Discovering deposition process regimes: Leveraging unsupervised learning for process insights, surrogate modeling, and sensitivity analysis
This work introduces a comprehensive approach utilizing data-driven methods to elucidate the deposition process regimes in Chemical Vapor Deposition (CVD) reactors and the interplay of physical mechanism that dominate in each one of them. Through this work, we address three key objectives. Firstly,...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-11-01
|
| Series: | Chemical Engineering Journal Advances |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S266682112400084X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846141740621234176 |
|---|---|
| author | Geremy Loachamín-Suntaxi Paris Papavasileiou Eleni D. Koronaki Dimitrios G. Giovanis Georgios Gakis Ioannis G. Aviziotis Martin Kathrein Gabriele Pozzetti Christoph Czettl Stéphane P.A. Bordas Andreas G. Boudouvis |
| author_facet | Geremy Loachamín-Suntaxi Paris Papavasileiou Eleni D. Koronaki Dimitrios G. Giovanis Georgios Gakis Ioannis G. Aviziotis Martin Kathrein Gabriele Pozzetti Christoph Czettl Stéphane P.A. Bordas Andreas G. Boudouvis |
| author_sort | Geremy Loachamín-Suntaxi |
| collection | DOAJ |
| description | This work introduces a comprehensive approach utilizing data-driven methods to elucidate the deposition process regimes in Chemical Vapor Deposition (CVD) reactors and the interplay of physical mechanism that dominate in each one of them. Through this work, we address three key objectives. Firstly, our methodology relies on process outcomes, derived by a detailed CFD model, to identify clusters of “outcomes” corresponding to distinct process regimes, wherein the relative influence of input variables undergoes notable shifts. This phenomenon is experimentally validated through Arrhenius plot analysis, affirming the efficacy of our approach. Secondly, we demonstrate the development of an efficient surrogate model, based on Polynomial Chaos Expansion (PCE), that maintains accuracy, facilitating streamlined computational analyses. Finally, as a result of PCE, sensitivity analysis is made possible by means of Sobol’ indices, that quantify the impact of process inputs across identified regimes.The insights gained from our analysis contribute to the formulation of hypotheses regarding phenomena occurring beyond the transition regime. Notably, the significance of temperature even in the diffusion-limited regime, as evidenced by the Arrhenius plot, suggests activation of gas phase reactions at elevated temperatures. Importantly, our proposed methods yield insights that align with experimental observations and theoretical principles, aiding decision-making in process design and optimization. By circumventing the need for costly and time-consuming experiments, our approach offers a pragmatic pathway toward enhanced process efficiency. Moreover, this study underscores the potential of data-driven computational methods for innovating reactor design paradigms. |
| format | Article |
| id | doaj-art-4e9abd65e7e242f6ba248349f64fd7b0 |
| institution | Kabale University |
| issn | 2666-8211 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Chemical Engineering Journal Advances |
| spelling | doaj-art-4e9abd65e7e242f6ba248349f64fd7b02024-12-04T05:14:40ZengElsevierChemical Engineering Journal Advances2666-82112024-11-0120100667Discovering deposition process regimes: Leveraging unsupervised learning for process insights, surrogate modeling, and sensitivity analysisGeremy Loachamín-Suntaxi0Paris Papavasileiou1Eleni D. Koronaki2Dimitrios G. Giovanis3Georgios Gakis4Ioannis G. Aviziotis5Martin Kathrein6Gabriele Pozzetti7Christoph Czettl8Stéphane P.A. Bordas9Andreas G. Boudouvis10Faculty of Science, Technology and Medicine, University of Luxembourg, Esch-sur-Alzette, L-4364, Luxembourg; School of Chemical Engineering, National Technical University of Athens, Zographos Campus, 15780, Attiki, GreeceFaculty of Science, Technology and Medicine, University of Luxembourg, Esch-sur-Alzette, L-4364, Luxembourg; School of Chemical Engineering, National Technical University of Athens, Zographos Campus, 15780, Attiki, GreeceFaculty of Science, Technology and Medicine, University of Luxembourg, Esch-sur-Alzette, L-4364, LuxembourgDepartment of Civil & Systems Engineering, Johns Hopkins University, Baltimore, MD 21218, USASchool of Chemical Engineering, National Technical University of Athens, Zographos Campus, 15780, Attiki, GreeceSchool of Chemical Engineering, National Technical University of Athens, Zographos Campus, 15780, Attiki, GreeceCERATIZIT Luxembourg S.à r.l. Mamer, L-8201, LuxembourgCERATIZIT Luxembourg S.