ACTA AERONAUTICAET ASTRONAUTICA SINICA >
Aerodynamic parameter identification of non-stall and near-stall flight data using recurrent neural networks
Received date: 2024-11-01
Revised date: 2024-12-16
Accepted date: 2025-04-02
Online published: 2025-04-10
Supported by
National Natural Science Foundation of China(12402272);Natural Science Basic Research Program of Shaanxi Province(2024JC-YBQN-0024);Fundamental Research Funds for the Central Universities(D5000240030)
This paper proposes a new aerodynamic parameter identification method that combines a Gated Recurrent Unit （GRU） neural network model and the Gauss-Newton （GN） optimization algorithm， aiming to accurately identify the unknown aerodynamic parameters from longitudinal flight data generated by a self-developed small-sized Unmanned Aerial Vehicle （UAV） and ATTAS aircraft. The GRU network model was designed and then trained to characterize the chosen aircraft systems’ dynamics while avoiding numerical integrals of the postulated dynamic models. The GN optimization algorithm incorporates the trained GRU network model to obtain high-confidence identification results by iteratively minimizing a cost function concerning the unknown aerodynamic parameters. The measured flight data used in this study includes non-stall flight data from the self-developed UAV and near-stall flight data from the ATTAS aircraft. The study results demonstrate that the GRU network model can maintain reliable prediction effects for the non-stall and near-stall flight data by adjusting the corresponding network parameters such as the number of hidden layers， number of units in each hidden layer， dropout rate， time-step， and learning rate. Furthermore， the effectiveness of the proposed parameter identification method is confirmed by comparing the identified aerodynamic parameters with the corresponding wind tunnel or reference values.
Zhe HUI , Dongyue DU , Yuting LIU , Min CHANG , Junqiang BAI . Aerodynamic parameter identification of non-stall and near-stall flight data using recurrent neural networks[J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2025 , 46(23) : 131483 -131483 . DOI: 10.7527/S1000-6893.2025.31483
| [1] | HAMEL P G， JATEGAONKAR R V. Evolution of flight vehicle system identification［J］. Journal of Aircraft， 1996， 33（1）： 9-28. |
| [2] | JATEGAONKAR R V. Flight vehicle system identification： A time-domain methodology， second edition［R］. Reston： AIAA， 2015. |
| [3] | SIMMONS B M， MCCLELLAND H G， WOOLSEY C A. Nonlinear model identification methodology for small， fixed-wing， unmanned aircraft［J］. Journal of Aircraft， 2019， 56（3）： 1056-1067. |
| [4] | HUI Z， CHEN G. Aerodynamic parameter estimation for a morphing unmanned aerial vehicle from flight tests［J］. Journal of Aerospace Information Systems， 2023， 20（9）： 588-595. |
| [5] | SEO G G， KIM Y， SADERLA S. Kalman-filter based online system identification of fixed-wing aircraft in upset condition［J］. Aerospace Science and Technology， 2019， 89： 307-317. |
| [6] | PEYADA N K， SEN A， GHOSH A K. Aerodynamic characterization of HANSA-3 aircraft using equation error， maximum likelihood and filter error methods［C］∥ Proceedings of the International MultiConference of Engineers and Computer Scientists 2008 （IMECS 2008）. Hongkong： IAENG， 2008. |
| [7] | TAI S， WANG L X， WANG Y L， et al. Flight dynamics modeling and aerodynamic parameter identification of four-degree-of-freedom virtual flight test［J］. AIAA Journal， 2023， 61（6）： 2652-2665. |
| [8] | CHOWDHARY G， JATEGAONKAR R. Aerodynamic parameter estimation from flight data applying extended and unscented Kalman filter［J］. Aerospace Science and Technology， 2010， 14（2）： 106-117. |
| [9] | KUMAR R， GHOSH A K， MISRA A. Parameter estimation from flight data of hansa-3 aircraft using quasi-steady stall modeling［J］. Journal of Aerospace Engineering， 2013， 26（3）： 544-554. |
| [10] | SADERLA S， KIM Y， GHOSH A K. Online system identification of mini cropped delta UAVs using flight test methods［J］. Aerospace Science and Technology， 2018， 80： 337-353. |
| [11] | HESS R. On the use of back propagation with feed-forward neural networks for the aerodynamic estimation problem： AIAA-1993-3638［R］. Reston： AIAA， 1993. |
| [12] | LINSE D J， STENGEL R F. Identification of aerodynamic coefficients using computational neural networks［J］. Journal of Guidance， Control， and Dynamics， 1993， 16（6）： 1018-1025. |
