Analysis of the Possibility of Intellectualization of Algorithms for Estimating the Parameters of Dynamic Systems Based on Adaptive Model of Motion

Abstract

Existing onboard systems for processing measurement information do not always provide the necessary accuracy in estimating the parameters of movement of unmanned aerial vehicles. These errors are due to the use of kinematic motion models based on filtering algorithms, which does not allow to take into account the action of external forces on the control object.The possibility of intellectualizing the adaptive algorithms for estimating the parameters of dynamic systems is considered. The proposed adaptive motion model with an intelligent system to determine the adaptation parameter as a part of the angular position estimation filter makes it possible to increase the estimation accuracy in comparison with the classical Kalman filter. The effectiveness of the proposed approach is confirmed by the comparative analysis of the results of numerical modeling of the process of estimation of the roll angle of the unmanned aerial vehicle model.KeywordsIntellectualizationAdaptationDynamic systemsKalman filterDecompositionNeural networkUnmanned aerial vehicles