| 226 | 0 | 250 |
| 下载次数 | 被引频次 | 阅读次数 |
钠固态电解质因其能量密度高、安全性好和成本低等优势被视作极具潜能的下一代电解质材料，然而较低的离子电导率成为限制钠固态电解质发展的主要瓶颈之一。本工作提出了一种机器学习与第一性原理计算结合的智能模型实现高通量筛选，将离子电导率作为主要的筛选指标，先后使用极端梯度提升(XGBoost)模型和从头算分子动力学(AIMD)预测并验证材料的离子电导率，最终筛选得到4种潜在的无机钠固态电解质材料即Na_3HfTiSi_2PO12,Na_3Bi(BO3)2,Na_2LuPCO7以及Na_2LuPWO8，并通过进一步分析探究钠离子的迁移机理。
Abstract：Introduction Development of new energy becomes popular due to the energy shortages and environmental pollution. The existing commercial secondary batteries are primarily lithium-ion batteries, which use organic solvents and lithium salts as electrolytes. These batteries have two significant drawbacks, i.e., global lithium resources are insufficient and unevenly distributed, and organic solvents are flammable, having safety risks. These drawbacks severely affect the further development of lithium-ion batteries. Sodium solid-state electrolytes(SSEs) are emerged as an ideal material for future battery electrolytes due to the high energy density, good thermal stability, strong mechanical rigidity, low cost and improved safety. This paper was to explore a potential sodium SSEs by a high-throughput screening method based on machine learning(ML) and first-principles calculations. The potential sodium SSEs were predicted by machine learning models and were validated through Ab initio molecular dynamics(AIMD) simulations. In addition, the conduction mechanism of sodium ions was also analyzed based on the results of the first-principles calculations. Methods The dataset of inorganic sodium-containing compounds was established before building ML models. All the data in this dataset were from the Materials Project database. Solid-state electrolytes have good thermodynamic stability and insulation. The materials with a band gap less than 1.5 e V or energy above hull greater than 0.03 e V/atom were excluded, resulting in a final dataset of 3631 sodium-containing inorganic compounds. To achieve the optimal performance of the regression model, we tried four ML algorithms, i.e., Random Forest(RF), e Xtreme Gradient Boosting(XGBoost), Categorical Boosting(CatBoost), and K-Nearest Neighbors(KNN). Magpie(Materials Agnostic Platform for Informatics and Exploration) was used to obtain the crystal structure information into 145 attributes as the input of ML models. To validate the performance of the screened sodium solid-state electrolytes and further analyze the migration mechanism of sodium ions, AIMD simulations and CI-NEB(Climbing Image Nudged Elastic Band) calculations were conducted to calculate their ionic conductivity, activation energy, probability density distribution, van Hove correlation functions and energy barriers along specific diffusion paths. Results and discussion In the four machine learning regression models, XGBoost has the optimum performance on both training and testing sets with R2 = 0.999 and 0.994, respectively, indicating its high accuracy and strong generalization ability. The XGBoost model is used to predict 3631 of sodium-containing inorganic compounds, discovering that 126 of them have a potential to be superior SSEs. We further screen these and select 14 compounds for AIMD simulations, among which four materials(i.e., Na_3HfTiSi_2PO12, Na_3Bi(BO3)2, Na_2LuPCO7 and Na_2LuPWO8) show a high ionic conductivity and a low activation energy. Since the difference between the machine learning prediction and AIMD calculated value is within an order of magnitude, the high-throughput screening method used is reliable. Among the four candidate SSE materials, Na_3HfTiSi_2PO12 belongs to the NASICON family. A previous study indicates that Na_3HfZrSi_2PO12 is a promising sodium SSE material, which is similar to Na_3HfTiSi_2PO12, except that Ti is replaced by Zr, indirectly proving the reliability of the machine learning model prediction. To clarify the sodium ion migration mechanism, the motion trajectories of various particles in each compound are investigated. The results show that at all simulation temperatures, the diffusion of sodium ions is evident, while other ions remain relatively stable, forming reliable channels for sodium ion migration. From the distinct parts, the four materials exhibit migration correlation, indicating that sodium ions do not move independently but rather diffuse cooperatively, which contributes significantly to the ionic conductivity. The migration pathways of Na_3Bi(BO3)2, Na_2LuPCO7 and Na_2LuPWO8 are discussed according to the probability density distributions. Moreover, the energy barrier of migration in Na_2LuPCO7 shows that the maximum obstacle is to bypass the triangular plane formed by CO3 within the diffusion channel. Conclusions We used the best-performing XGBoost model to search the established dataset of 3631 inorganic sodium-containing compounds, identifying 126 compounds with a high ionic conductivity. Also, we selected 14 of the 126 compounds for AIMD simulations to calculate their ionic conductivity and activation energy, ultimately identifying four inorganic sodium-containing compounds(i.e., Na_3HfTiSi_2PO12, Na_3Bi(BO3)2, Na_2LuPCO7 and Na_2LuPWO8) with a high ionic conductivity. We derived the van Hove correlation functions and probability density distributions based on the AIMD simulation results. It was indicated that the common characteristic of the four high ionic conductivity materials could be the presence of stable sodium ion diffusion channels with sodium ions migrating in a coordinated manner. Finally, the migration mechanism of sodium ions was analyzed based on the results of AIMD and CI-NEB.
