A Gray-Box Non-Parametric Aircraft System Identification Method Using the ANFIS Network for Prediction of High Angle of Attack Maneuvers

Document Type : Research Article

Authors

1 Department of Mechanical Engineering, Najafabad Branch, Islamic Azad University, Najafabad, Iran

2 Department of Aerospace Engineering, Amirkabir University of Technology, Tehran, IRAN.

Abstract

This paper aims to identify a gray-box non-parametric model for the airplane nonlinear aerodynamics throughout high angle of attack maneuvers using the Adaptive Neuro-Fuzzy Inference System (ANFIS). The gray-box modeling is employed in this paper in which the force and moments are predicted rather than the flight parameters. Flight test data of a large-scale unpowered model of a fighter airplane is modeled by ANFIS, and the results are compared with the traditional multi-layer feed forward Artificial Neural Network (ANN). The employed gray-box identification method considers both the nonlinearity and the longitudinal-lateral/directional coupling effects. The control commands and the flight conditions are the inputs to the system identification block while the force and moment coefficients are the targets. The optimal values for the ANFIS parameters are adjusted by the hybrid learning algorithm in order to minimize the Mean Squared Error (MSE) between the best estimated, target force, and moment coefficients while the ANN is trained by several learning algorithms. The precision of the model is checked during the training and test phases for a single flight condition. Afterwards, the generalization of the model is checked for flight conditions dissimilar from the training one. The results indicate that the ANN has moderate precision in the test phase while the ANFIS has excellent precision. Furthermore, based on the results, the ANN predictions cannot follow the flight data in flight conditions dissimilar from the training ones while the ANFIS seems quite robust in those conditions.

