Machine learning based very-high-cycle fatigue life prediction of Ti-6Al-4V alloy fabricated by selective laser melting
Source abstract
Abstract
Few machine learning (ML) models were applied for very-high-cycle fatigue (VHCF) analysis and these methods encounter limitations in data sparsity and overfitting. The present work aims to overcome data sparsity and propose an easy-to-use and nonredundant ML model for VHCF analysis. Monte Carlo simulation (MCs) is run to enlarge dataset size and a ML method is proposed to investigate the synergic influence of defect size, depth, location and build orientation on Ti-6Al-4V. The coefficient factor that indicates the percentage variation between the predicted and experimental fatigue lives can reach up to 0.98, meaning that the model demonstrates good prediction accuracy.
Source: openaire · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Additive Manufacturing Materials and Processes · Welding Techniques and Residual Stresses · Titanium Alloys Microstructure and Properties
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (41)
Show source-provided references
1. Efficient determination of influence factors in fatigue of additive manufactured metals10.1016/j.prostr.2017.12.020 ↗
2. Very-high-cycle fatigue behavior of Ti-6Al-4V manufactured by selective laser melting: effect of build orientation10.1016/j.ijfatigue.2020.105628 ↗
3. Very-high-cycle fatigue behavior of AlSi10Mg manufactured by selective laser melting: effect of build orientation and mean stress10.1016/j.ijfatigue.2020.105696 ↗
4. Machine learning prediction of mechanical properties of concrete: critical review10.1016/j.conbuildmat.2020.119889 ↗
5. Gialanella S, Malandruccolo A. Titanium and titanium alloys. In: Aerospace alloys. Topics in mining, metallurgy and materials engineering. Cham: Springer; 2020. https://doi.org/10.1007/978-3-030-24440-8_4.10.1007/978-3-030-24440-8 ↗
6. Mechanical properties of biomedical titanium alloys10.1016/S0921-5093(97)00806-X ↗
7. Titanium alloy production technology, market prospects and industry development10.1016/j.matdes.2010.09.011 ↗
8. Additive manufacturing technologies: state of the art and trends10.1080/00207543.2015.1115909 ↗
9. Rapid prototyping or rapid production? 3D printing processes move industry towards the latter10.1108/01445150310501190 ↗
10. Rapid prototyping for direct manufacture10.1108/EUM0000000005753 ↗
11. Correlation between porosity and processing parameters in TiAl6V4 produced by selective laser melting10.1016/j.matdes.2016.05.070 ↗
12. Additive manufacturing of Ti6Al4V alloy: a review10.1016/j.matdes.2018.107552 ↗
13. A study of the microstructural evolution during selective laser melting of Ti–6Al–4V10.1016/j.actamat.2010.02.004 ↗
14. Effect of build orientation on mechanical properties and microstructure of Ti-6Al-4V manufactured by selective laser melting10.1007/s11661-019-05322-w ↗
15. A novel approach based on the elastoplastic fatigue damage and machine learning models for life prediction of aerospace alloy parts fabricated by additive manufacturing10.1016/j.ijfatigue.2020.106089 ↗
16. Fatigue life prediction of aluminum alloy 6061 based on defects analysis10.1016/j.ijfatigue.2021.106189 ↗
17. Low cycle fatigue and creep–fatigue interaction behavior of 316L(N) stainless steel and life prediction by artificial neural network approach10.1016/S0142-1123(03)00064-1 ↗
18. Fracture mechanics and mechanical fault detection by artificial intelligence methods: a review10.1016/j.engfailanal.2017.07.011 ↗
19. Fatigue life prediction of metallic materials considering mean stress effects by means of an artificial neural network10.1016/j.ijfatigue.2020.105527 ↗
20. A machine-learning fatigue life prediction approach of additively manufactured metals10.1016/j.engfracmech.2020.107508 ↗
21. Probabilistic S-N fields based on statistical distributions applied to metallic and composite materials: state of the art10.1177/1687814019870395 ↗
22. Probabilistic strain-fatigue life performance based on stochastic analysis of structural and WAAM-stainless steels10.1016/j.engfailanal.2021.105495 ↗
23. Probabilistic fatigue life prediction and reliability assessment of a high pressure turbine disc considering load variations10.1177/1056789517737132 ↗
24. Unified two-stage fatigue methodology based on a probabilistic damage model applied to structural details10.1016/j.tafmec.2017.09.004 ↗
25. Casting defects and fatigue behaviour of ductile cast iron for wind turbine components: a comprehensive study10.1002/mawe.201100911 ↗
26. Cevallos-Torres · 2019 · 87
27. Low-cycle fatigue modelling supported by strain energy density-based Huffman model considering the variability of dislocation density10.1016/j.engfailanal.2021.105608 ↗
28. Machine learning based fatigue life prediction with effects of additive manufacturing process parameters for printed SS 316L10.1016/j.ijfatigue.2020.105941 ↗
29. High-cycle and very-high-cycle fatigue lifetime prediction of additively manufactured AlSi10Mg via crystal plasticity finite element method10.1016/j.ijfatigue.2021.106577 ↗
30. A statistical model of fatigue failure incorporating effects of specimen size and load amplitude on fatigue life10.1080/14786435.2019.1609707 ↗
31. Essential structure of S-N curve: prediction of fatigue life and fatigue limit of defective materials and nature of scatter10.1016/j.ijfatigue.2020.106138 ↗
32. A new method to simulate the triangular distribution10.1016/j.mcm.2008.06.013 ↗
33. Davis R. Teaching note—teaching project simulation in excel using PERT-beta distributions. INFORMS Trans Educ 8 (3):139–8. https://doi.org/10.1287/ited.1080.0013.10.1287/ited.1080.0013 ↗
34. Importance of input data normalization for the application of neural networks to complex industrial problems10.1109/23.589532 ↗
35. Experimental validation of an ANN model for random loading fatigue analysis10.1016/j.ijfatigue.2019.04.028 ↗
36. Application of backpropagation artificial neural network prediction model for the PAH bioremediation of polluted soil10.1016/j.chemosphere.2016.07.003 ↗
37. Backpropagation learning algorithm based on Levenberg Marquardt algorithm
38. Roweis S. Levenberg-Marquardt Optimization, Computer Science. New York University. https://cs.nyu.edu/~roweis/notes/lm.pdf.
39. Activation functions in neural networks
40. A survey on modern trainable activation functions10.1016/j.neunet.2021.01.026 ↗
41. LeCun YA, Bottou L, Orr GB, Müller K. Efficient BackProp. In: Montavon G, Orr GB, Müller KR, editors. Neural networks: tricks of the trade. Lecture notes in computer science, Vol. 7700. Berlin, Heidelberg: Springer; 2012. https://doi.org/10.1007/978-3-642-35289-8_3.10.1007/978-3-642-35289-8_3 ↗