Artificial Intelligence Algorithm Enabled Industrial-Scale Graphene Characterization
No characterization method is available to quickly perform quality inspection of 2D materials produced on an industrial scale. This hinders the adoption of 2D materials for product manufacturing in many industries. Here, we report an artificial-intelligence-assisted Raman analysis to quickly probe t...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-04-01
|
| Series: | Crystals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4352/10/4/308 |
| _version_ | 1797570471882915840 |
|---|---|
| author | Wei Sun Leong Giuseppe Arrabito Giuseppe Prestopino |
| author_facet | Wei Sun Leong Giuseppe Arrabito Giuseppe Prestopino |
| author_sort | Wei Sun Leong |
| collection | DOAJ |
| description | No characterization method is available to quickly perform quality inspection of 2D materials produced on an industrial scale. This hinders the adoption of 2D materials for product manufacturing in many industries. Here, we report an artificial-intelligence-assisted Raman analysis to quickly probe the quality of centimeter-large graphene samples in a non-destructive manner. Chemical vapor deposition of graphene is devised in this work such that two types of samples were obtained: layer-plus-islands and layer-by-layer graphene films, at centimeter scales. Using these samples, we implemented and integrated an unsupervised learning algorithm with an automated Raman spectroscopy to precisely cluster 20,250 and 18,000 Raman spectra collected from layer-plus-islands and layer-by-layer graphene films, respectively, into five and two clusters. Each cluster represents graphene patches with different layer numbers and stacking orders. For instance, the two clusters detected in layer-by-layer graphene films represent monolayer and bilayer graphene based on their Raman fingerprints. Our intelligent Raman analysis is fully automated, with no human operation involved, is highly reliable (99.95% accuracy), and can be generalized to other 2D materials, paving the way towards industrialization of 2D materials for various applications in the future. |
| first_indexed | 2024-03-10T20:26:03Z |
| format | Article |
| id | doaj.art-5635d6585564415995783dcde633b04f |
| institution | Directory Open Access Journal |
| issn | 2073-4352 |
| language | English |
| last_indexed | 2024-03-10T20:26:03Z |
| publishDate | 2020-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Crystals |
| spelling | doaj.art-5635d6585564415995783dcde633b04f2023-11-19T21:48:01ZengMDPI AGCrystals2073-43522020-04-0110430810.3390/cryst10040308Artificial Intelligence Algorithm Enabled Industrial-Scale Graphene CharacterizationWei Sun Leong0Giuseppe Arrabito1Giuseppe Prestopino2Department of Materials Science and Engineering, National University of Singapore, Singapore 117575, SingaporeDipartimento di Fisica e Chimica - Emilio Segrè, Università degli Studi di Palermo, Ed.17, V.le delle Scienze, 90128 Palermo, ItalyDipartimento di Ingegneria Industriale, Università di Roma ‘Tor Vergata’, Via del Politecnico 1, I-00133 Roma, ItalyNo characterization method is available to quickly perform quality inspection of 2D materials produced on an industrial scale. This hinders the adoption of 2D materials for product manufacturing in many industries. Here, we report an artificial-intelligence-assisted Raman analysis to quickly probe the quality of centimeter-large graphene samples in a non-destructive manner. Chemical vapor deposition of graphene is devised in this work such that two types of samples were obtained: layer-plus-islands and layer-by-layer graphene films, at centimeter scales. Using these samples, we implemented and integrated an unsupervised learning algorithm with an automated Raman spectroscopy to precisely cluster 20,250 and 18,000 Raman spectra collected from layer-plus-islands and layer-by-layer graphene films, respectively, into five and two clusters. Each cluster represents graphene patches with different layer numbers and stacking orders. For instance, the two clusters detected in layer-by-layer graphene films represent monolayer and bilayer graphene based on their Raman fingerprints. Our intelligent Raman analysis is fully automated, with no human operation involved, is highly reliable (99.95% accuracy), and can be generalized to other 2D materials, paving the way towards industrialization of 2D materials for various applications in the future.https://www.mdpi.com/2073-4352/10/4/308two-dimensional materialsgrapheneRaman spectroscopyunsupervised learning |
| spellingShingle | Wei Sun Leong Giuseppe Arrabito Giuseppe Prestopino Artificial Intelligence Algorithm Enabled Industrial-Scale Graphene Characterization Crystals two-dimensional materials graphene Raman spectroscopy unsupervised learning |
| title | Artificial Intelligence Algorithm Enabled Industrial-Scale Graphene Characterization |
| title_full | Artificial Intelligence Algorithm Enabled Industrial-Scale Graphene Characterization |
| title_fullStr | Artificial Intelligence Algorithm Enabled Industrial-Scale Graphene Characterization |
| title_full_unstemmed | Artificial Intelligence Algorithm Enabled Industrial-Scale Graphene Characterization |
| title_short | Artificial Intelligence Algorithm Enabled Industrial-Scale Graphene Characterization |
| title_sort | artificial intelligence algorithm enabled industrial scale graphene characterization |
| topic | two-dimensional materials graphene Raman spectroscopy unsupervised learning |
| url | https://www.mdpi.com/2073-4352/10/4/308 |
| work_keys_str_mv | AT weisunleong artificialintelligencealgorithmenabledindustrialscalegraphenecharacterization AT giuseppearrabito artificialintelligencealgorithmenabledindustrialscalegraphenecharacterization AT giuseppeprestopino artificialintelligencealgorithmenabledindustrialscalegraphenecharacterization |