PDF (17.8 MB)
Collect
Submit Manuscript
Research Article | Open Access

A fast composition-stability machine learning model for screening MAX phases and guiding discovery of Ti2SnN

Zhiyao LuYun FanZhaoxu SunXiaodong HeChuchu YangHang YinJinze ZhangGuangping SongYongting ZhengYuelei Bai()
National Key Laboratory of Science and Technology on Advanced Composites in Special Environments and Center for Composite Materials and Structures, Harbin Institute of Technology, Harbin 150080, China
Show Author Information

Graphical Abstract

View original image Download original image

Abstract

To explore the MAX phase with experimental value over a wider range, a data-driven machine learning (ML) model was trained to rapidly predict the stability of MAX phases via a random forest classifier (RFC), support vector machine (SVM), and gradient boosting tree (GBT), where the deemed significant descriptors were compiled from the literature and the stability of 1804 combinations of MAX phases was collected. Using this well-trained model, 190 new MAX phases were screened from 4347 MAX phases, 150 of which met the criteria for thermodynamic and intrinsic stability on the basis of first-principles calculations. Additionally, with the help of the ML model, the mean number of valence electrons and the valence electron deviation are the two most critical factors influencing stability. Additionally, one of these predicted MAX phases, Ti₂SnN, was experimentally synthesized through Lewis acid substitution reactions at 750 °C, with interesting A-site deintercalation and self-extrusion. First-principles calculations revealed that Ti₂SnN has lower elastic properties, higher damage tolerance and fracture toughness, and a higher coefficient of thermal expansion (CTE).

Electronic Supplementary Material

Download File(s)
JAC1050_ESM.pdf (5.4 MB)

References

[1]

Bai YL, Qi XX, Duff A, et al. Density functional theory insights into ternary layered boride MoAlB. Acta Mater 2017, 132: 69–81.

[2]

Du YQ, Wang FL, Hu MH, et al. Stability and wettability of ternary carbide Mo2Ga2C in molten metals. Ceram Int 2023, 49: 21449–21454.

[3]

Ding HM, Li M, Li YB, et al. Progress in structural tailoring and properties of ternary layered ceramics. J Inorg Mater 2023, 38: 845.

[4]

Lei X, Lin NM. Structure and synthesis of MAX phase materials: A brief review. Crit Rev Solid State 2022, 47: 736–771.

[5]

Sun ZM. Progress in research and development on MAX phases: A family of layered ternary compounds. Int Mater Rev 2011, 56: 143–166.

[6]
Pan Y. W2AlC: A new layered MAX phase to adjust the balance between strength and ductility. Mater Today Chem 2024, 35 : 101915.
[7]

Rougab M, Gueddouh A. A DFT exploration of the stabilities, physical properties, and tensile strength of new synthesized Nb2AC (A = Ni and Co) MAX phases. Solid State Sci 2024, 158: 107733.

[8]

Rougab M, Gueddouh A. Investigation of the stability and physical properties of the newly synthesized Ta2AC (A = Co and Ni) MAX phases from first principles. Solid State Sci 2024, 154: 107603.

[9]
Barsoum M W. MAX Phases: Properties of Machinable Ternary Carbides and Nitrides. Weinheim (Germany): Wiley-VCH, 2013.
[10]

Gonzalez-Julian J, Go T, Mack DE, et al. Thermal cycling testing of TBCs on Cr2AlC MAX phase substrates. Surf Coat Technol 2018, 340: 17–24.

[11]

Greco G, Iucolano F, Roccaforte F. Ohmic contacts to gallium nitride materials. Appl Surf Sci 2016, 383: 324–345.

[12]

Fashandi H, Andersson M, Eriksson J, et al. Single-step synthesis process of Ti3SiC2 ohmic contacts on 4H-SiC by sputter-deposition of Ti. Scripta Mater 2015, 99: 53–56.

[13]

Borysiewicz MA, Kamińska E, Piotrowska A, et al. Ti–Al–N MAX phase, a candidate for ohmic contacts to n-GaN. Acta Phys Pol A 2008, 114: 1061–1066.

[14]

Zhou XB, Han YH, Shen XF, et al. Fast joining SiC ceramics with Ti3SiC2 tape film by electric field-assisted sintering technology. J Nucl Mater 2015, 466: 322–327.

[15]

Fitriani P, Septiadi A, Hyuk JD, et al. Joining of SiC monoliths using a thin MAX phase tape and the elimination of joining layer by solid-state diffusion. J Eur Ceram Soc 2018, 38: 3433–3440.

[16]

Tatarko P, Casalegno V, Hu CF, et al. Joining of CVD-SiC coated and uncoated fibre reinforced ceramic matrix composites with pre-sintered Ti3SiC2 MAX phase using spark plasma sintering. J Eur Ceram Soc 2016, 36: 3957–3967.

