Multi-Objective Aerodynamic Optimization of Ride Height and Rake Angle in a Sedan Car Using CFD and Machine Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915477293367296 |
|---|---|
| author | Kheirkhah, Mahdi Roohi, Ehsan Pasandidehfard, Mahmoud |
| author_facet | Kheirkhah, Mahdi Roohi, Ehsan Pasandidehfard, Mahmoud |
| contents | This study investigates the aerodynamic performance of an Audi A4 sedan using CFD analysis. A 3D model was developed in SolidWorks and validated against DrivAer Notchback wind-tunnel data, showing only a 3.25 percent deviation in drag coefficient (Cd). Ride height varied from 1.336 to 1.536 m and rake angle from 0 to 5 degrees, across four Reynolds numbers. Gradient Boosting emerged as the most accurate predictive model (R square = 0.97 for Cd and 0.96 for lift coefficient, Cl), outperforming Random Forest and LightGBM. Differential Evolution optimization was performed under balanced, drag-focused, and downforce-focused conditions. Reynolds number had minimal impact on optimum location; therefore, detailed results are reported for one Reynolds number, with other Re showing similar trends. The baseline geometry exhibited Cd = 0.313 and Cl = 0.0288. Balanced optimization achieved Cd = 0.287 and Cl = - 0.0826. Minimum drag condition reached Cd = 0.285 with slight positive lift (Cl = 0.0142), while maximum downforce optimization reached Cl = - 0.1084 with a 6.71 percent drag penalty (Cd = 0.334). Near-optimal solutions were found within ride heights of 1.341 to 1.365 m and rakes of 0.158 to 4.610 degrees, indicating robust aerodynamic performance. Machine learning predictions were further validated against CFD with a small error in Cd. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_02917 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multi-Objective Aerodynamic Optimization of Ride Height and Rake Angle in a Sedan Car Using CFD and Machine Learning Kheirkhah, Mahdi Roohi, Ehsan Pasandidehfard, Mahmoud Fluid Dynamics This study investigates the aerodynamic performance of an Audi A4 sedan using CFD analysis. A 3D model was developed in SolidWorks and validated against DrivAer Notchback wind-tunnel data, showing only a 3.25 percent deviation in drag coefficient (Cd). Ride height varied from 1.336 to 1.536 m and rake angle from 0 to 5 degrees, across four Reynolds numbers. Gradient Boosting emerged as the most accurate predictive model (R square = 0.97 for Cd and 0.96 for lift coefficient, Cl), outperforming Random Forest and LightGBM. Differential Evolution optimization was performed under balanced, drag-focused, and downforce-focused conditions. Reynolds number had minimal impact on optimum location; therefore, detailed results are reported for one Reynolds number, with other Re showing similar trends. The baseline geometry exhibited Cd = 0.313 and Cl = 0.0288. Balanced optimization achieved Cd = 0.287 and Cl = - 0.0826. Minimum drag condition reached Cd = 0.285 with slight positive lift (Cl = 0.0142), while maximum downforce optimization reached Cl = - 0.1084 with a 6.71 percent drag penalty (Cd = 0.334). Near-optimal solutions were found within ride heights of 1.341 to 1.365 m and rakes of 0.158 to 4.610 degrees, indicating robust aerodynamic performance. Machine learning predictions were further validated against CFD with a small error in Cd. |
| title | Multi-Objective Aerodynamic Optimization of Ride Height and Rake Angle in a Sedan Car Using CFD and Machine Learning |
| topic | Fluid Dynamics |
| url | https://arxiv.org/abs/2509.02917 |