Advancing buffet onset prediction: a deep learning approach with enhanced interpretability for aerodynamic engineering
Abstract The interaction between the shock wave and boundary layer of transonic wings can trigger periodic self-excited oscillations, resulting in transonic buffet. Buffet severely restricts the flight envelope of civil aircraft and is directly related to their aerodynamic performance and safety. De...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2024-11-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-024-01612-y |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571141944770560 |
|---|---|
| author | Jing Wang Wei Liu Hairun Xie Miao Zhang |
| author_facet | Jing Wang Wei Liu Hairun Xie Miao Zhang |
| author_sort | Jing Wang |
| collection | DOAJ |
| description | Abstract The interaction between the shock wave and boundary layer of transonic wings can trigger periodic self-excited oscillations, resulting in transonic buffet. Buffet severely restricts the flight envelope of civil aircraft and is directly related to their aerodynamic performance and safety. Developing efficient and reliable techniques for buffet onset prediction is crucial for the advancement of civil aircraft. In this study, utilizing a comprehensive database of supercritical airfoils generated through numerical simulations, a convolutional neural network (CNN) model is firstly developed to perform buffet classification based on the flow fields. After that, employing explainable machine learning techniques, including Gradient-weighted Class Activation Mapping (Grad-CAM), random forest algorithms, and statistical analysis, the research investigates the correlations between supervised CNN features and key physical characteristics related with the separation region, shock wave, leading edge suction peak, and post-shock loading. Finally, physical buffet onset metric is established with good generalization and accuracy, providing valuable guidance for engineering design in civil aircraft. |
| format | Article |
| id | doaj-art-06c26574fa6c439da55f859fd01c7207 |
| institution | Kabale University |
| issn | 2199-4536 2198-6053 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Springer |
| record_format | Article |
| series | Complex & Intelligent Systems |
| spelling | doaj-art-06c26574fa6c439da55f859fd01c72072025-02-02T12:48:53ZengSpringerComplex & Intelligent Systems2199-45362198-60532024-11-0111111810.1007/s40747-024-01612-yAdvancing buffet onset prediction: a deep learning approach with enhanced interpretability for aerodynamic engineeringJing Wang0Wei Liu1Hairun Xie2Miao Zhang3School of Aeronautics and Astronautics, Shanghai Jiao Tong UniversityShanghai Aircraft Design and Research InstituteKey Laboratory for Satellite Digitalization Technology, Innovation Academy for Microsatellites of CASShanghai Aircraft Design and Research InstituteAbstract The interaction between the shock wave and boundary layer of transonic wings can trigger periodic self-excited oscillations, resulting in transonic buffet. Buffet severely restricts the flight envelope of civil aircraft and is directly related to their aerodynamic performance and safety. Developing efficient and reliable techniques for buffet onset prediction is crucial for the advancement of civil aircraft. In this study, utilizing a comprehensive database of supercritical airfoils generated through numerical simulations, a convolutional neural network (CNN) model is firstly developed to perform buffet classification based on the flow fields. After that, employing explainable machine learning techniques, including Gradient-weighted Class Activation Mapping (Grad-CAM), random forest algorithms, and statistical analysis, the research investigates the correlations between supervised CNN features and key physical characteristics related with the separation region, shock wave, leading edge suction peak, and post-shock loading. Finally, physical buffet onset metric is established with good generalization and accuracy, providing valuable guidance for engineering design in civil aircraft.https://doi.org/10.1007/s40747-024-01612-yTransonic buffetDeep learningExplainable machine learningAerodynamic design |
| spellingShingle | Jing Wang Wei Liu Hairun Xie Miao Zhang Advancing buffet onset prediction: a deep learning approach with enhanced interpretability for aerodynamic engineering Complex & Intelligent Systems Transonic buffet Deep learning Explainable machine learning Aerodynamic design |
| title | Advancing buffet onset prediction: a deep learning approach with enhanced interpretability for aerodynamic engineering |
| title_full | Advancing buffet onset prediction: a deep learning approach with enhanced interpretability for aerodynamic engineering |
| title_fullStr | Advancing buffet onset prediction: a deep learning approach with enhanced interpretability for aerodynamic engineering |
| title_full_unstemmed | Advancing buffet onset prediction: a deep learning approach with enhanced interpretability for aerodynamic engineering |
| title_short | Advancing buffet onset prediction: a deep learning approach with enhanced interpretability for aerodynamic engineering |
| title_sort | advancing buffet onset prediction a deep learning approach with enhanced interpretability for aerodynamic engineering |
| topic | Transonic buffet Deep learning Explainable machine learning Aerodynamic design |
| url | https://doi.org/10.1007/s40747-024-01612-y |
| work_keys_str_mv | AT jingwang advancingbuffetonsetpredictionadeeplearningapproachwithenhancedinterpretabilityforaerodynamicengineering AT weiliu advancingbuffetonsetpredictionadeeplearningapproachwithenhancedinterpretabilityforaerodynamicengineering AT hairunxie advancingbuffetonsetpredictionadeeplearningapproachwithenhancedinterpretabilityforaerodynamicengineering AT miaozhang advancingbuffetonsetpredictionadeeplearningapproachwithenhancedinterpretabilityforaerodynamicengineering |