International Journal of Mechanical and Production Engineering (IJMPE)
.
Follow Us On :
current issues
Volume-11,Issue-11  ( Nov, 2023 )
Past issues
  1. Volume-11,Issue-10  ( Oct, 2023 )
  2. Volume-11,Issue-9  ( Sep, 2023 )
  3. Volume-11,Issue-8  ( Aug, 2023 )
  4. Volume-11,Issue-7  ( Jul, 2023 )
  5. Volume-11,Issue-6  ( Jun, 2023 )
  6. Volume-11,Issue-5  ( May, 2023 )
  7. Volume-11,Issue-4  ( Apr, 2023 )
  8. Volume-11,Issue-3  ( Mar, 2023 )
  9. Volume-11,Issue-2  ( Feb, 2023 )
  10. Volume-11,Issue-1  ( Jan, 2023 )

Statistics report
Feb. 2024
Submitted Papers : 80
Accepted Papers : 10
Rejected Papers : 70
Acc. Perc : 12%
Issue Published : 128
Paper Published : 2371
No. of Authors : 6757
  Journal Paper


Paper Title :
Exploring The Use of Ml Algorithms in Active Flow Control Strategy to Facilitate Real-Time Prediction of Aerodynamic Forces of Multi-Element Wings

Author :Kartikey Vishnu, Devdoot Chatterjee, Kartikey Gupta, Raj Kumar Singh

Article Citation :Kartikey Vishnu ,Devdoot Chatterjee ,Kartikey Gupta ,Raj Kumar Singh , (2023 ) " Exploring The Use of Ml Algorithms in Active Flow Control Strategy to Facilitate Real-Time Prediction of Aerodynamic Forces of Multi-Element Wings " , International Journal of Mechanical and Production Engineering (IJMPE) , pp. 13-19, Volume-11,Issue-5

Abstract : The task of determining the aerodynamic properties of a multi-element airfoil has historically been a difficult, time-consuming process, and impractical for real-time applications. Machine learning (ML) and deep learning (DL) have shown promise in predicting aerodynamic properties. However, there has been limited research on using these techniques for multi-wing systems. In this study, we explore the use of ML algorithms to predict the aerodynamic performance of a multielement wing, which has not been attempted in the literature. Training them on data generated using ANSYS Fluent, the models can predict these aerodynamic forces based on input parameters. Our approach has potential applications in optimizing the aerodynamic performance of high-speed vehicles, and may inspire further research in this area. The use of ensembling techniques further reduces computation time and power during offline stages. Thus reducing time taken for a cfd analysis from 10-15 minutes to 10-60 microseconds making it 1.0-6.0 ∗ 108 times faster. Keywords - Airfoil, Rear Wing, Deep Learning, Multi-Layer Perceptron, Autoencoders

Type : Research paper

Published : Volume-11,Issue-5


DOIONLINE NO - IJMPE-IRAJ-DOIONLINE-19764   View Here

Copyright: © Institute of Research and Journals

| PDF |
Viewed - 30
| Published on 2023-08-24
   
   
IRAJ Other Journals
IJMPE updates
Volume-11,Issue-10 (Oct, 2023 )
The Conference World

JOURNAL SUPPORTED BY