Unmanned air vehicle attitude robust fault tolerance control method based on neural network observer

Abstract

Based on a neural network technology and an instruction filtering inversion method, the invention discloses a robust fault tolerance control system design structure based on instruction filtering inversion. Firstly, a mathematical model of an NSV attitude control system is given out, uncertainties and external disturbance caused by modeling errors are considered based on the mathematical model, a state equation of the NSV attitude control system under the fault of a control surface is also considered. The method mainly includes the two design parts including design of an auxiliary system and design of a controller based on the auxiliary system. The auxiliary system is introduced into the neural network to ensure robustness of the auxiliary system, and stability of a closed-loop system is strictly proved through Lyapunov theorem. Meanwhile, simulation is carried out on an attitude control system of a corresponding air vehicle, and a result shows that the method enables the uncertain flight control system with the external disturbance to have the ideal fault tolerance tracking performance under damage to the control surface.

Description

technical field [0001] The invention relates to the field of aircraft attitude fault-tolerant control, in particular to an unmanned aerial vehicle attitude robust fault-tolerant control method based on a neural network observer. [0002] Background technique [0003] Near space (Near Space) refers to the space area 20km~100km away from the sea level, and current human exploration activities rarely involve this height range. It has the atmospheric stratosphere region (height 20km~55km), the atmospheric mesosphere region (height 55km~85km) and a small part of the warming layer region (height above 85km), of which the region below 60km is the non-ionosphere, and the region above 60km is the The ionosphere, the atmospheric composition in most of its space is a homogeneous atmosphere (the area below about 90km in height). It is precisely because of its unique spatial location that the near space has a unique flight environment and nature, so it has great strategic significance ...

AI Technical Summary

Problems solved by technology

However, nonlinear predictive control is still immature in system stability analysis.

Inversion control is a controller design method based on Lyapunov stability theory. It has been widely concerned by researchers since it was proposed in the 1990s. However, it also has three main defects. (1) Differential expansion problem ; (2) requires a strict feedback form, (3) controls the constraint problem

In the flight control system, the defects (1) and (3) are the main obstacles to its practical application, especially the defect (3), if it is not considered in practice, it will cause the accumulation of errors and make the parameter estimation incorrect , causing system instability or even divergence

Images