Simulation modeling of free shipless inertial navigation system UAV based on neural network algorithms.

Abstract

The object of the article is the process of controlling the trajectory of unmanned aerial vehicles (UAVs) in autonomous flight mode based on neural network algorithms. The study is based on the application of numerical-analytical approach to the selection of modern technical solutions for building standard models of platformless inertial navigation systems (BINS) for micro- and small UAVs with subsequent reinforcement of assumptions in the simulation environment, which allowed: MEMS-based technology (using microelectromechanical systems) and Arduino microcomputers, and monitor its operation during the disappearance of the GPS signal; secondly, to experimentally determine the nature of the influence of the structure of the selected neural network on the process of formation of navigation data. Thus, to evaluate the effectiveness of the proposed solutions for the construction of BINS, a comparative analysis of the application of two ELM (Extreme Learning Machine) algorithms - Kalman and WANN (Wavelet Artificial Neural Network - RNN (Recurrent Neural Network) - Madgwick in the form of two experiments. The purpose of the experiments was determined: the study of the influence of the number of neurons of the latent level of the neural network on the accuracy of the approximation of navigation data; determination of the speed of the process of adaptive learning of neural network algorithms BINS UAV. The results of the experiments showed that the use of the algorithm based on ELM - Kalman provides better accuracy of learning the BINS neural network compared to the WANN - RNN - Madgwick algorithm. However, it should be noted that the accuracy of training improved with the number of neurons in the structure of the latent level <500, which increases computational complexity and increases the learning process, which may complicate practical implementation using micro- and small UAV equipment.