Modeling method and using method of dynamics network prediction model of unmanned aerial vehicle and related equipment

Abstract

The embodiment of the invention provides modeling and using methods and devices of a dynamics network prediction model of an unmanned aerial vehicle, a computer readable storage medium and electronic equipment, and belongs to the technical field of computers and communication. The modeling method comprises the following steps that: flight data of the unmanned aerial vehicle is acquired, wherein the flight data comprises training data; and a dynamic network prediction model of the unmanned aerial vehicle is trained by using the training data to complete modeling of the dynamic network prediction model, wherein the dynamic network prediction model of the unmanned aerial vehicle comprises a long-short term memory neural network and a full-connection neural network. According to the modeling method disclosed by the invention, modeling of the dynamic network prediction model of the unmanned aerial vehicle can be realized.

Description

technical field [0001] The present disclosure relates to the field of computer and communication technologies, and in particular, relates to the modeling, use method and device, computer-readable storage medium and electronic equipment of a UAV dynamics network prediction model. Background technique [0002] At present, the dynamic model modeling of fixed-wing UAV can be generally divided into mechanism analysis modeling method and parameter identification based on flight data. Traditional modeling methods generally use computational fluid dynamics (CFD) numerical calculations or wind tunnel blowing methods to obtain aerodynamic data, but these methods generally simplify to a certain extent and cannot effectively analyze unsteady parameters. However, using the actual flight data for identification, the obtained system model is closer to the dynamic characteristics in the actual operation process, but it is presented in the form of a definite expression so that it does not ha...

AI Technical Summary

Problems solved by technology

Traditional modeling methods generally use computational fluid dynamics (CFD) numerical calculations or wind tunnel blowing methods to obtain aerodynamic data, but these methods generally perform certain simplifications and cannot effectively analyze unsteady parameters

However, using the actual flight data for identification, the obtained system model is relatively close to the dynamic characteristics in the actual operation process, but it is presented in the form of a definite expression so that it does not have the dynamic optimality in an uncertain environment.

Images