A database construction method for fault detection of UAV flight control system

Abstract

The invention discloses a database construction method used for the fault detection of an unmanned aerial vehicle flight control system, and belongs to the technical field of the fault detection of an unmanned aerial vehicle. Normal unmanned aerial vehicle real-time flight control data screened through a judging rule is blended into historical data; whether unmanned aerial vehicle flight control data of an unknown fault at a future moment fails or not is judged through the judging rule trained according to the historical data; a reference database formed by normal historical data is dynamically updated so as to guarantee the real-time update of the judging rule and guarantee the real-time characteristic performance of the reference database formed by the normal historical data; and the judging rule which is dynamically updated can effectively detect various exceptional forms including isolated point exception, context exception, accumulation exception and the like in the unmanned aerial vehicle flight control data so as to effectively improve the recall ratio and the accuracy of fault detection and simultaneously lower a false alarm rate.

Description

technical field [0001] The invention discloses a database construction method for fault detection of a flight control system of an unmanned aerial vehicle, and belongs to the technical field of fault detection of an unmanned aerial vehicle. Background technique [0002] In recent years, with the introduction of the concept of failure prediction and health management technology (PHM) to the comprehensive management system of UAVs, the demand for informatization and intelligence of UAV safety management is increasing. The core part of drone safety management - safety monitoring and abnormal warning, can comprehensively monitor the health status of drones, which is of great significance to improve the safety performance of drones, ensure maintenance efficiency, and reduce the life cycle. As the core component of the UAV, the flight control system of the UAV is composed of various sensors, network links, actuators and other subsystems. The flight control sensor measures the real...

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to address the above-mentioned deficiencies in the background technology and provide a database construction method for the fault detection of the UAV flight control system, which realizes the fault detection database of the UAV flight control system by extracting normal data features online in real time The dynamic construction of the UAV flight control system solves the technical problem that the fault detection of the UAV flight control system cannot meet the needs of abnormal detection because it is difficult to extract each fault feature

Images