[17]

Pan Y, Xu LR. New insight into the structural, mechanical and thermodynamic properties of Mo2C MXene as the ultrahigh temperature ceramics. Mater Today Chem 2024, 42: 102449.

[18]

Zhang Y, Wang L, Zhang N, et al. Adsorptive environmental applications of MXene nanomaterials: A review. RSC Adv 2018, 8: 19895–19905.

[19]
Unal MA, Bayrakdar F, Fusco L, et al. 2D MXenes with antiviral and immunomodulatory properties: A pilot study against SARS-CoV-2. Nano Today 2021, 38 : 101136.
[20]

Kang ZM, Khan MA, Gong YM, et al. Recent progress of MXenes and MXene-based nanomaterials for the electrocatalytic hydrogen evolution reaction. J Mater Chem A 2021, 9: 6089–6108.

[21]

Rackl T, Eisenburger L, Niklaus R, et al. Syntheses and physical properties of the MAX phase boride Nb2SB and the solid solutions Nb2SB x C1– x ( x = 0–1). Phys Rev Materials 2019, 3: 054001.

[22]

Zhang QQ, Zhou YC, San XY, et al. Zr2SeB and Hf2SeB: Two new MAB phase compounds with the Cr2AlC-type MAX phase (211 phase) crystal structures. J Adv Ceram 2022, 11: 1764–1776.

[23]

Ingason AS, Petruhins A, Dahlqvist M, et al. A nanolaminated magnetic phase: Mn2GaC. Mater Res Lett, 2014, 2: 89–93.

[24]

Dahlqvist M, Barsoum MW, Rosen J. MAX phases—Past, present, and future. Mater Today 2024, 72: 1–24.

[25]

Dahlqvist M, Alling B, Rosén J. Stability trends of MAX phases from first principles. Phys Rev B 2010, 81: 220102.

[26]

Qi XX, He XD, Yin WL, et al. Stability trend, weak bonding, and magnetic properties of the Al- and Si-containing ternary-layered borides MAB phases. J Am Ceram Soc 2023, 106: 1513–1530.

[27]

Ni N, Zhang HC, Zhou YC. Electronic structure, bonding characteristics, and mechanical behaviors of a new family of Si-containing damage-tolerant MAB phases M5SiB2 (M = IVB–VIB transition metals). J Adv Ceram 2022, 11: 1626–1640.

[28]

Ding H, Li Y, Li M, et al. Chemical scissor-mediated structural editing of layered transition metal carbides. Science 2023, 379: 1130–1135.

[29]

Shehab M, Abualigah L, Shambour Q, et al. Machine learning in medical applications: A review of state-of-the-art methods. Comput Biol Med 2022, 145: 105458.

[30]

Zhang J, Xu B, Xiong YX, et al. Design high-entropy carbide ceramics from machine learning. NPJ Comput Mater 2022, 8: 5.

[31]

Zhang L, He M, Shao SF. Machine learning for halide perovskite materials. Nano Energy 2020, 78: 105380.

[32]

Fan Y, Bai YL, Li Q, et al. Compositional design and phase formation capability of high-entropy rare-earth disilicates from machine learning and decision fusion. NPJ Comput Mater 2024, 10: 95.

[33]

Park H, Mall R, Alharbi FH, et al. Learn-and-match molecular cations for perovskites. J Phys Chem A 2019, 123: 7323–7334.

[34]

Schleder GR, Acosta CM, Fazzio A. Exploring two-dimensional materials thermodynamic stability via machine learning. ACS Appl Mater Inter 2020, 12: 20149–20157.

[35]

Fan Y, Bai YL, Lu ZY, et al. Exploring high-performance environmental barrier coatings for rare earth silicates: A combined approach of first principles calculations and machine learning. J Materiomics 2025, 11: 100921.

[36]

Frey NC, Wang J, Vega Bellido GI, et al. Prediction of synthesis of 2D metal carbides and nitrides (MXenes) and their precursors with positive and unlabeled machine learning. ACS Nano 2019, 13: 3031–3041.

[37]

Xu X, Zhang X, Bitzek E, et al. Origin of the yield stress anomaly in L12 intermetallics unveiled with physically informed machine-learning potentials. Acta Mater 2024, 281: 120423.

[38]

Liu YC, Chu KL, Zhou Y, et al. Discovery of orthorhombic perovskite oxides with low thermal conductivity by first-principles calculations. J Adv Ceram 2022, 11: 1596–1603.

[39]

Islam N, Huang WJ, Zhuang HL. Machine learning for phase selection in multi-principal element alloys. Comp Mater Sci 2018, 150: 230–235.