à r.l. Mamer, L-8201, LuxembourgCERATIZIT Austria GmbH Reutte, A-6600, AustriaFaculty of Science, Technology and Medicine, University of Luxembourg, Esch-sur-Alzette, L-4364, Luxembourg; Correspondence to: School of Chemical Engineering, National Technical University of Athens, Zographos Campus, 15780, Attiki, Greece.School of Chemical Engineering, National Technical University of Athens, Zographos Campus, 15780, Attiki, GreeceThis work introduces a comprehensive approach utilizing data-driven methods to elucidate the deposition process regimes in Chemical Vapor Deposition (CVD) reactors and the interplay of physical mechanism that dominate in each one of them. Through this work, we address three key objectives. Firstly, our methodology relies on process outcomes, derived by a detailed CFD model, to identify clusters of “outcomes” corresponding to distinct process regimes, wherein the relative influence of input variables undergoes notable shifts. This phenomenon is experimentally validated through Arrhenius plot analysis, affirming the efficacy of our approach. Secondly, we demonstrate the development of an efficient surrogate model, based on Polynomial Chaos Expansion (PCE), that maintains accuracy, facilitating streamlined computational analyses. Finally, as a result of PCE, sensitivity analysis is made possible by means of Sobol’ indices, that quantify the impact of process inputs across identified regimes.The insights gained from our analysis contribute to the formulation of hypotheses regarding phenomena occurring beyond the transition regime. Notably, the significance of temperature even in the diffusion-limited regime, as evidenced by the Arrhenius plot, suggests activation of gas phase reactions at elevated temperatures. Importantly, our proposed methods yield insights that align with experimental observations and theoretical principles, aiding decision-making in process design and optimization. By circumventing the need for costly and time-consuming experiments, our approach offers a pragmatic pathway toward enhanced process efficiency. Moreover, this study underscores the potential of data-driven computational methods for innovating reactor design paradigms.http://www.sciencedirect.com/science/article/pii/S266682112400084XArrhenius plotFe CVD reactorHierarchical clusteringPolynomial chaos expansionUncertainty quantificationSensitivity analysis |
| spellingShingle | Geremy Loachamín-Suntaxi Paris Papavasileiou Eleni D. Koronaki Dimitrios G. Giovanis Georgios Gakis Ioannis G. Aviziotis Martin Kathrein Gabriele Pozzetti Christoph Czettl Stéphane P.A. Bordas Andreas G. Boudouvis Discovering deposition process regimes: Leveraging unsupervised learning for process insights, surrogate modeling, and sensitivity analysis Chemical Engineering Journal Advances Arrhenius plot Fe CVD reactor Hierarchical clustering Polynomial chaos expansion Uncertainty quantification Sensitivity analysis |
| title | Discovering deposition process regimes: Leveraging unsupervised learning for process insights, surrogate modeling, and sensitivity analysis |
| title_full | Discovering deposition process regimes: Leveraging unsupervised learning for process insights, surrogate modeling, and sensitivity analysis |
| title_fullStr | Discovering deposition process regimes: Leveraging unsupervised learning for process insights, surrogate modeling, and sensitivity analysis |
| title_full_unstemmed | Discovering deposition process regimes: Leveraging unsupervised learning for process insights, surrogate modeling, and sensitivity analysis |
| title_short | Discovering deposition process regimes: Leveraging unsupervised learning for process insights, surrogate modeling, and sensitivity analysis |
| title_sort | discovering deposition process regimes leveraging unsupervised learning for process insights surrogate modeling and sensitivity analysis |
| topic | Arrhenius plot Fe CVD reactor Hierarchical clustering Polynomial chaos expansion Uncertainty quantification Sensitivity analysis |
| url | http://www.sciencedirect.com/science/article/pii/S266682112400084X |
| work_keys_str_mv | AT geremyloachaminsuntaxi discoveringdepositionprocessregimesleveragingunsupervisedlearningforprocessinsightssurrogatemodelingandsensitivityanalysis AT parispapavasileiou discoveringdepositionprocessregimesleveragingunsupervisedlearningforprocessinsightssurrogatemodelingandsensitivityanalysis AT elenidkoronaki discoveringdepositionprocessregimesleveragingunsupervisedlearningforprocessinsightssurrogatemodelingandsensitivityanalysis AT dimitriosggiovanis discoveringdepositionprocessregimesleveragingunsupervisedlearningforprocessinsightssurrogatemodelingandsensitivityanalysis AT georgiosgakis discoveringdepositionprocessregimesleveragingunsupervisedlearningforprocessinsightssurrogatemodelingandsensitivityanalysis AT ioannisgaviziotis discoveringdepositionprocessregimesleveragingunsupervisedlearningforprocessinsightssurrogatemodelingandsensitivityanalysis AT martinkathrein discoveringdepositionprocessregimesleveragingunsupervisedlearningforprocessinsightssurrogatemodelingandsensitivityanalysis AT gabrielepozzetti discoveringdepositionprocessregimesleveragingunsupervisedlearningforprocessinsightssurrogatemodelingandsensitivityanalysis AT christophczettl discoveringdepositionprocessregimesleveragingunsupervisedlearningforprocessinsightssurrogatemodelingandsensitivityanalysis AT stephanepabordas discoveringdepositionprocessregimesleveragingunsupervisedlearningforprocessinsightssurrogatemodelingandsensitivityanalysis AT andreasgboudouvis discoveringdepositionprocessregimesleveragingunsupervisedlearningforprocessinsightssurrogatemodelingandsensitivityanalysis |