Deep learning modeling of manufacturing and build variations on multistage axial compressors aerodynamics
Applications of deep learning to physical simulations such as Computational Fluid Dynamics have recently experienced a surge in interest, and their viability has been demonstrated in different domains. However, due to the highly complex, turbulent, and three-dimensional flows, they have not yet been...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Cambridge University Press
2025-01-01
|
| Series: | Data-Centric Engineering |
| Subjects: | |
| Online Access: | https://www.cambridge.org/core/product/identifier/S2632673625000024/type/journal_article |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832544321001226240 |
|---|---|
| author | Giuseppe Bruni Sepehr Maleki Senthil K. Krishnababu |
| author_facet | Giuseppe Bruni Sepehr Maleki Senthil K. Krishnababu |
| author_sort | Giuseppe Bruni |
| collection | DOAJ |
| description | Applications of deep learning to physical simulations such as Computational Fluid Dynamics have recently experienced a surge in interest, and their viability has been demonstrated in different domains. However, due to the highly complex, turbulent, and three-dimensional flows, they have not yet been proven usable for turbomachinery applications. Multistage axial compressors for gas turbine applications represent a remarkably challenging case, due to the high-dimensionality of the regression of the flow field from geometrical and operational variables. This paper demonstrates the development and application of a deep learning framework for predictions of the flow field and aerodynamic performance of multistage axial compressors. A physics-based dimensionality reduction approach unlocks the potential for flow-field predictions, as it re-formulates the regression problem from an unstructured to a structured one, as well as reducing the number of degrees of freedom. Compared to traditional “black-box” surrogate models, it provides explainability to the predictions of the overall performance by identifying the corresponding aerodynamic drivers. The model is applied to manufacturing and build variations, as the associated performance scatter is known to have a significant impact on
$ \mathrm{C}{\mathrm{O}}_2 $
emissions, which poses a challenge of great industrial and environmental relevance. The proposed architecture is proven to achieve an accuracy comparable to that of the CFD benchmark, in real-time, for an industrially relevant application. The deployed model is readily integrated within the manufacturing and build process of gas turbines, thus providing the opportunity to analytically assess the impact on performance with actionable and explainable data. |
| format | Article |
| id | doaj-art-206df36ec5174a218f1cc17cba41ef49 |
| institution | Kabale University |
| issn | 2632-6736 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Cambridge University Press |
| record_format | Article |
| series | Data-Centric Engineering |
| spelling | doaj-art-206df36ec5174a218f1cc17cba41ef492025-02-03T10:35:53ZengCambridge University PressData-Centric Engineering2632-67362025-01-01610.1017/dce.2025.2Deep learning modeling of manufacturing and build variations on multistage axial compressors aerodynamicsGiuseppe Bruni0https://orcid.org/0009-0003-0280-3448Sepehr Maleki1https://orcid.org/0000-0001-6897-7385Senthil K. Krishnababu2https://orcid.org/0009-0003-2745-8783Lincoln AI Lab, University of Lincoln, Lincoln, UK Siemens Energy, Lincoln, UKSiemens Energy, Lincoln, UKLincoln AI Lab, University of Lincoln, Lincoln, UK Siemens Energy, Lincoln, UKApplications of deep learning to physical simulations such as Computational Fluid Dynamics have recently experienced a surge in interest, and their viability has been demonstrated in different domains. However, due to the highly complex, turbulent, and three-dimensional flows, they have not yet been proven usable for turbomachinery applications. Multistage axial compressors for gas turbine applications represent a remarkably challenging case, due to the high-dimensionality of the regression of the flow field from geometrical and operational variables. This paper demonstrates the development and application of a deep learning framework for predictions of the flow field and aerodynamic performance of multistage axial compressors. A physics-based dimensionality reduction approach unlocks the potential for flow-field predictions, as it re-formulates the regression problem from an unstructured to a structured one, as well as reducing the number of degrees of freedom. Compared to traditional “black-box” surrogate models, it provides explainability to the predictions of the overall performance by identifying the corresponding aerodynamic drivers. The model is applied to manufacturing and build variations, as the associated performance scatter is known to have a significant impact on $ \mathrm{C}{\mathrm{O}}_2 $ emissions, which poses a challenge of great industrial and environmental relevance. The proposed architecture is proven to achieve an accuracy comparable to that of the CFD benchmark, in real-time, for an industrially relevant application. The deployed model is readily integrated within the manufacturing and build process of gas turbines, thus providing the opportunity to analytically assess the impact on performance with actionable and explainable data.https://www.cambridge.org/core/product/identifier/S2632673625000024/type/journal_articleaerodynamicsaxial compressorCFDconvolutional neural networkdeep learninggas turbine |
| spellingShingle | Giuseppe Bruni Sepehr Maleki Senthil K. Krishnababu Deep learning modeling of manufacturing and build variations on multistage axial compressors aerodynamics Data-Centric Engineering aerodynamics axial compressor CFD convolutional neural network deep learning gas turbine |
| title | Deep learning modeling of manufacturing and build variations on multistage axial compressors aerodynamics |
| title_full | Deep learning modeling of manufacturing and build variations on multistage axial compressors aerodynamics |
| title_fullStr | Deep learning modeling of manufacturing and build variations on multistage axial compressors aerodynamics |
| title_full_unstemmed | Deep learning modeling of manufacturing and build variations on multistage axial compressors aerodynamics |
| title_short | Deep learning modeling of manufacturing and build variations on multistage axial compressors aerodynamics |
| title_sort | deep learning modeling of manufacturing and build variations on multistage axial compressors aerodynamics |
| topic | aerodynamics axial compressor CFD convolutional neural network deep learning gas turbine |
| url | https://www.cambridge.org/core/product/identifier/S2632673625000024/type/journal_article |
| work_keys_str_mv | AT giuseppebruni deeplearningmodelingofmanufacturingandbuildvariationsonmultistageaxialcompressorsaerodynamics AT sepehrmaleki deeplearningmodelingofmanufacturingandbuildvariationsonmultistageaxialcompressorsaerodynamics AT senthilkkrishnababu deeplearningmodelingofmanufacturingandbuildvariationsonmultistageaxialcompressorsaerodynamics |