| [13] | GHOSH A K， RAISINGHANI S C， KHUBCHANDANI S. Estimation of aircraft lateral-directional parameters using neural networks［J］. Journal of Aircraft， 1998， 35（6）： 876-881. |
| [14] | RAISINGHANI S C， GHOSH A K， KALRA P K. Two new techniques for aircraft parameter estimation using neural networks［J］. The Aeronautical Journal， 1998， 102（1011）： 25-30. |
| [15] | SINGH S， GHOSH A. Parameter estimation from flight data of a missile using maximum likelihood and neural network method： AIAA-2006-6284［R］. Reston： AIAA， 2006. |
| [16] | DAS S， KUTTIERI R A， SINHA M， et al. Neural partial differential method for extracting aerodynamic derivatives from flight data［J］. Journal of Guidance， Control， and Dynamics， 2010， 33（2）： 376-384. |
| [17] | PEYADA N K， GHOSH A K. Aircraft parameter estimation using a new filtering technique based upon a neural network and Gauss-Newton method［J］. The Aeronautical Journal， 2009， 113（1142）： 243-252. |
| [18] | PEYADA N， GHOSH A. Aircraft parameter estimation using neural network based algorithm： AIAA-2009- 5941［R］. Reston： AIAA， 2009. |
| [19] | KUMAR R， GHOSH A K. Nonlinear aerodynamic modeling from flight data at high angles of attack using neural-Gauss-Newton method： AIAA-2015-2707［R］. Reston： AIAA， 2015. |
| [20] | SADERLA S， DHAYALAN R， GHOSH A K. Parameter estimation from near stall flight data using conventional and neural-based methods［J］. Defence Science Journal， 2016， 67（1）： 3-11. |
| [21] | SADERLA S， DHAYALAN R， SINGH K， et al. Longitudinal and lateral aerodynamic characterisation of reflex wing unmanned aerial vehicle from flight tests using maximum likelihood， least square and neural gauss newton methods［J］. The Aeronautical Journal， 2019， 123（1269）： 1807-1839. |
| [22] | WANG Z G， LI A J， WANG L H， et al. Aerodynamic coefficients modeling using Levenberg-Marquardt algorithm and network［J］. Aircraft Engineering and Aerospace Technology， 2022， 94（3）： 336-350. |
| [23] | VERMA H O， PEYADA N K. Parameter estimation of unstable aircraft using extreme learning machine［J］. Defence Science Journal， 2017， 67（6）： 603-611. |
| [24] | VERMA H O， PEYADA N. Parameter estimation of stable and unstable aircraft using extreme learning machine： AIAA-2018-0526［R］. Reston： AIAA， 2018. |
| [25] | VERMA H O， PEYADA N K. Estimation of aerodynamic parameters near stall using maximum likelihood and extreme learning machine-based methods［J］. The Aeronautical Journal， 2021， 125（1285）： 489-509. |
| [26] | VERMA H O， PEYADA N K. Estimation of longitudinal aerodynamic parameters using recurrent neural network［J］. The Aeronautical Journal， 2023， 127（1308）： 255-267. |
| [27] | HUI Z， KONG Y N， YAO W G， et al. Aircraft parameter estimation using a stacked long short-term memory network and Levenberg-Marquardt method［J］. Chinese Journal of Aeronautics， 2024， 37（2）： 123-136. |
| [28] | HUANG G B， ZHU Q Y， SIEW C K. Extreme learning machine： Theory and applications［J］. Neurocomputing， 2006， 70（1-3）： 489-501. |
| [29] | HOCHREITER S， SCHMIDHUBER J. Long short-term memory［J］. Neural Computation， 1997， 9（8）： 1735-1780. |
| [30] | CHO K， VAN MERRIENBOER B， GULCEHRE C， et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation ［DB/OL］. arXiv preprint：1406.1078， 2014. |
| [31] | DEY R， SALEM F M. Gate-variants of gated recurrent unit （GRU） neural networks［C］∥2017 IEEE 60th International Midwest Symposium on Circuits and Systems （MWSCAS）. Piscataway： IEEE Press， 2017： 1597-1600. |
| [32] | SRIVASTAVA N， HINTON G E， KRIZHEVSKY A， et al. Dropout： A simple way to prevent neural networks from overfitting［J］. Journal of Machine Learning Research， 2014， 15（1）： 1929-1958. |
| [33] | HUI Z， ZHANG Y， CHEN G. Aerodynamic performance investigation on a morphing unmanned aerial vehicle with bio-inspired discrete wing structures［J］. Aerospace Science and Technology， 2019， 95： 105419. |
| [34] | XU D， HUI Z， LIU Y Q， et al. Morphing control of a new bionic morphing UAV with deep reinforcement learning［J］. Aerospace Science and Technology， 2019， 92： 232-243. |
| [35] | GLOROT X， BENGIO Y. Understanding the difficulty of training deep feedforward neural networks［C］∥Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics （AISTATS）. Brookline： Microtome Publishing， 2010. |
/
| 〈 |
|
〉 |
CJA