[40]

Zhou ZQ, Zhou YJ, He QF, et al. Machine learning guided appraisal and exploration of phase design for high entropy alloys. npj Comput Mater 2019, 5: 128.

[41]

Kaufmann K, Vecchio KS. Searching for high entropy alloys: A machine learning approach. Acta Mater 2020, 198: 178–222.

[42]

Zhang L, Chen HM, Tao XM, et al. Machine learning reveals the importance of the formation enthalpy and atom-size difference in forming phases of high entropy alloys. Mater Design 2020, 193: 108835.

[43]

Zhang Y, Wen C, Wang CX, et al. Phase prediction in high entropy alloys with a rational selection of materials descriptors and machine learning models. Acta Mater 2020, 185: 528–539.

[44]

He M, Zhang L. Machine learning and symbolic regression investigation on stability of MXene materials. Comp Mater Sci 2021, 196: 110578.

[45]

Zhang Y, Xu W, Liu G, et al. Bandgap prediction of two-dimensional materials using machine learning. PLOS One 2021, 16: 0255637.

[46]

Zhang YM, Mao ZY, Han Q, et al. The role of Hume−Rothery’s rules play in the MAX phases formability. Materialia 2020, 12: 100810.

[47]

Lu ZY, He XD, Yin H, et al. Theoretical screening, intrinsic brittleness and thermal properties of the S-containing MAX carbides and borides. J Materiomics 2023, 9: 1056–1066.

[48]

Malik AM, Rohrer J, Albe K. Theoretical study of thermodynamic and magnetic properties of transition metal carbide and nitride MAX phases. Phys Rev Materials 2023, 7: 044408.

[49]

Jeitschko W, Nowotny H, Benesovsky F. Die H-phasen Ti2TlC, Ti2PbC, Nb2InC, Nb2SnC und Ta2GaC. Monatsh Chem Verw Tl 1964, 95: 431–435.

[50]

Zhang YM, Xu YJ, Huang Q, et al. Structure maps for MAX phases formability revisited. Ceram Int 2024, 50: 2855–2863.

[51]

Eklund P, Beckers M, Jansson U, et al. The M n +1AX n phases: Materials science and thin-film processing. Thin Solid Films 2010, 518: 1851–1878.

[52]

Barsoum MW, Farber L. Room-temperature deintercalation and self-extrusion of Ga from Cr2GaN. Science 1999, 284: 937–939.

[53]
Cordero B, Gómez V, Platero-Prats AE, et al. Covalent radii revisited. Dalton T 2008: 2832.
[54]

Oyedele O. Determining the optimal number of folds to use in a K-fold cross-validation: A neural network classification experiment. Res Math 2023, 10: 2201015.

[55]

Kresse G, Furthmüller J. Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set. Phys Rev B 1996, 54: 11169–11186.

[56]

Perdew JP, Burke K, Ernzerhof M. Generalized gradient approximation made simple. Phys Rev Lett 1996, 77: 3865–3868.

[57]

Popoola AI, Oluyamo SS. Physical properties of some noble metal compounds from PAW-DFT calculations. J Sci Technol 2015, 34: 47.

[58]

Togo A, Tanaka I. First principles phonon calculations in materials science. Scripta Mater 2015, 108: 1–5.

[59]

Kroumova E, Aroyo MI, Perez-Mato JM, et al. Bilbao crystallographic server: Useful databases and tools for phase-transition studies. Phase Transit 2003, 76: 155–170.

[60]

Hill R. The elastic behaviour of a crystalline aggregate. P Phys Soc Lond A 1952, 65: 349–354.

[61]

Bai YL, He XD, Wang RG, et al. An ab initio study on compressibility of Al-containing MAX-phase carbides. J Appl Phys 2013, 114: 173709.

[62]

Bai YL, Qi XX, He XD, et al. Phase stability and weak metallic bonding within ternary-layered borides CrAlB, Cr2AlB2, Cr3AlB4, and Cr4AlB6. J Am Ceram Soc 2019, 102: 3715–3727.

[63]

Kashiwaya S, Lai CC, Lu J, et al. Formation of Ti2AuN from Au-covered Ti2AlN thin films: A general strategy to thermally induce intercalation of noble metals into MAX phases. Cryst Growth Des 2020, 20: 4077–4081.

[64]

Presser V, Naguib M, Chaput L, et al. First-order Raman scattering of the MAX phases: Ti2AlN, Ti2AlC0.5N0.5, Ti2AlC, (Ti0.5V0.5)2AlC, V2AlC, Ti3AlC2, and Ti3GeC2. J Raman Spectrosc 2012, 43: 168–172.

