Aeroelastic system flutter signal abnormal data expansion method

Abstract

The invention relates to an aeroelastic system flutter signal abnormal data expansion method. Based on a time sequence signal generation algorithm of a generator in a generative adversarial network, aflutter data set can be expanded through a pre-trained generator network by only needing a small number of flutter signals with coupling resonance occurring in structural response signals of an aeroelastic system or an aircraft, normal data and abnormal data are balanced as much as possible, and the influence of data samples on the method in the method verification process is reduced. Compared with the prior art, the flutter signal data set extension method based on the deep learning algorithm is provided by introducing the deep learning algorithm into the data set extension of the vibrationsignals of the aeroelastic system. Based on a pre-trained generative adversarial network, conversion from random signals based on Gaussian distribution to flutter signals with flutter characteristicsis achieved through a small number of actually-measured wind tunnel flutter test flutter signals of coupling resonance, and the purpose of expanding a data set is achieved.

Description

technical field [0001] The invention belongs to an aeroelastic system data processing method, and relates to an aeroelastic system flutter signal abnormal data extension method. Background technique [0002] For aeroelastic systems, flutter is a structural instability phenomenon of aeroelastic systems caused by the mutual coupling of aerodynamic force and elastic force. The status monitoring data of normal operation is relatively easy to obtain and the data volume is huge. On the contrary, the status monitoring data under abnormal operation of the system is usually smaller than the normal data in terms of data volume. This data imbalance makes many chatter type judgments and chatter boundaries based on chatter signals and data-driven Forecasting methods suffer from issues such as insufficient sample size. [0003] In the existing flutter signal processing, methods such as flutter judgment and boundary prediction are usually studied based on simulation data, and then verifie...

AI Technical Summary

Problems solved by technology

Since the simulation signal cannot completely simulate the structural response signal of the actual system, for some data-driven methods with high data sensitivity, the imbalance between the abnormal data and the normal data of the flutter signal of the aeroelastic system waiting to be solved

[0004] There are usually two main ways to obtain the flutter signal data of the aeroelastic system in the case of flutter. On the one hand, it is obtained through the simulation environment or the aeroelastic model of the wind tunnel test, and on the other hand, it is artificially obtained in the actual aircraft flight test However, under normal circumstances, the long-term abnormal operation of the aeroelastic system is destructive, which makes it difficult to obtain data. Therefore, the data obtained by the above method has the following two problems:

[0005] 1. There are deviations between the simulation data and the actual aircraft flight test data due to different systems, and the methods based on simulation data research usually have insufficient robust performance when applied in act

Images