Study of Hybrid Machine Learning Multiaxial Low‐Cycle Fatigue Life Prediction Model of CP‐Ti
Source abstract
Abstract
ABSTRACT Symmetric and asymmetric multiaxial low‐cycle fatigue tests were conducted on commercially pure titanium under different control modes and multiaxial strain/stress ratios to establish a reliable hybrid physics and data‐driven method. Optimized analysis formula–based models are proposed to provide reliable physical information first. Based on the dataset enhanced by the nonlinear variational autoencoder method, a hybrid VAE‐ANN model is established and trained, developed using the Pearson correlation coefficient analysis and Leaky ReLU activation function. Through a series of fatigue life prediction validations under both symmetric and asymmetric loading conditions, the VAE‐ANN model demonstrates excellent prediction accuracy, broad generalization capability, and strong compatibility, achieving the lowest average absolute relative error of 6.76% under symmetric and 22.61% under asymmetric loading conditions.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Fatigue and fracture mechanics · Mechanical Failure Analysis and Simulation · High Temperature Alloys and Creep
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Mechanical and Power Engineering Nanjing Tech University Nanjing China
Funding
National Natural Science Foundation of China
References (45)
Show source-provided references
1. 10.1111/ffe.1318210.1111/ffe.13182 ↗
2. 10.1111/ffe.1367510.1111/ffe.13675 ↗
3. 10.1016/j.engfailanal.2008.08.00810.1016/j.engfailanal.2008.08.008 ↗
4. 10.1016/j.engfailanal.2011.05.00810.1016/j.engfailanal.2011.05.008 ↗
5. 10.1016/j.ijfatigue.2022.10702210.1016/j.ijfatigue.2022.107022 ↗
6. 10.1111/ffe.1227210.1111/ffe.12272 ↗
7. 10.1016/j.ijfatigue.2010.05.00610.1016/j.ijfatigue.2010.05.006 ↗
8. 10.1016/j.pmatsci.2023.10112610.1016/j.pmatsci.2023.101126 ↗
9. 10.1016/j.prostr.2017.07.04910.1016/j.prostr.2017.07.049 ↗
10. 10.1111/j.1460-2695.2011.01585.x10.1111/j.1460-2695.2011.01585.x ↗
11. 10.1016/j.ijfatigue.2022.10694710.1016/j.ijfatigue.2022.106947 ↗
12. Biaxial low‐Cycle Fatigue Fracture of 316 Stainless Steel at Elevated Temperature
13. 10.1111/j.1460-2695.1988.tb01169.x10.1111/j.1460-2695.1988.tb01169.x ↗
14. 10.1016/j.ijfatigue.2021.10671610.1016/j.ijfatigue.2021.106716 ↗
15. 10.1016/j.jmst.2024.01.08610.1016/j.jmst.2024.01.086 ↗
16. 10.1016/j.engfailanal.2024.10842310.1016/j.engfailanal.2024.108423 ↗
17. 10.1016/j.ijfatigue.2023.10786810.1016/j.ijfatigue.2023.107868 ↗
18. 10.1016/j.ijfatigue.2022.10727010.1016/j.ijfatigue.2022.107270 ↗
19. 10.1016/j.ijfatigue.2022.10748310.1016/j.ijfatigue.2022.107483 ↗
20. 10.1016/j.engfailanal.2023.10712810.1016/j.engfailanal.2023.107128 ↗
21. 10.1016/j.ijfatigue.2022.10727410.1016/j.ijfatigue.2022.107274 ↗
22. 10.1016/j.ijfatigue.2023.10760910.1016/j.ijfatigue.2023.107609 ↗
23. 10.1016/j.commatsci.2023.11243410.1016/j.commatsci.2023.112434 ↗
24. 10.1016/j.engfracmech.2024.10996110.1016/j.engfracmech.2024.109961 ↗
25. 10.1016/j.ijfatigue.2022.10674810.1016/j.ijfatigue.2022.106748 ↗
26. 10.1016/j.ymssp.2024.11112010.1016/j.ymssp.2024.111120 ↗
27. 10.1016/j.ijfatigue.2024.10818710.1016/j.ijfatigue.2024.108187 ↗
28. 10.1016/j.engfracmech.2023.10924210.1016/j.engfracmech.2023.109242 ↗
29. 10.1063/5.003337610.1063/5.0033376 ↗
30. 10.1016/j.ijfatigue.2017.07.01810.1016/j.ijfatigue.2017.07.018 ↗
31. 10.1111/ffe.1387010.1111/ffe.13870 ↗
32. 10.1016/j.engfracmech.2021.10793010.1016/j.engfracmech.2021.107930 ↗
33. 10.1016/j.ijfatigue.2020.10581810.1016/j.ijfatigue.2020.105818 ↗
34. 10.1016/j.ijfatigue.2019.10535010.1016/j.ijfatigue.2019.105350 ↗
35. 10.1016/j.proeng.2014.06.27010.1016/j.proeng.2014.06.270 ↗
36. 10.1016/j.ijfatigue.2022.10686810.1016/j.ijfatigue.2022.106868 ↗
37. 10.1016/j.engfracmech.2023.10954210.1016/j.engfracmech.2023.109542 ↗
38. 10.1016/j.ijfatigue.2018.07.03610.1016/j.ijfatigue.2018.07.036 ↗
39. A Stress‐Strain Function for the Fatigue of Metals
40. 10.1016/j.triboint.2019.10591310.1016/j.triboint.2019.105913 ↗
41. 10.1016/j.ijfatigue.2018.02.00710.1016/j.ijfatigue.2018.02.007 ↗
42. 10.1108/ACMM-10-2019-219010.1108/ACMM-10-2019-2190 ↗
43. 10.1016/j.ijfatigue.2023.10776310.1016/j.ijfatigue.2023.107763 ↗
44. 10.1016/j.ast.2021.10708410.1016/j.ast.2021.107084 ↗
45. 10.1016/j.ijfatigue.2010.02.01610.1016/j.ijfatigue.2010.02.016 ↗