[65]

Raghavan V. Al−N−Ti (aluminum−nitrogen−titanium). J Phase Equilib Diff 2006, 27: 159–162.

[66]

Jeitschko W, Nowotny H, Benesovsky F. Die H-phasen: Ti2CdC, Ti2GaC, Ti2GaN, Ti2InN, Zr2InN und Nb2GaC. Monatsh Chem Verw Tl 1964, 95: 178–179.

[67]

Manoun B, Leaffer OD, Gupta S, et al. On the compression behavior of Ti2InC, (Ti0.5,Zr0.5)2InC, and M2SnC (M = Ti, Nb, Hf) to quasi-hydrostatic pressures up to 50 GPa. Solid State Commun 2009, 149: 1978–1983.

[68]

Liu Y, Zhang P, Ling C, et al. Spontaneous Sn whisker formation on Ti2SnC. J Mater Sci Mater El 2017, 28: 5788–5795.

[69]

Li M, Lu J, Luo K, et al. Element replacement approach by reaction with lewis acidic molten salts to synthesize nanolaminated MAX phases and MXenes. J Am Chem Soc 2019, 141: 4730–4737.

[70]

Sun ZM, Hashimoto H, Tian WB, et al. Synthesis of the MAX phases by pulse discharge sintering. Int J Appl Ceram Tec 2010, 7: 704–718.

[71]

Roy C, Banerjee P, Bhattacharyya S. Molten salt shielded synthesis (MS3) of Ti2AlN and V2AlC MAX phase powders in open air. J Eur Ceram Soc 2020, 40: 923–929.

[72]

Khediri R, Hammoutène D, Kassali K, et al. High-pressure structural, elastic, vibrational, and thermodynamic study of MAX-phase Ti2InN. Comput Condens Matter 2023, 36: 00829.

[73]
Manoun B, Zhang FX, Saxena SK, et al. X-ray high-pressure study of Ti2AlN and Ti2AlC. J Phys Chem Solids 2006, 67 : 2091–2094.
[74]

Bentzel GW, Naguib M, Lane NJ, et al. High-temperature neutron diffraction, Raman spectroscopy, and first-principles calculations of Ti3SnC2 and Ti2SnC. J Am Ceram Soc 2016, 99: 2233–2242.

[75]

Lin ZJ, Zhuo MJ, Li MS, et al. Synthesis and microstructure of layered-ternary Ti2AlN ceramic. Scripta Mater 2007, 56: 1115–1118.

[76]

Lapauw T, Vanmeensel K, Lambrinou K, et al. Rapid synthesis and elastic properties of fine-grained Ti2SnC produced by spark plasma sintering. J Alloys Compd 2015, 631: 72–76.

[77]

Cygan T, Wozniak J, Broniszewski K, et al. Analysis of microstructure and mechanical properties of alumina composites reinforced with Ti2AlN MAX phases. Int J Refract Met H 2024, 122: 106725.

[78]

Lane NJ, Vogel SC, Barsoum MW. Temperature-dependent crystal structures of Ti2AlN and Cr2GeC as determined from high temperature neutron diffraction. J Am Ceram Soc 2011, 94: 3473–3479.

[79]

Murnaghan FD. The compressibility of media under extreme pressures. P Natl Acad Sci USA 1944, 30: 244–247.

[80]

Zhou WB, Liu L, Zhu JQ, et al. Facile synthesis of high-purity Ti2SC powders by spark plasma sintering technique. Ceram Int 2017, 43: 9363–9368.

[81]

He XD, Bai YL, Zhu CC, et al. Polymorphism of newly discovered Ti4GaC3: A first-principles study. Acta Mater 2011, 59: 5523–5533.

[82]

Bai YL, He XD, Wang RG. Lattice dynamics of Al-containing MAX-phase carbides: A first-principle study. J Raman Spectrosc 2015, 46: 784–794.

[83]

Djedid A, Méçabih S, Abbes O, et al. Theoretical investigations of structural, electronic and thermal properties of Ti2AlX (X = C, N). Physica B 2009, 404: 3475–3482.

[84]

Qi XX, Yin WL, Jin S, et al. Density-functional-theory predictions of mechanical behaviour and thermal properties as well as experimental hardness of the Ga-bilayer Mo2Ga2C. J Adv Ceram 2022, 11: 273–282.

Journal of Advanced Ceramics
Article number: 9221050
Cite this article:
Lu Z, Fan Y, Sun Z, et al. A fast composition-stability machine learning model for screening MAX phases and guiding discovery of Ti2SnN. Journal of Advanced Ceramics, 2025, 14(4): 9221050. https://doi.org/10.26599/JAC.2025.9221050
Metrics & Citations  
Article History
Copyright
Rights and Permissions
Return