Screening for shape memory alloys with narrow thermal hysteresis using combined XGBoost and DFT calculation
Source abstract
Abstract
Shape memory alloys (SMAs) are desirable candidates for elastocaloric effect materials, but they all suffer from large thermal hysteresis (Thys). This study analyzes multicomponent TiNi-based SMAs dataset by machine learning (ML) to explore new SMAs with narrow Thys. The second-largest eigenvalue λ2 of the stretch transformation matrix U is added to the original dataset to guide the ML process as a feature. Firstly, λ2 is obtained by first-principles calculations combined with ML. XGBoost Regressor (XGBR) combined with Leave-One-Out Cross-Validation (LOO-CV) is selected from four algorithms for modeling with the highest coefficient of determination R2 of 0.87. The introduction of λ2 improves the performance of the model. The dataset is divided into 15 groups based on different doping elements (such as Hf, Cu, Zr, etc.), among which TiNiCu is the most predictive component with the R2 of 0.89. Over 500 TiNiCu components are randomly generated and predicted Thys. Based on the contour maps created from the prediction results, it is found that Thys is likely to decrease with the increase of Cu doping in general, and minimum Thys occurs when the Cu is about 15 at. %, which is consistent with the existing experimental results. Eventually, a potential Thys minimum (1.2 K) region of TixNiyCuz (58.3%≤x ≤ 58.5%, 26.5%≤y ≤ 27%, 14.8%≤z ≤ 15.3%, x + y + z = 100%) SMA composition is predicted. Our study not only provides a potential selection of narrow Thys TiNi-based SMAs but also indicates combining of XGBoost and DFT calculation is an effective strategy for materials design.
Source: expertdata · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Shape Memory Alloy Transformations · Topology Optimization in Engineering
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (45)
Show source-provided references
1. United Nations Environmental Programme, The Importance of Energy Efficiency in the Refrigeration, Air-conditioning and Heat Pump Sectors. https://ozone.unep.org/sites/default/files/2019-08/briefingnote-a_importance-of-energy-efficiency-in-the-refrigeration-air-conditioning-and-heat-pump-sectors.pdf, 2018 (accessed May 2018).
2. Energy-efficient and-economic technologies for air conditioning with vapor compression refrigeration: A comprehensive review10.1016/j.apenergy.2018.09.067 ↗
3. Opportunities and insights for reducing fossil fuel consumption by households and organizations10.1038/nenergy.2016.43 ↗
4. Five thermal energy grand challenges for decarbonization10.1038/s41560-020-0675-9 ↗
5. Giant elastocaloric effect in FeRh alloy10.1016/0375-9601(92)90432-L ↗
6. J. Tušek, K. Engelbrecht, R. Millán-Solsona, L. Mañosa, E. Vives, L. P. Mikkelsen, N. Pryds, The elastocaloric effect: a way to cool efficiently, Adv. Energy Mater.5 (2015) 1500361. 10.1002/aenm.201500361.10.1002/aenm.201500361 ↗
7. Colossal elastocaloric effect in ferroelastic Ni-Mn-Ti alloys10.1103/PhysRevLett.122.255703 ↗
8. Large tunable elastocaloric effect in additively manufactured Ni–Ti shape memory alloys10.1016/j.actamat.2020.04.007 ↗
9. Fatigue-resistant high-performance elastocaloric materials made by additive manufacturing10.1126/science.aax7616 ↗
10. Low-pressure-induced giant barocaloric effect in an all-d-metal Heusler Ni35.5Co14.5Mn35Ti15 magnetic shape memory alloy10.1063/5.0005021 ↗
11. Elastocaloric effect in Ni50Fe19Ga27Co4 single crystals10.1016/j.actamat.2015.05.054 ↗
12. A regenerative elastocaloric heat pump
13. Elastocaloric heat pump with specific cooling power of 20.9 W g–1 exploiting snap-through instability and strain-induced crystallization10.1038/s41560-020-00770-w ↗
