Aircraft actuator fault diagnosis method based on AdaBoost-ASVM algorithm

Abstract

The invention discloses an aircraft actuator fault diagnosis method based on an AdaBoost-ASVM algorithm. With common jamming, loose floating, damage and reverse faults of an aircraft actuator as research objects, collected various fault signals and signals in a normal state are subjected to integrated empirical mode decomposition to obtain a series of stable intrinsic mode functions (IMF) and residual errors; a large number of time domain characteristic parameters are calculated for each intrinsic mode function and residual error; principal component analysis is carried out on the characteristic parameters by utilizing a principal component analysis method, and characteristics with relatively high contribution rates are extracted to construct a training set and a test set; and finally, an AdaBoost-ASVM classifier is established on the training set, and whether the actuator has a fault or not and the type of the fault are determined. The method is high in calculation speed and high inrecognition precision, and can be effectively applied to fault diagnosis of the aircraft actuator.

Description

technical field [0001] The invention relates to an aircraft actuator fault diagnosis method, in particular to an aircraft actuator fault diagnosis method based on the AdaBoost-ASVM algorithm. Background technique [0002] Aircraft is one of the most frequently used aircraft in the world, and people have higher and higher requirements for its safety and reliability. With the increase in the complexity of airborne equipment and the close connection between various systems, the probability of aircraft failure also increases. The aircraft actuator is the aircraft control surface system, which is the most important device to control the movement of the aircraft. During the flight, the actuator will frequently perform control tasks. If things go on like this, the intermittent rotation will easily cause the actuator to fail. Signals with faults entering the flight control system will directly affect the maneuverability of the aircraft, which is very likely to cause a major acciden...

AI Technical Summary

Problems solved by technology

However, the former only targets three kinds of faults, and the coverage is not wide; the latter only extracts one feature, and the fault information cannot be fully utilized.

Images