[1] KIM S W, SEO D H, MA X H, et al. Electrode materials for rechargeable sodium-ion batteries:Potential alternatives to current lithium-ion batteries[J]. Adv Energy Mater, 2012, 2(7):710–721.
[2] KIM J J, YOON K, PARK I, et al. Progress in the development of sodium-ion solid electrolytes[J]. Small Meth, 2017, 1(10):1700219.
[3] ZHAO C L, LIU L L, QI X G, et al. Solid-state sodium batteries[J].Adv Energy Mater, 2018, 8(17):1703012.
[4] AHMAD H, KUBRA K T, BUTT A, et al. Recent progress, challenges,and perspectives in the development of solid-state electrolytes for sodium batteries[J]. J Power Sources, 2023, 581:233518.
[5] GOODENOUGH J B, HONG H Y, KAFALAS J A. Fast Na+-ion transport in skeleton structures[J]. Mater Res Bull, 1976, 11(2):203–220.
[6] LI Z P, LIU P, ZHU K J, et al. Solid-state electrolytes for sodium metal batteries[J]. Energy Fuels, 2021, 35(11):9063–9079.
[7] KIM J, KANG S, MIN K. Screening platform for promising Na superionic conductors for Na-ion solid-state electrolytes[J]. ACS Appl Mater Interfaces, 2023, 15(35):41417–41425.
[8] ZHANG Y, ZHAN T, SUN Y, et al. Revolutionizing solid-state NASICON sodium batteries:Enhanced ionic conductivity estimation through multivariate experimental parameters leveraging machine learning[J]. ChemSusChem, 2024, 17(6):e202301284.
[9] ZHOU P F, ZHAO Z R, SUN K T, et al. Machine learning guided cobalt-doping strategy for solid-state NASICON electrolytes[J]. Eur J Inorg Chem, 2023, 26(26):e202300382.
[10] LEE B D, GAVALI D S, KIM H, et al. Discovering virtual Na-based argyrodites as solid-state electrolytes using DFT, AIMD, and machine learning techniques[J]. J Mater Chem A, 2025,https://doi.org/10.1039/D4TA06927G.
[11] GUIN M, TIETZ F, GUILLON O. New promising NASICON material as solid electrolyte for sodium-ion batteries:Correlation between composition, crystal structure and ionic conductivity of Na3+xSc2SixP3-xO12[J].Solid State Ion, 2016, 293:18–26.
[12] DENG Z, ZHU Z Y, CHU I H, et al. Data-driven first-principles methods for the study and design of alkali superionic conductors[J].Chem Mater, 2017, 29(1):281–288.
[13] XIAO W S, WU M W, WANG H, et al. Li-ion transport mechanisms in selenide-based solid-state electrolytes in lithium-metal batteries:A study of Li8SeN2, Li7PSe6, and Li6PSe5X(X=Cl, Br, I)[J]. Energy Environ Mater, 2024, 7(5):e12729.
[14] JAIN A, ONG S P, HAUTIER G, et al. Commentary:The Materials Project:A materials genome approach to accelerating materials innovation[J]. 2013, 1(1):011002.
[15] HONRAO S J, YANG X, RADHAKRISHNAN B, et al. Discovery of novel Li SSE and anode coatings using interpretable machine learning and high-throughput multi-property screening[J]. Sci Rep, 2021, 11(1):16484.
