Aileron Actuator Fault Diagnosis Method and Device Based on Amesim Model

Abstract

The embodiment of the present application provides an aileron actuator fault diagnosis method and device based on the AMESim model, which relate to the technical field of aircraft. The fault diagnosis model is obtained by training the pre-built deep neural network model, and the fault diagnosis model is used to conduct fault analysis on the working condition data of the aileron actuator to determine whether there is a fault in the aileron actuator. The feature extraction of the time series signal in the multi-source fusion monitoring information of the actuator avoids the gradient dispersion and improves the accuracy of fault diagnosis and recognition.

Description

technical field [0001] The present application relates to the field of aircraft technology, in particular, to a method and device for fault diagnosis of aileron actuators based on the AMESim model. Background technique [0002] Electric hydrostatic actuator is a system-type actuator that integrates electronic components, hydraulic components and mechanical components. It is widely used in in the flight control system of the aircraft. As the key nerve center of the aircraft, the flight control system may cause the aircraft to lose normal flight control and cause catastrophic accidents once it fails. [0003] As a key electric hydrostatic actuator in the flight control system to ensure that the aircraft achieves lifting and stable flight tasks, the aileron actuator inevitably has structural complexity, that is, the system has the characteristics of redundant structure, so as to ensure When the structure or function of a certain functional transmission path is abnormal, the f...

AI Technical Summary

Problems solved by technology

[0004] However, such a redundant structure also leads to the diversity, suddenness, and complexity of the causes of failures. Nowadays, the health monitoring of aileron actuators often adopts the strategy of after-the-fact maintenance, that is, after the failure occurs and in the aircraft Health maintenance and protection can only be achieved after landing

In recent years, equipment health status assessment based on sensor monitoring data has been extensively studied, but there are still deficiencies in data-driven aileron actuator fault diagnosis research, that is, the coverage of fault types involved in fault diagnosis research is low and lacks The diagnosis and identification of compound fault types and the actual aileron actuator cannot be simulated for fault implantation and it is difficult to obtain a large amount of fault monitoring data. The above problems lead to low accuracy of fault detection for aileron actuators

Images