Aerospace engine abnormity intelligent detection method based on hierarchical adversarial training

Abstract

The invention discloses an aerospace engine abnormity intelligent detection method based on hierarchical adversarial training, and the method comprises the steps: employing a plurality of sensors to collect original signals of an aerospace engine in an operation state as multi-source data, intercepting a time sequence at a fixed length to obtain a multi-channel data sample set, and converting a one-dimensional sequence into a two-dimensional image; dividing the two-dimensional image sample into a training set and a test set; constructing a relative generative adversarial network as an anomalydetection model, and performing hierarchical adversarial training by using the training set; using the training model to evaluate the state of the training set sample, modeling the obtained evaluationscore distribution, and calculating the score threshold of the normal sample; using the model for evaluating the state of a test set, aggregating neighborhood information during testing, and conducting anomaly detection according to a score threshold value. According to the method, the model detection capability is improved through hierarchical adversarial training, multi-source information is fused, neighborhood information is aggregated to improve the result reliability, and finally, intelligent detection of abnormal operation of the aerospace engine can be realized.

Description

Technical field[0001]The invention relates to the technical field of aerospace engine fault diagnosis, in particular to an aerospace engine abnormality intelligent detection method based on hierarchical confrontation training.Background technique[0002]The engine is the core of the aerospace vehicle power system, mostly in extreme conditions such as high temperature, high pressure, and strong vibration. The high-thrust aerospace engine is a complex nonlinear system with strong coupling of mechanical operation-liquid flow-chemical combustion, etc. Small faults in any part may be transmitted to the entire system, causing huge economic losses and even casualties. Therefore, accurate and timely detection of abnormal operation of aerospace engines is essential to improve its reliability and safety.[0003]The detection methods for aerospace engine operation abnormalities can be roughly divided into three types: model-driven, signal processing, and artificial intelligence. The model-driven m...

AI Technical Summary

Problems solved by technology

[0004] In actual anomaly detection, the diversity of engine failure modes makes fault simulation difficult, so it is difficult to collect enough abnormal data, which hinders the detection methods based on data-driven methods such as signal processing and deep learning

In addition, the health status of aerospace engines is monitored by multiple sensors, but traditional methods usually analyze each data source independently, making it difficult to comprehensively evaluate the real health status of the engine, and the accuracy of anomaly detection is not high

Images