and bootstrapping are considered to improve the performance of DNN. Through comparative analysis, it is shown that this new proposed approach can effectively predict the fretting fatigue crack initiation lifetime. The prediction accuracy and stability are greatly improved compared with the theoretical formulation based on FP.
Source: openaire · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Mechanical stress and fatigue analysis · Fatigue and fracture mechanics · Electrical Contact Performance and Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (47)
Show source-provided references
1. Recent developments in the understanding of fretting fatigue10.1016/j.engfracmech.2005.01.013 ↗
2. Fretting fatigue in dovetail blade roots: Experiment and analysis10.1016/j.triboint.2006.02.044 ↗
3. Analysis of crack initiation10.1007/978-94-015-8281-0_9 ↗
4. Fretting fatigue crack nucleation: a review10.1016/j.triboint.2018.01.029 ↗
5. A theory for the effect of mean stress on fatigue of metals under combined torsion and axial load or bending10.1115/1.4008327 ↗
6. Critical plane approaches for multiaxial fatigue damage assessment
7. Evaluation of an energy-based approach and a critical plane approach for predicting constant amplitude multiaxial fatigue life10.1016/S0142-1123(99)00111-5 ↗
8. A general criterion for high cycle multiaxial fatigue failure10.1111/j.1460-2695.1991.tb00673.x ↗
9. On the use of multiaxial fatigue criteria for fretting fatigue life assessment10.1016/j.ijfatigue.2007.02.018 ↗
10. A shear stress-based parameter for fretting fatigue crack initiation10.1046/j.1460-2695.2001.00412.x ↗
11. Fretting fatigue crack initiation mechanism in Ti–6Al–4V10.1046/j.1460-2695.2002.00549.x ↗
12. The effect of rapidly varying contact stress fields on fretting fatigue10.1016/S0142-1123(01)00191-8 ↗
13. Fretting fatigue crack initiation behavior using process volume approach and finite element analysis10.1016/S0301-679X(02)00139-1 ↗
14. Initiation criteria in fretting fatigue with spherical contact10.1016/j.ijfatigue.2004.05.004 ↗
15. Effect of stress gradient and quadrant averaging on fretting fatigue crack initiation angle and life10.1016/j.triboint.2018.10.036 ↗
16. From uni-to multi-axial fretting-fatigue crack nucleation: Development of a stress-gradient-dependent critical distance approach10.1016/j.ijfatigue.2013.05.016 ↗
17. On the prediction of high-cycle fretting fatigue strength: Theory of critical distances vs. hot-spot approach10.1016/j.engfracmech.2007.03.026 ↗
18. Geometrical effects in fatigue: a unifying theoretical model10.1016/S0142-1123(99)00007-9 ↗
19. Artificial neural network combined with damage parameters to predict fretting fatigue crack initiation lifetime10.1016/j.triboint.2022.107854 ↗
20. An energy approach to the solution of partial differential equations in computational mechanics via machine learning: Concepts, implementation and applications10.1016/j.cma.2019.112790 ↗
21. A physics-informed neural network technique based on a modified loss function for computational 2D and 3D solid mechanics
22. Chakraborty A, Anitescu C, Goswami S, et al. Variational energy based XPINNs for phase field analysis in brittle fracture. arXiv preprint arXiv:2207.02307, 2022.
23. Efficient deep learning for gradient-enhanced stress dependent damage model10.3390/app10072556 ↗
24. Han S, Khatir S, Abdel Wahab M. Application of Machine Learning for Fatigue and Fretting Fatigue[C]//Tenth international conference on Fracture, Fatigue and Wear (FFW 2022). 2022.10.1007/978-981-16-8810-2 ↗
25. A machine learning approach to the prediction of fretting fatigue life10.1016/j.triboint.2019.105913 ↗
26. A hybrid ANN-multiaxial fatigue nonlocal model to estimate fretting fatigue life for aeronautical Al alloys
27. A generalized ANN-multiaxial fatigue nonlocal approach to compute fretting fatigue life for aeronautical Al alloys
28. Parametric deep energy approach for elasticity accounting for strain gradient effects10.1016/j.cma.2021.114096 ↗
29. Machine learning assisted multiscale modeling of composite phase change materials for Li-ion batteries’ thermal management10.1016/j.ijheatmasstransfer.2021.121199 ↗
30. Fatigue life prediction of a L-PBF component in Ti-6Al-4V using sample data, FE-based simulations and machine learning10.1016/j.ijfatigue.2022.107276 ↗
31. Transfer learning enhanced physics informed neural network for phase-field modeling of fracture10.1016/j.tafmec.2019.102447 ↗
32. A review of artificial neural networks in the constitutive modeling of composite materials10.1016/j.compositesb.2021.109152 ↗
33. Machine learning predicts fretting and fatigue key mechanical properties10.1016/j.ijmecsci.2021.106949 ↗
34. Observation, analysis and prediction of fretting fatigue in 2024–T351 aluminum alloy10.1016/S0043-1648(98)00264-6 ↗
35. Fretting: review on the numerical simulation and modeling of wear, fatigue and fracture
36. Fretting fatigue crack initiation lifetime predictor tool: Using damage mechanics approach10.1016/j.triboint.2012.10.028 ↗
37. Estimation of Fretting Fatigue Lifetime in Heterogeneous Material based on Microstructure Characterization and Multi-scale Homogenization
38. Investigation on fretting fatigue crack initiation in heterogenous materials using a hybrid of multiscale homogenization and direct numerical simulation10.1016/j.triboint.2022.107470 ↗
39. The effect of a critical micro-void defect on fretting fatigue crack initiation in heterogeneous material using a multiscale approach10.1016/j.triboint.2019.105909 ↗
40. Fretting fatigue analysis of FGM coating under out-of-phase loadings10.1016/j.triboint.2019.01.049 ↗
41. Gao H, Pei J, Huang H. Demystifying dropout[C]//International Conference on Machine Learning. PMLR, 2019: 2112-2121.
42. A numerical investigation on critical plane orientation and initiation lifetimes in fretting fatigue under out of phase loading conditions10.1016/j.triboint.2017.05.036 ↗
43. Deep learning10.1038/nature14539 ↗
44. Khayatazad · 2023
45. On the integration of domain knowledge and branching neural network for fatigue life prediction with small samples10.1016/j.ijfatigue.2023.107648 ↗
46. A physics-informed neural network approach to fatigue life prediction using small quantity of samples10.1016/j.ijfatigue.2022.107270 ↗
47. A physically consistent framework for fatigue life prediction using probabilistic physics-informed neural network10.1016/j.ijfatigue.2022.107234 ↗