The Development of New Perovskite-Type Oxygen Transport Membranes Using Machine Learning

被引：7

作者：

Schlenz, Hartmut ^{[1
,2
,3
]}

Baumann, Stefan ^{[1
,3
]}

Meulenberg, Wilhelm Albert ^{[1
,3
,4
]}

Guillon, Olivier ^{[1
,3
,5
]}

机构：

[1] Forschungszentrum Juelich, IEK 1 Mat Synth & Proc, Inst Energy & Climate Res IEK, Wilhelm Johnen Str, D-52425 Julich, Germany

[2] Univ Bonn, Inst Geosci, Div Geochem & Petrol, Meckenheimer Allee 139, D-53115 Bonn, Germany

[3] Juelich Aachen Res Alliance JARA Energy, D-52425 Julich, Germany

[4] Univ Twente, Fac Sci & Technol, Inorgan Membranes, POB 217, NL-7500 AE Enschede, Netherlands

[5] Rhein Westfal TH Aachen, Inst Mineral Engn, Dept Ceram & Refractory Mat, D-52064 Aachen, Germany

来源：

CRYSTALS | 2022年 / 12卷 / 07期

关键词：

ceramic; perovskite; oxygen separation membrane; mixed ionic-electronic conducting membrane MIEC; valence bond calculations; machine learning; !text type='python']python[!/text] programming; Pecon; py; BOND-VALENCE PARAMETERS; ELECTRICAL-CONDUCTIVITY; SOLID ELECTROLYTES; IONIC-CONDUCTIVITY; FUEL-CELL; SRTIO3; PREDICTION; OXIDES; STABILITY; VACANCIES;

D O I：

10.3390/cryst12070947

中图分类号：

O7 [晶体学];

学科分类号：

0702 ; 070205 ; 0703 ; 080501 ;

摘要：

The aim of this work is to predict suitable chemical compositions for the development of new ceramic oxygen gas separation membranes, avoiding doping with toxic cobalt or expensive rare earths. For this purpose, we have chosen the system Sr<INF>1-x</INF>Ba<INF>x</INF>(Ti<INF>1-y-z</INF>V<INF>y</INF>Fe<INF>z</INF>)O<INF>3-delta</INF> (cubic perovskite-type phases). We have evaluated available experimental data, determined missing crystallographic information using bond-valence modeling and programmed a Python code to be able to generate training data sets for property predictions using machine learning. Indeed, suitable compositions of cubic perovskite-type phases can be predicted in this way, allowing for larger electronic conductivities of up to sigma<INF>e</INF> = 1.6 S/cm and oxygen conductivities of up to sigma<INF>i</INF> = 0.008 S/cm at T = 1173 K and an oxygen partial pressure p<INF>O<INF>2</INF></INF> = 10-15 bar, thus enabling practical applications.

引用

页数：17

共 78 条

[1] AHA DW, 1991, MACH LEARN, V6, P37, DOI 10.1007/BF00153759
[2] Artificial Neural Network Modeling to Predict the Effect of Milling Time and TiC Content on the Crystallite Size and Lattice Strain of Al7075-TiC Composites Fabricated by Powder Metallurgy
Alam, Mohammad Azad
Ya, Hamdan H.
Azeem, Mohammad
Yusuf, Mohammad
Soomro, Imtiaz Ali
Masood, Faisal
Shozib, Imtiaz Ahmed
Sapuan, Salit M.
Akhter, Javed
[J]. CRYSTALS, 2022, 12 (03)
[3] Defect Genome of Cubic Perovskites for Fuel Cell Applications
Balachandran, Janakiraman
Lin, Lianshan
Anchell, Jonathan S.
Bridges, Craig A.
Ganesh, P.
[J]. JOURNAL OF PHYSICAL CHEMISTRY C, 2017, 121 (48) : 26637 - 26647
[4] BOND-VALENCE PARAMETERS FOR SOLIDS
BRESE, NE
OKEEFFE, M
[J]. ACTA CRYSTALLOGRAPHICA SECTION B-STRUCTURAL SCIENCE, 1991, 47 : 192 - 197
[5] Brown I.D., 2016, The Chemical Bond in Inorganic Chemistry, V2
[6] Brown ID, 2014, STRUCT BOND, V158, P1, DOI 10.1007/978-3-642-54968-7
[7] Machine learning for molecular and materials science
Butler, Keith T.
Davies, Daniel W.
Cartwright, Hugh
Isayev, Olexandr
Walsh, Aron
[J]. NATURE, 2018, 559 (7715) : 547 - 555
[8] LIBSVM: A Library for Support Vector Machines
Chang, Chih-Chung
Lin, Chih-Jen
[J]. ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2011, 2 (03)
[9] A Critical Review of Machine Learning of Energy Materials
Chen, Chi
Zuo, Yunxing
Ye, Weike
Li, Xiangguo
Deng, Zhi
Ong, Shyue Ping
[J]. ADVANCED ENERGY MATERIALS, 2020, 10 (08)
[10] Comparative analysis of machine learning approaches on the prediction of the electronic properties of perovskites: A case study of ABX3 and A2BB'X6
Chenebuah, Ericsson Tetteh
Nganbe, Michel
Tchagang, Alain Beaudelaire
[J]. MATERIALS TODAY COMMUNICATIONS, 2021, 27

← 1 2 3 4 5 6 7 8 →