Machine learning-based beta transus temperature prediction for titanium alloys
Source abstract
Abstract
Beta transus temperature (βtr) is one of the most crucial features of titanium alloys. It is typically used as the index while designing the heat treatment process for titanium alloys. The βtr is also a significant parameter to optimize the processing technology of titanium alloys. Four machine learning algorithms and one empirical formula is developed in this study to estimate the βtr of titanium alloys: Artificial Neural Networks (ANN), Gauss Processing Regression (GPR), Super Vector Machine (SVM), and Ensemble Regression Trees (ERT). According to the correlation coefficient (R), Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) to verify the accuracy of models, and the experimentally measured phase transition temperature of Ti600 alloy was also used to verify the generalization ability of the model. Choosing the best model to analyze the sensitivity of the elements and determine how each component affects the βtr. The result demonstrated that the ANN model has the highest prediction accuracy among the five models, and different model structures have different effects on predicting new data. The ANN model with 10 neurons has the highest prediction accuracy, while the ANN model with 8 neurons has the strongest generalization ability. The results of the sensitivity analysis proved that all the alloy compositions used as input parameters were valid parameters.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Titanium Alloys Microstructure and Properties · Hydrogen embrittlement and corrosion behaviors in metals · Welding Techniques and Residual Stresses
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (41)
Show source-provided references
1. Effect of hydrogen on the β transus temperature of TC21 alloy10.1016/j.matchar.2011.06.003 ↗
2. Extremely high beta-transus temperature of graphene oxide reinforced high-temperature titanium alloy matrix composite10.1016/j.matlet.2021.129575 ↗
3. C. Leyens, M. Peters, Titanium and titanium alloys: fundamentals and applications, John Wiley & Sons2003.10.1002/3527602119 ↗
4. Influence of hydride-induced microstructure modification on mechanical properties of metastable beta titanium alloy Ti 10V-2Fe-3Al10.1016/j.ijhydene.2015.06.167 ↗
5. Microstructure evolution and tensile properties of Ti-6.5Al-2Zr-Mo-V alloy processed with thermo hydrogen treatment10.1016/j.msea.2014.09.104 ↗
6. Application of thermohydrogen treatment for enhancement of the high-temperature strength of VT9 titanium alloy10.1007/s11003-008-9082-2 ↗
7. In situ study of phase transformations in Ti–6Al–4V–xH alloys10.1016/S1003-6326(15)63916-4 ↗
8. Effect of hydrogen on hot deformation behavior of TC21 alloy
9. Effect of hydrogen on microstructure evolution and deformation behaviors of Ti-2Fe-0.1B alloy10.1016/j.jallcom.2021.163473 ↗
10. Determination of beta transform temperature of TC8 titanium alloy
11. Determination of transformation point of BT22 titanium alloy
12. Potential role of machine learning techniques for modeling the hardness of OPH steels
13. Artificial intelligence and machine learning in design of mechanical materials10.1039/D0MH01451F ↗
14. Machine learning for design, phase transformation and mechanical properties of alloys10.1016/j.pmatsci.2021.100797 ↗
15. A physics-informed machine learning method for predicting grain structure characteristics in directed energy deposition10.1016/j.commatsci.2021.110958 ↗
16. Study on effects of alloying elements on beta transus temperature of titanium alloys using artificial neural network
17. Construction and evaluation of the prediction models of tianium alloys' (α+β)/β transus temperature
18. Beta transus prediction of titanium alloys through integration of artificial neural network and multifactor dimensionality reduction analyses10.1016/j.md.2016.01.001 ↗
19. Modelling beta transus temperature of titanium alloys using artificial neural network10.1016/j.commatsci.2004.05.004 ↗
20. Practical model for predicting beta transus temperature of titanium alloys
21. Hybrid machine learning techniques and computational mechanics: estimating the dynamic behavior of oxide precipitation hardened steel10.1109/ACCESS.2021.3129454 ↗
22. Neuro-fuzzy approaches to estimating thermal overstress behavior of IGBTs
23. A dynamic artificial neural network approach to estimate thermal behaviors of li-ion batteries
24. Microstructure and deformation behavior of hydrogenated TC16 titanium alloy
25. Determination of phase transition temperature of titanium alloys by differential scanning calorimetry
26. Effects of thermohydrogen treatment on the structure and mechianical properties of Ti-60 alloy
27. G. Welsch, R. Boyer, E. Collings, Materials properties handbook: titanium alloys, ASM international1993.
28. Ma · 2001 · vol. 4
29. Predicting glass transition temperatures using neural networks10.1016/j.actamat.2018.08.022 ↗
30. Modeling effects of alloying elements and heat treatment parameters on mechanical properties of hot die steel with back-propagation artificial neural network10.1016/S1006-706X(18)30025-6 ↗
31. People counting based on improved gauss process regression
32. Overview of Gaussian process regression
33. A machine learning approach to fracture mechanics problems10.1016/j.actamat.2020.03.016 ↗
34. Greedy function approximation
35. Support-vector networks10.1023/A:1022627411411 ↗
36. Beta titanium alloys and their role in the titanium industry10.1007/BF03220742 ↗
37. Accurate calculation of (α+β)/β phase transition of titanium alloys based on binary phase diagrams
38. J.-. Y, Z.-h. Zhou, A.-y. Zhou, Machine learning and applications, Press of Tsinghua University2006.
39. Effects of β-stabilizer elements on microstructure formation and mechanical properties of titanium alloys10.1016/j.jallcom.2021.160085 ↗
40. Thermodynamic modeling of the Ti–Al–Cr ternary system10.1016/j.jallcom.2010.10.092 ↗
41. Thermodynamic description of the Ti–H system10.1016/j.calphad.2010.07.001 ↗