Civil aircraft test flight vibration fault prediction model and prediction system

Abstract

The invention discloses a civil aircraft test flight vibration fault prediction model which is established through the following steps: 1, establishing a database which is composed of a characteristicparameter set and states corresponding to characteristics; wherein the characteristic parameter set comprises time domain characteristics extracted from the vibration parameters of each part of the civil aircraft, frequency domain characteristics extracted from the vibration parameters of each part of the civil aircraft, and flight parameters of which the correlation with the vibration parametersis greater than 0.6; wherein the time domain characteristics comprise the maximum value, the minimum value, the peak-to-peak value and the amplitude change rate of the vibration amplitude; wherein the frequency domain characteristics comprise frequency composition, frequency size and a change trend of the frequency along with time; and 2, establishing a civil aircraft test flight vibration faultprediction model by using the binary support vector machine model to obtain the binary support vector machine model so as to determine the early warning boundary of the test flight data, and taking the early warning boundary as the basis for judging the normal and abnormal single states of the data. The invention also discloses a civil aircraft test flight vibration fault prediction system.

Description

technical field [0001] The invention relates to a model and system for identifying aircraft vibration faults. The main function is to use collected high-frequency vibration data as input during the real-time monitoring of flight tests to complete the identification and alarm of vibration fault risks. Background technique [0002] Aircraft, especially large civil aircraft, will vibrate due to factors such as airflow, engine, flight attitude, and dynamic mass changes during flight or test flight, and its landing gear, wings, and horizontal tail will vibrate, which will cause damage to the airframe in severe cases and affect Airplane flight safety. At present, the vibration failures in civil aircraft test flights are analyzed after the event, that is, only known vibration damage phenomena can be improved or optimized. For vibration, the traditional analysis process is as follows: [0003] (1) Time-domain analysis: draw the trend curve of the collected vibration parameters for...

AI Technical Summary

Problems solved by technology

[0008] (1) The analysis method is relatively simple: the vibration phenomenon analysis method adopted is only the correlation analysis between parameters, so it is difficult to locate the vibration source;

[0009] (2) The analysis method is relatively lagging: only when vibration faults or vibration phenomena occur (such as structural damage to the body), sensors will be installed for analysis or real-time monitoring, and potential vibration faults cannot be predicted and prevented;

[0010] (3) The analysis cycle is relatively lengthy: the traditional vibration data analysis method relies on experience, and often requires multiple enumerations and exclusions to determine relevant parameters. At the same time, due to the huge vibration data, the analysis cycle is long

Images