[16] WARD L, AGRAWAL A, CHOUDHARY A, et al. A general-purpose machine learning framework for predicting properties of inorganic materials[J]. NPJ Comput Mater, 2016, 2:16028.
[17] BREIMAN L. Random forests[J]. Mach Learn, 2001, 45(1):5–32.
[18] CHEN T Q, GUESTRIN C. XGBoost:A scalable tree boosting system[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco California USA. ACM, 2016.
[19] Prokhorenkova L, GUSEV G, VOROBEV A, et al. CatBoost:unbiased boosting with categorical features[C]//32nd Conference on Neural Information Processing Systems(NeurIPS 2018). Montréal, Canada,2018:31.
[20] COVER T, HART P. Nearest neighbor pattern classification[J]. IEEE Trans Inf Theory, 1967, 13(1):21–27.
[21] PEDREGOSA F, VAROQUAUX G, GRAMFORT A, et al.Scikit-learn:Machine learning in python[J]. J. Mach Learn Res, 2011,12:2825–2830.
[22] CHEN H H, CHEN J P, DING J H. Data evaluation and enhancement for quality improvement of machine learning[J]. IEEE Trans Reliab,2021, 70(2):831–847.
[23] LIU Y, YANG Z, ZOU X, et al. Data quantity governance for machine learning in materials science[J]. Natl Sci Rev, 2023, 10(7):nwad125.
[24] YANG F L, CAMPOS DOS SANTOS E, JIA X, et al. A dynamic database of solid-state electrolyte(DDSE)picturing all-solid-state batteries[J]. Nano Mater Sci, 2024, 6(2):256–262.
[25] KRESSE G, FURTHMüLLER J. Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set[J]. Phys Rev B Condens Matter, 1996, 54(16):11169–11186.
[26] KRESSE G, FURTHMüLLER J. Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set[J]. Comput Mater Sci, 1996, 6(1):15–50.
[27] BL?CHL P E. Projector augmented-wave method[J]. Phys Rev B,1994, 50(24):17953–17979.
[28] PERDEW J P, BURKE K, ERNZERHOF M. Generalized gradient approximation made simple[J]. Phys Rev Lett, 1996, 77(18):3865–3868.
[29] HE X F, ZHU Y Z, EPSTEIN A, et al. Statistical variances of diffusional properties from ab initio molecular dynamics simulations[J].NPJ Comput Mater, 2018, 4:18.
[30] HOOVER W G. Canonical dynamics:Equilibrium phase-space distributions[J]. Phys Rev A, 1985, 31(3):1695–1697.
[31] NOSéS. A unified formulation of the constant temperature molecular dynamics methods[J]. 1984, 81(1):511–519.
[32] MOMMA K, IZUMI F. VESTA 3for three-dimensional visualization of crystal, volumetric and morphology data[J]. J Appl Crystallogr, 2011,44(6):1272–1276.
[33] HENKELMAN G, UBERUAGA B P, JóNSSON H. A climbing image nudged elastic band method for finding saddle points and minimum energy paths[J]. 2000, 113(22):9901–9904.
[34] OUYANG B, WANG J, HE T, et al. Synthetic accessibility and stability rules of NASICONs[J]. Nat Commun, 2021, 12(1):5752.
[35] ZHANG Z Z, ZOU Z Y, KAUP K, et al. Correlated migration invokes higher Na+-ion conductivity in Na SICON-type solid electrolytes[J].Adv Energy Mater, 2019, 9(42):1902373.
[36] LI C, LI R, LIU K N, et al. NaSICON:A promising solid electrolyte for solid-state sodium batteries[J]. Interdiscip Mater, 2022, 1(3):396–416.
基本信息:
DOI：10.14062/j.issn.0454-5648.20240787
中图分类号:O646;TM912
引用信息:
[1]刘怿泓,毕文柱,Mohamed Ait Tamerd,等.智能模型高通量筛选无机钠固态电解质[J].硅酸盐学报,2025,53(07):1801-1808.DOI:10.14062/j.issn.0454-5648.20240787.
基金信息:
国家自然科学基金(52302302)
2024-12-09
2024
2025-05-26
2025-05-26
2025
1
2025-05-26
2025-05-26
2025-05-26