Abstract
This paper proposes an unmanned aerial vehicle (UAV) flight tracking Control method based on BP neural network to improve the proportional-integral-differential (PID) control of four-rotor UAV flight tracking control. The traditional PID control cannot be updated in real time. K <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</sub> ,K <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i</sub> ,K <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">d</sub> parameters, BP neural network algorithm error convergence speed is slow, training learning is easy to fall into local optimal value, and so on. A control method combining BP neural network and PID control using genetic algorithm (GA) to optimize the additional inertia term is the designed. Through the global search ability of the genetic algorithm, the weight and threshold of the BP neural network are adjusted to improve the system convergence speed and system accuracy. Simulation analysis shows that comparison between the traditional PID and BP neural network-PID control, the proposed method improves the robustness and dynamic performance of the system, improves the convergence accuracy and convergence rate, and thus the attitude of the drone. Control adjustment tracking has a good practical reference value.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have