飞控液压系统故障诊断方法研究

Research on fault diagnosis method of flight control hydraulic system

飞控液压系统作为飞机控制系统的关键装备,一旦其发生故障将对飞机的运行安全造成严重影响。以飞控液压系统——飞机舱门液压驱动系统为研究对象,基于其系统结构和基本原理使用AMESim平台进行仿真建模,并通过故障仿真模拟开展故障诊断研究工作,提出了一种基于多级注意力机制的自编码器-多层感知机故障诊断方法,可以有效指导装备的维护维修工作并提高装备的运行安全性。首先,通过自编码器进行特征提取;然后,基于多级注意力机制进一步挖掘关键特征信息;最后,利用多层感知机作为分类器开展故障诊断工作。实验结果表明,与其他传统的机器学习和深度学习模型相比,所提方法的故障诊断准确率达到了97.5%且假正类率仅为1.1%,充分证明了所提方法的有效性。

The flight control hydraulic system is a key equipment of the aircraft control system.Once it malfunctions,it will seriously affect the safe operation of the aircraft.This article takes the flight control hydraulic system-the hydraulic drive system of the aircraft door as the research object,based on its system structure and basic principles,uses the AMESim platform for simulation modeling,and conducts fault diagnosis research through fault simulation simulation.A multi-level attention mechanism-based autoencoder-multilayer perceptron fault diagnosis method is proposed that can effectively guide the maintenance and repair of equipment and improve the operational safety of the equipment.Firstly,feature extraction is performed using an autoencoder.Then,based on the multi-level attention mechanism,key feature information is further excavated.Finally,a multilayer perceptron is used as a classifier to carry out fault diagnosis.Experimental results show that compared with other traditional machine learning and deep learning models,the proposed method has a fault diagnosis accuracy of 97.5%and a false positive rate of only 1.1%,fully demonstrating the effectiveness of the proposed method.