Keywords

Main Subjects


[1] Batterson, J.G. and Klein, V., 1989. Partitioning of flight data for aerodynamic modeling of aircraft at high angles of attack. Journal of Aircraft26(4), pp.334-339.
[2] Dias, J.N., 2015. Unsteady and Post-Stall Model Identification Using Dynamic Stall Maneuvers. In AIAA Atmospheric Flight Mechanics Conference (p. 2705).
[3] Klein, V., Batterson, J.G. and Murphy, P.C., 1981. Determination of airplane model structure from flight data by using modified stepwise regression. NASA Technical Publication (TP), NASA-TP-1916.
[4] Bagherzadeh, S.A., Sabzeparvar, M. and Karrari, M., 2015. Nonlinear aerodynamic model identification using empirical mode decomposition. Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering229(9), pp.1588-1605.
[5] Roudbari, A. and Saghafi, F., 2016. Generalization of ANN-based aircraft dynamics identification techniques into the entire flight envelope. IEEE Transactions on Aerospace and Electronic Systems52(4), pp.1866-1880.
[6] Verma, H.O. and Peyada, N.K., 2020. Aircraft parameter estimation using ELM network. Aircraft Engineering and Aerospace Technology. 92(6), pp. 895-907.
[7] Sanwale, J. and Singh, D.J., 2018. Aerodynamic parameters estimation using radial basis function neural partial differentiation method. Defence Science Journal68(3), p.241.
[8] Talwar, A., Lokhande, G., Jain, R. and Singh, S., 2017, August. Estimation of aerodynamic parameters using Cascade Forward Back Propagation. In 2017 2nd International Conference on Telecommunication and Networks (TEL-NET) (pp. 1-6). IEEE.
[9] Mohamed, M. and Dongare, V., 2018. Aircraft neural modeling and parameter estimation using neural partial differentiation. Aircraft Engineering and Aerospace Technology. 90(5), pp. 764-778.
[10] Fan, H.Y., Dulikravich, G.S. and Han, Z.X., 2005. Aerodynamic data modeling using support vector machines. Inverse Problems in Science and Engineering13(3), pp.261-278.
[11] Majeed, M. and Kar, I.N., 2013. Aerodynamic parameter estimation using adaptive unscented Kalman filter. Aircraft Engineering and Aerospace Technology. 85(4), pp. 267-279.
[12] Chowdhary, G. and Jategaonkar, R., 2010. Aerodynamic parameter estimation from flight data applying extended and unscented Kalman filter. Aerospace science and technology14(2), pp.106-117.
[13] Göttlicher, C., Gnoth, M., Bittner, M. and Holzapfel, F., 2016. Aircraft parameter estimation using optimal control methods. In AIAA Atmospheric Flight Mechanics Conference (p. 1534).
[14] Saghafi, F. and Roudbari, A., 2014. Modeling and Identification of Fighter Aircraft Nonlinear Flight Dynamics, by Using Fuzzy Logic Algorithm. In Proc. of the Scientific Cooperation’s Intern. Workshops on Engineering Branches, Istanbul, Turkey (pp. 9-17).
[15] Kouba, G., Botez, R.M. and Boely, N., 2010. Fuzzy logic method use in F/A-18 aircraft model identification. Journal of aircraft47(1), pp.10-17.
[16] Hemakumara, P. and Sukkarieh, S., 2011, May. Non-parametric UAV system identification with dependent Gaussian processes. In 2011 IEEE International Conference on Robotics and Automation (pp. 4435-4441). IEEE.
[17] Mohammadi, S.J., Sabzeparvar, M. and Karrari, M., 2010. Aircraft stability and control model using wavelet transforms. Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering224(10), pp.1107-1118.
[18] Bagherzadeh, S.A., 2018. Nonlinear aircraft system identification using artificial neural networks enhanced by empirical mode decomposition. Aerospace Science and Technology75, pp.155-171.
[19] Verma, H.O. and Peyada, N.K., 2017, January. Modelling of aircraft’s dynamics using least square support vector machine regression. In International Conference on Mathematics and Computing (pp. 132-140). Springer, Singapore.
[20] Mengall G. Fuzzy modelling for aircraft dynamics identification. The Aeronautical Journal. 2001 Sep;105(1051):551-5.
[21] Roudbari, A. and Saghafi, F., 2017. Modeling and identification of highly maneuverable fighter aircraft dynamics using block-oriented nonlinear models. Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering231(7), pp.1293-1311.
[22] Lan, C.E., Li, J., Yau, W. and Brandon, J., 2002. Longitudinal and lateral-directional coupling effects on nonlinear unsteady aerodynamic modeling from flight data. In AIAA Atmospheric Flight Mechanics Conference and Exhibit (p. 4804).
[23] Kouba, G., Botez, R. M., & Boely, N., 2010. Fuzzy logic method use in F/A-18 aircraft model identification. Journal of aircraft, 47(1), pp.10-17.
[24] Jang, J.S., 1993. ANFIS: adaptive-network-based fuzzy inference system. IEEE transactions on systems, man, and cybernetics23(3), pp.665-685.
[25] Roy, A.G. and Peyada, N.K., 2017(a). Aircraft parameter estimation using hybrid neuro fuzzy and artificial bee colony optimization (HNFABC) algorithm. Aerospace Science and Technology71, pp.772-782.
[26] Roy, A.G. and Peyada, N.K., 2017(b). Lateral aircraft parameter estimation using neuro-fuzzy and genetic algorithm based method. In 2017 IEEE Aerospace Conference (pp. 1-11). IEEE.
[27] Roy, A.G. and Peyada, N.K., 2017(c). Longitudinal aircraft parameter estimation using neuro-fuzzy and genetic algorithm based method. In AIAA Atmospheric Flight Mechanics Conference (p. 3896).
[28] Kumar, A. and Ghosh, A.K., 2019. ANFIS-Delta method for aerodynamic parameter estimation using flight data. Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering233(8), pp.3016-3032.
[29] Holleman EC., 1976. Summary of flight tests to determine the spin and controllability characteristics of a remotely piloted, large-scale (3/8) fighter airplane model. NASA Technical Note (TN). NASA-TN-D-8052.