The Development of New Perovskite-Type Oxygen Transport Membranes Using Machine Learning
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<sub>1−x</sub>Ba<sub>x</sub>(Ti<s...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Crystals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4352/12/7/947 |
| _version_ | 1797440153161039872 |
|---|---|
| author | Hartmut Schlenz Stefan Baumann Wilhelm Albert Meulenberg Olivier Guillon |
| author_facet | Hartmut Schlenz Stefan Baumann Wilhelm Albert Meulenberg Olivier Guillon |
| author_sort | Hartmut Schlenz |
| collection | DOAJ |
| description | 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<sub>1−x</sub>Ba<sub>x</sub>(Ti<sub>1−y−z</sub>V<sub>y</sub>Fe<sub>z</sub>)O<sub>3−<i>δ</i></sub> (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 σ<sub><i>e</i></sub> = 1.6 S/cm and oxygen conductivities of up to σ<sub><i>i</i></sub> = 0.008 S/cm at <i>T</i> = 1173 K and an oxygen partial pressure <i>p<sub>O<sub>2</sub></sub></i> = 10<sup>−15</sup> bar, thus enabling practical applications. |
| first_indexed | 2024-03-09T12:03:00Z |
| format | Article |
| id | doaj.art-b7f5effb4e75487581ed6b2938eb3ef4 |
| institution | Directory Open Access Journal |
| issn | 2073-4352 |
| language | English |
| last_indexed | 2024-03-09T12:03:00Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Crystals |
| spelling | doaj.art-b7f5effb4e75487581ed6b2938eb3ef42023-11-30T23:01:19ZengMDPI AGCrystals2073-43522022-07-0112794710.3390/cryst12070947The Development of New Perovskite-Type Oxygen Transport Membranes Using Machine LearningHartmut Schlenz0Stefan Baumann1Wilhelm Albert Meulenberg2Olivier Guillon3Forschungszentrum Juelich, Institute of Energy and Climate Research (IEK), IEK-1: Materials Synthesis and Processing, Wilhelm-Johnen-Strasse, D-52425 Juelich, GermanyForschungszentrum Juelich, Institute of Energy and Climate Research (IEK), IEK-1: Materials Synthesis and Processing, Wilhelm-Johnen-Strasse, D-52425 Juelich, GermanyForschungszentrum Juelich, Institute of Energy and Climate Research (IEK), IEK-1: Materials Synthesis and Processing, Wilhelm-Johnen-Strasse, D-52425 Juelich, GermanyForschungszentrum Juelich, Institute of Energy and Climate Research (IEK), IEK-1: Materials Synthesis and Processing, Wilhelm-Johnen-Strasse, D-52425 Juelich, GermanyThe 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<sub>1−x</sub>Ba<sub>x</sub>(Ti<sub>1−y−z</sub>V<sub>y</sub>Fe<sub>z</sub>)O<sub>3−<i>δ</i></sub> (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 σ<sub><i>e</i></sub> = 1.6 S/cm and oxygen conductivities of up to σ<sub><i>i</i></sub> = 0.008 S/cm at <i>T</i> = 1173 K and an oxygen partial pressure <i>p<sub>O<sub>2</sub></sub></i> = 10<sup>−15</sup> bar, thus enabling practical applications.https://www.mdpi.com/2073-4352/12/7/947ceramicperovskiteoxygen separation membranemixed ionic-electronic conducting membrane MIECvalence bond calculationsmachine learning |
| spellingShingle | Hartmut Schlenz Stefan Baumann Wilhelm Albert Meulenberg Olivier Guillon The Development of New Perovskite-Type Oxygen Transport Membranes Using Machine Learning Crystals ceramic perovskite oxygen separation membrane mixed ionic-electronic conducting membrane MIEC valence bond calculations machine learning |
| title | The Development of New Perovskite-Type Oxygen Transport Membranes Using Machine Learning |
| title_full | The Development of New Perovskite-Type Oxygen Transport Membranes Using Machine Learning |
| title_fullStr | The Development of New Perovskite-Type Oxygen Transport Membranes Using Machine Learning |
| title_full_unstemmed | The Development of New Perovskite-Type Oxygen Transport Membranes Using Machine Learning |
| title_short | The Development of New Perovskite-Type Oxygen Transport Membranes Using Machine Learning |
| title_sort | development of new perovskite type oxygen transport membranes using machine learning |
| topic | ceramic perovskite oxygen separation membrane mixed ionic-electronic conducting membrane MIEC valence bond calculations machine learning |
| url | https://www.mdpi.com/2073-4352/12/7/947 |
| work_keys_str_mv | AT hartmutschlenz thedevelopmentofnewperovskitetypeoxygentransportmembranesusingmachinelearning AT stefanbaumann thedevelopmentofnewperovskitetypeoxygentransportmembranesusingmachinelearning AT wilhelmalbertmeulenberg thedevelopmentofnewperovskitetypeoxygentransportmembranesusingmachinelearning AT olivierguillon thedevelopmentofnewperovskitetypeoxygentransportmembranesusingmachinelearning AT hartmutschlenz developmentofnewperovskitetypeoxygentransportmembranesusingmachinelearning AT stefanbaumann developmentofnewperovskitetypeoxygentransportmembranesusingmachinelearning AT wilhelmalbertmeulenberg developmentofnewperovskitetypeoxygentransportmembranesusingmachinelearning AT olivierguillon developmentofnewperovskitetypeoxygentransportmembranesusingmachinelearning |