UNMANNED AIR VEHICLE STABILIZATION BASED ON NEURAL NETWORK REGULATOR

 A problem of stabilizing for the multirotor unmanned aerial vehicle in an environment with external disturbances is researched. A classic proportional-integral-derivative controller is analyzed, its flaws are outlined: inability to respond to changing of external conditions and the need for manual adjustment of coefficients. The paper presents an adaptive adjustment method for coefficients of the proportional-integral-derivative controller based on neural networks. A neural network structure, its input and output data are described. Neural networks with three layers are used to create an adaptive stabilization system for the multirotor unmanned aerial vehicle. Training of the networks is done with the back propagation method. Each neural network produces regulator coefficients for each angle of stabilization as its output. A method for network training is explained. Several graphs of transition process on different stages of learning, including processes with external disturbances, are presented. It is shown that the system meets stabilization requirements with sufficient number of iterations. Described adjustment method for coefficients can be used in remote control of unmanned aerial vehicles, operating in the changing environment.

1. Belyaev S.S., Budko M.B., Budko M.Y., Guirik A.V., Zhigulin G.P. Functional design of flight and navigation controller unit for multirotor unmanned aerial vehicle. Radiopromyshlennost', 2015, no. 4, pp. 77–87.
2. Shepherd III J.F., Tumer K. Robust neuro-control for a micro quadrotor. Proc. 12th Annual Genetic and Evolutionary Computation Conference, GECCO’10. Portland, USA, 2010. doi: 10.1145/1830483.1830693
3. Bobtsov A.A., Pyrkin A.A. Adaptive and Robust Control with Uncertainties Compensation. St. Petersburg, NRU ITMO, 2013, 135 p. (In Russian)
4. Salichon M., Tumer K. A neuro-evolutionary approach to micro aerial vehicle control. Proc. 12th Annual Genetic and Evolutionary Computation Conference, GECCO’10. Portland, USA, 2010, pp. 1123–1130. doi: 10.1145/1830483.1830692
5. Evgenov A.A. Neuro-controller of quadcopter control system. Modern Problems of Science and Education, 2013, no. 5, p. 61.
6. Chowdhary G., Johnson N.E. Adaptive neural network flight control using both current and recorded data. AIAA Guidance, Navigation and Control Conference. Hilton Head, USA, 2007, pp. 1721–1740.
7. Rivas-Echeverria F., Rios-Bolivar A., Casales-Echeverria J. Neural network-based auto-tuning for PID controllers. Neural Network World, 2001, vol. 11, no. 3, pp. 277–284.
8. Ziegler J.G., Nichols N.B. Optimum settings for automatic controllers. Trans. ASME, 1942, vol. 64, pp. 759–768.
9. Shahrokhi M., Zomorrodi A. Comparison of PID controller tuning methods. 2012. Available at: http://www.ie.itcr.ac.cr/einteriano/control/clase/Zomorrodi_Shahrokhi_PID_tunning_comparison.pdf (accessed 02.08.2016).
10. Melkov D.A. Comparison of methods for setting the PID parameters of the oscillations disturbance variable. Young Scientist, 2013, no. 4, pp. 72–76.
11. Mikhailenko V.S., Lozhechnikov V.F. Metody nastroiki nechetkogo adaptivnogo PID-regulyatora. Avtomatika. Avtomatizatsiya. Elektrotekhnicheskie Kompleksy i Sistemy, 2009, no. 2, p. 174. (In Russian)
12. Rojas R. Neural Networks. A Systematic Introduction. Berlin, Springer-Verlag, 1996, 502 p. doi: 10.1007/978-3-642-61068-4
13. Eberhart R.C., Dobbins R.W. Neural Network PC Tools: a Practical Guide. London, Academic Press, 1990.
14. Maren A.J., Harston C.T., Pap R.M. Handbook of Neural Computing Applications. Academic Press, 2001, 448 p.
15. Karsoliya S. Approximating number of hidden layer neurons in multiple hidden layer BPNN architecture. International Journal of Engineering Trends and Technology, 2012, vol. 31, no. 6, pp. 714–717.
 

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License