Method and device for automatically identifying and intercepting test flight action mode data

Abstract

The invention provides a method and a device for automatically identifying and intercepting test flight action mode data. The method comprises the steps: presetting a starting end point template sequence and a termination template end point sequence of a flight mode, calculating a DTW distance between a target parameter sequence of a sub-sequence and the preset end point sequence by employing a DTW algorithm, and identifying a starting point and an ending point of the flight mode; then taking the data of to-be-tested flight data between the starting point and the ending point as a to-be-identified sequence of the flight mode; and calculating to obtain feature data of the to-be-identified sequence, and inputting the feature data into the trained machine learning model corresponding to the flight mode to obtain a model judgment result. Therefore, automatic identification and interception of the test flight action mode data are realized, the data processing time is shortened, the labor cost is reduced, and the data identification effect is improved.

Description

technical field [0001] The invention relates to the field of data processing, more specifically, to a method and device for automatically identifying and intercepting flight test action pattern data. Background technique [0002] The amount of data generated during the flight test sorties is huge and the transformation coupling of related physical parameters. At present, most of the flight test action pattern data are obtained by manual identification and manual interception; that is, the flight data is drawn using professional tools MatLab or Pyhton scripts, and then the flight test action pattern data is obtained through professional observation and manual interception. [0003] Usually, the flight data that can be collected in one test flight reaches GB level. In the case of a large amount of data, it is intercepted based on manual experience. The uniformity of the interception standard is poor, and it is easy to miss valid data or identify invalid data, which not only ca...

AI Technical Summary

Problems solved by technology

[0003] Usually, the flight data that can be collected in one test flight reaches GB level. In the case of a large amount of data, it is intercepted based on manual experience. The uniformity of the interception standard is poor, and it is easy to miss valid data or identify invalid data, which not only causes loss or error of model data information, but also Labor costs and learning costs are also increasing

Images