Flight risk behavior identification method based on improved random forest

A random forest and identification method technology, applied in the field of flight risk behavior identification, can solve problems such as no effective methods found, and achieve the effect of improving technical actions
CN110533095AActive Publication Date: 2019-12-03CIVIL AVIATION UNIV OF CHINA
8 Cites 11 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
CIVIL AVIATION UNIV OF CHINA
Publication Date
2019-12-03

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a flight risk behavior identification method based on an improved random forest. The method comprises the steps of calibrating and resampling original QAR data and acquiring feature vectors of each sortie flight take-off and landing stage; performing dimension reduction and feature extraction on the feature vector to obtain a final feature vector; constructing a high-riskover-limit event judgment data set in the take-off and landing stages, and improving the high-risk over-limit event judgment data set to obtain an improved high-risk over-limit event judgment data set; building a high-risk over-limit event recognition model based on the improved random forest; and classifying and identifying the data in the improved high-risk over-limit event judgment data set byutilizing an identification model, and making secondary discrimination on unknown risk events. According to the invention, common high-risk over-limit events in take-off and landing stages can be accurately identified; according to the invention, flights with potential flight risks can be screened out for secondary discrimination by safety management personnel, so that pilots can improve technicalactions more timely, and the management personnel can make decisions more leisurely.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the technical field of air transport safety big data, and in particular relates to a flight risk behavior identification method based on improved random forest. Background technique

[0002] With the continuous expansion of China's civil aviation fleet, China will become the world's largest civil aviation market in the next two decades. However, with the sharp increase in route density, the complexity of airlines' daily operations will increase, and it will also bring greater challenges to flight safety. Although the reliability of aircraft has been greatly improved, and the number of flight accidents caused by mechanical factors has decreased year by year, the number of accidents caused by human factors has remained high, and nearly 90% of the accidents occurred during takeoff and landing.

[0003] In order to monitor and manage the flight of the aircraft, domestic passenger planes are equipped with airborne quick access reco...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More