Design of uav robust autopilot based on adaptive neuro-fuzzy inference system
DOI:
https://doi.org/10.18372/2306-1472.37.1624Abstract
This paper is devoted to the application of adaptive neuro-fuzzy inference systems to the robust control of the UAV longitudinal motion. The adaptive neore-fuzzy inference system model needs to be trained by input/output data. This data were obtained from the modeling of a ”crisp” robust control system. The synthesis of this system is based on the separation theorem, which defines the structure and parameters of LQG-optimal controller, and further - robust optimization of this controller, based on the genetic algorithm. Such design procedure can define the rule base and parameters of fuzzyfication and defuzzyfication algorithms of the adaptive neore-fuzzy inference system controller, which ensure the robust properties of the control system. Simulation of the closed loop control system of UAV longitudinal motion with adaptive neore-fuzzy inference system controller demonstrates high efficiency of proposed design procedure.
References
Tunik A.A., Abramovich E.A. Parametric Robust Optimization of Digital Flight Control Systems// Proc. of the National Aviation University. − 2003. − № 2. − P. 31–37.
Tunik A.A., Galaguz T. A. Robust Stabilization and Nominal Performance of the Flight Control System for Small UAV // Applied and Computational Mathematics. − 2004, Vol. 3, №1. −P. 34–45.
Tunik A. A. Touat M. A. Structured parametric optimization of multivariable robust control based on genetic algorithms // Proc. of the National Aviation University. − 2008. − № 2. − P. 10−17.
Robust Flight Control. A Design Challenge. J.-F. Magni, S. Bernani, J. Terlouw eds. Springer, London, 1997. − 649 p.
Tunik A.A., Touat M.A. Hard and Soft Computing in the Robust Flight Control Systems, Appl. Comput. Math. 5 (2006). − № 2. − P. 166−180.
Tunik A.A., Xu Guo Dong, Touat M.A. RobustAutopilots Based on the Fuzzy Model Reference Learning Control // Proc. of the National Aviation University. − 2006. − No.3 (29). −P. 30−38.
Jang J-S. R., Sun C-T., Neuro-Fuzzy and Soft Computing, a computational approach to learning and machine intelligence, by Prentice-hall, 1997. − 607 p.
Godjevac J. Neuro-fuzzy controllers, design and application. Press Polytechniques et universitaires, Romandes, 1997. − 149 p.
Fahd A. Alturki, Adel Ben Abdenour. Neuro-Fuzzy Control of a Steam Boiler-Turbine Unit. Proceeding of the 1999 IEEE // Intern. Conf. on Control Applications, Kohala Coat-Island of Hawai’i, USA August 22-27,1999. − P. 1050−1055.
Xian-Ku Zhang, Yi-Cheng, Ge Guo. ANFIS Applied to a ship autopilot design // Proc. of the Fifth Intern. Conf. on Machine Learning and Cybernetics, Dalian, 13-16 August 2006. 2006 IEEE. −P. 2233−2236.
Bihua Lin, Pu Han, Dongfeng Wang, Qigang Guo. Control of Boiler-Turbine Unit Based on Adaptive Neuro-Fuzzy Inference System. Power Engineering Department, North China Electric Power University. 2003 IEEE. − P. 2821−2826.
Passino K.M., Yurkovich S. Fuzzy Control. Addison-Wesley. − Menlo Park, Reading, Harlow, Berkley, Sidney, Bonn, Amsterdam, 1998. − 502 p.
Квакернаак Х., Сиван Р. Линейные оптимальные системы управления. − М.: Мир, 1977. − 653 с.
McLean, D. Automatic Flight Control Systems. Prentice Hall Inc., Englewood Cliffs. − 1990. − 593 p.
Aerosim Blockset // www.u-dynamics.com
Hung T. Nguyen, Nadipuram R. Prasad, Carol L. Walker, Elbert A. Walker. A First Course in FUZZY and NEURAL CONTROL. CHAPMAN &HALL/CRC. A CRC Press Company, Boca Raton, London, New York, Washington, D.C. 291 p.
Fuzzy logic toolbox TM 2, user guide www.mathworks.com
Dreyfus G., Martinez J.-M, Samuelides M., Réseaux de Neurons. Méthodologie et applications : Editions Eyrolles, 61, Bld Saint-Germain 75240 Paris cedex 05. Deuxième triage 2002. − 379 p.
Danuta Rutkowska. Neuro-Fuzzy Architectures and Hybrid Learning. Physica-Verlag, a Springer Company, Heidelberg; New York, 2002 (studies in fuzziness and soft computing), 241 p.
