In this paper, aerodynamic parameters have been estimated using neuro-fuzzy-based novel approach (ANFIS-Delta). ANFIS-Delta is an extension of a feed-forward neural network based Delta method. This method augments the philosophies of an adaptive neuro-fuzzy inference system (ANFIS) in the Delta method. The current work studies the comparison of ANFIS-Delta estimated results with the existing methods using the flight data gathered on the Hansa-3 research aircraft at IIT Kanpur and also, demonstrates the efficacy of the algorithm on DLR HFB-320 aircraft data. Further, the robustness of the ANFIS-Delta is examined using simulated data with known measurement noise of various strength and estimated parameters are compared with the wind tunnel extracted aerodynamic parameters.
Jategaonkar RV. Flight vehicle system identification: A time domain methodology. AIAA Education Series. Reston, VA: AIAA, 2006.
2.
Eugene A. Morelli. Real-time aerodynamic parameter estimation without air flow angle measurements. Journal of Aircraft 2012; 49(4): 1064–1074.
3.
Peyada NK, Sinha A and Ghosh AK. Aerodynamic characterization of HANSA-3 aircraft using equation error, maximum likelihood, and filter error methods. In: Proceedings of the international multi-conference of engineers and computer scientists, Hong Kong, 2008.
4.
SadrelaSDhayalanRGhoshAK. Longitudinal parameter estimation from real flight data of unmanned cropped delta flat plate configuration. Int J Intell Unmanned Syst2016; 4: 2–22.
5.
Morelli E. Efficient global aerodynamic modeling from flight data. In: 50th aerospace sciences meeting, January 2012, pp.1–26. Reston, VA: AIAA.
6.
IgnatyevDKhrabrovAAlexanderN. Neural network modeling of unsteady aerodynamic characteristics at high angles of attack. Aerosp Sci Technol2015; 41: 106–115.
7.
SinghSGhoshAK. Estimation of lateral-directional parameters using neural networks based modified delta method. Aeronaut J2007; 111: 659–667.
8.
NellesO. Nonlinear system identification from classical approaches to neural networks and fuzzy models, Berlin Heidelberg: Springer, 2001.
9.
PeyadaNKGhoshAK. Aircraft parameter estimation using a new filtering technique based upon a neural network and Gauss-Newton method. Aeronaut J2009; 113: 243–252.
10.
Babuska R. Neuro-fuzzy methods for modeling and identification. In: Recent advances in intelligent paradigms and applications. Heidelberg: Springer, 2002, pp.161–186.
11.
Boëly N and Botez RM. New approach for the identification and validation of a nonlinear F/A-18 model by use of neural networks. IEEE Transactions on Neural Networks 2010; 21(11): 1759–1765.
12.
De JesusMotaSBotezRM. New helicopter model identification method based on a neural network optimization algorithm and on flight test data. Aeronaut J2011; 115: 295–314.
13.
Roy AG and Peyada NK. Lateral aircraft parameter estimation using neuro-fuzzy and genetic algorithm based method. In: IEEE aerospace conference, Big Sky, MT, USA, 4–11 March 2017, pp.1–11. New York: IEEE.
14.
Denai MA, Palis F and Zeghbib A. ANFIS based modelling and control of non-linear systems: A tutorial. In: IEEE international conference on systems, man and cybernetics, vol. 4, 2004. New York: IEEE..
15.
Ghosh AK, Raisinghani SC, and Sunil Khubchandani. Estimation of aircraft lateral-directional parameters using neural networks. Journal of Aircraft 1998; 35(6): 876–881.
16.
RaolJRGirijaGSinghJ. Modelling and parameter estimation of dynamic systems, London, UK: IET, 2004.
17.
Dongare V and Mohamed M. Lateral-directional aerodynamics parameter estimation using neural partial differentiation. In: International conference on cognitive computing and information processing, Noida, India, 3–4 March 2015; pp.1–6. IEEE.
18.
RogerJSSunCT. Neuro-fuzzy modeling and control. IEEE Trans Syst Man Cybernet1993; 23: 665–685.
19.
Grauer J and Morelli E. A new formulation of the filter-error method for aerodynamic parameter estimation in turbulence. In: AIAA atmospheric flight mechanics conference, Dallas, TX, USA, 22–26 June 2015.
20.
Dhayalan R. Parameter estimation of flight vehicles using conventional and neural based methods. PhD Thesis, IIT Kanpur, India, 2015.
21.
Chowdhary G and Jategaonkar R. Aerodynamic parameter estimation from flight data applying extended and unscented Kalman filter. Aerospace Science and Technology 2010; 14(2): 106–117.