14. Elastocaloric effect vs fatigue life: Exploring the durability limits of Ni-Ti plates under pre-strain conditions for elastocaloric cooling10.1016/j.actamat.2018.03.032 ↗
15. Fatigue behavior and cyclic deformation of additive manufactured NiTi10.1016/j.jmatprotec.2017.10.006 ↗
16. Study of the thermal physical properties of Ti47Ni44Nb9 wide hysteresis shape memory alloy10.1016/j.msea.2006.08.016 ↗
17. Experimentally correlating thermal hysteresis and phase compatibility in multifunctional Heusler alloys
18. High-temperature shape memory alloys: some recent developments10.1016/j.msea.2003.10.324 ↗
19. Phase engineering and supercompatibility of shape memory alloys10.1016/j.mattod.2017.10.002 ↗
20. High-dimensional materials and process optimization using data-driven experimental design with well-calibrated uncertainty estimates, Integr. Mater. Manuf
21. Bayesian machine learning in metamaterial design: Fragile becomes supercompressible10.1002/adma.201904845 ↗
22. Machine learning for alloys10.1038/s41578-021-00340-w ↗
23. Physics-informed machine learning for composition–process–property design: Shape memory alloy demonstration
24. An informatics approach to transformation temperatures of NiTi-based shape memory alloys10.1016/j.actamat.2016.12.009 ↗
25. On the printability and transformation behavior of nickel-titanium shape memory alloys fabricated using laser powder-bed fusion additive manufacturing10.1016/j.jmapro.2018.08.037 ↗
26. Machine learning modeling of lattice constants for half-Heusler alloys
27. Quantum Grover search-based optimization for innovative material discovery
28. Combinatorial Exploration and Mapping of Phase Transformation in a Ni-Ti-Co Thin Film Library10.1021/acscombsci.0c00097 ↗
29. Accelerated search for materials with targeted properties by adaptive design10.1038/ncomms11241 ↗
30. Numerical investigation of thermal frequency responses of graded hybrid smart nanocomposite (CNT-SMA-Epoxy) structure10.1080/15376494.2020.1725193 ↗
31. An application of slime mould algorithm for optimizing parameters of power system stabilizer
32. Subsynchronous control interaction studies in DFIG-based wind farms using selective modal analysis10.1016/j.ijepes.2020.106291 ↗
33. Modal performance of two-fiber orthogonal gradient composite laminates embedded with SMA10.3390/ma13051102 ↗
34. Efficient global optimization of expensive black-box function10.1023/A:1008306431147 ↗
35. Accelerated design for elastocaloric performance in NiTi-based alloys through machine learning10.1063/5.0068290 ↗
36. The coefficient of determination R2 and intra-class correlation coefficient from generalized linear mixed-effects models revisited and expanded10.1098/rsif.2017.0213 ↗
37. The correlation coefficient: An overview10.1080/10408340500526766 ↗
38. Linear regression, Wiley Interdiscip. Rev
39. A tutorial on Gaussian process regression: Modelling, exploring, and exploiting functions10.1016/j.jmp.2018.03.001 ↗
40. A survey of decision tree classifier methodology10.1109/21.97458 ↗
41. T. Chen, C. Guestrin, Xgboost: A scalable tree boosting system, Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining. (2016) 785-794. 10.1145/2939672.2939785.10.1145/2939672.2939785 ↗
42. Combinatorial search of thermoelastic shape-memory alloys with extremely small hysteresis width10.1038/nmat1593 ↗
43. The structure of NiTiCu shape memory alloys10.1007/BF02658390 ↗
44. Cu-content dependence of shape memory characteristics in Ti-Ni-Cu alloys10.2320/matertrans1989.31.959 ↗
45. Effect of Fe addition on microstructure and mechanical properties of as-cast Ti49Ni51 alloy10.3390/ma12193114 ↗