ADS-B track cleaning and calibration method based on local traversal density clustering

Abstract

The invention relates to an ADS-B track cleaning and calibration method based on local traversal density clustering. The ADS-B track cleaning and calibration method based on local traversal density clustering comprises the steps that a data sample based on feature fields of ADS-B track data is established, the feature fields comprise an initial field and an extended field, and the extended field is obtained through calculation of the initial field;; de-duplication is carried out on the data sample; a feature field is selected according to data characteristics of the feature field in the data sample and is used for the feature field for field data exception detection and processing; outlier identification is carried out on the feature fields of the data samples according to a DBSCAN densityclustering method of local traversal, abnormal points are judged, and the abnormal points are corrected or deleted; and the flight path is calibrated according to the initial field in the data sample. The outliers are identified by using a DBSCAN density clustering method of local traversal, the cleaning efficiency is greatly improved, and the timestamp is corrected through track calibration, sothat the whole flight path conforms to the particle kinematics law.

Description

technical field [0001] The invention relates to the field of aviation, in particular to an ADS-B track cleaning and calibration method based on local ergodic density clustering. Background technique [0002] Automatic Dependent Surveillance-Broadcast (Automatic Dependent Surveillance-Broadcast, ADS-B) is determined by the International Civil Aviation Organization (ICAO) as the main navigation surveillance technology in the future. Other aircraft and ground receiving stations equipped with ADS-B receiving equipment automatically broadcast flight identification marks, location and flight status information to realize coordinated and integrated monitoring of air-to-air, air-to-ground and surface operations. In recent years, my country has begun to vigorously promote the development and application of ADS-B technology in the air traffic control system. [0003] The ADS-B flight track of a flight consists of multiple track points, and each track point has multiple field informat...

AI Technical Summary

Problems solved by technology

When the abnormal point happens to be the first point (boundary point) of the trajectory, using the filtering method requires additional pre-judgment processing and is more cumbersome to implement, while using the density clustering method will not be affected by the position of the abnormal point, but When the number of track points is large, the detection efficiency is greatly reduced due to the sharp increase in the number of traversals

Images