Correlation Analysis of <scp>ADS</scp> ‐B Data Jump and <scp>UAV</scp> Positioning Error Combined With Data Mining Algorithm

ABSTRACT Aiming at the problem that ADS‐B (Automatic Dependent Surveillance Broadcast) data jump characteristics and multi‐source heterogeneous errors are difficult to dynamically associate, this paper constructs a data mining framework that combines time series anomaly detection and multi‐modal feature fusion. First, this paper performs missing value interpolation, time alignment and standardization preprocessing on the collected ADS‐B data, energy status parameters, material environment parameters and flight environment information; secondly, based on the LSTM‐AE (Long Short‐Term Memory‐Autoencoder) model, an unsupervised model for ADS‐B data jump detection is constructed, which identifies the jump point by reconstructing the error and extracts jump features with physical significance. Finally, this paper introduces the Transformer architecture, cross‐modally fuses the jump features with multi‐source heterogeneous parameters, constructs a semantic alignment mechanism, and combines the error evolution modeling strategy to explore the complex influence mechanism of different factors on positioning errors. Experimental results show that the proposed method has better jump recognition accuracy (average 90.7%) and error prediction mean square error (average 5.81) than Isolation Forest and Variational Autoencoder (VAE), providing a new technical path for improving the positioning reliability and safety control of unmanned aerial vehicles (UAVs).