Flight trajectory anomaly detection method based on LSTM-GBSVDD model

By using the LSTM-GBSVDD model, which combines the LSTM network and the SVDD algorithm, the problems of varying flight trajectory data length and complexity are solved, achieving efficient and accurate flight trajectory anomaly detection. This improves detection accuracy and efficiency and is suitable for unsupervised anomaly detection of complex time-series data.

CN119848536BActive Publication Date: 2026-05-01NAVAL UNIV OF ENG PLA
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
NAVAL UNIV OF ENG PLA
Filing Date
2024-12-02
Publication Date
2026-05-01

AI Technical Summary

Technical Problem

Existing flight trajectory anomaly detection methods suffer from inaccurate feature extraction and low detection efficiency when dealing with complex, dynamic flight trajectory data with real-time changes in data length. They also struggle to effectively capture long-term dependencies in the trajectory, resulting in insufficient detection accuracy.

Method used

An anomaly detection method based on the LSTM-GBSVDD model is adopted. The time series features are extracted by the LSTM network and the feature mean pooling is performed. A multidimensional hypersphere classifier is constructed by combining the SVDD model. Gradient optimization is used to train the LSTM and SVDD parameters to achieve joint optimization and improve detection accuracy and efficiency.

Benefits of technology

It effectively handles variable-length data sequences, improves the model's universality and detection accuracy, significantly enhances the accuracy and computational efficiency of anomaly detection, can efficiently identify potential abnormal trajectories, reduces false alarm rates, and is suitable for anomaly detection of flight trajectories in unsupervised environments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119848536B_ABST
    Figure CN119848536B_ABST
Patent Text Reader

Abstract

The application relates to a flight trajectory anomaly detection method based on an LSTM-GBSVDD model. In order to cope with the length variation problem of flight trajectory data, the application uses LSTM to extract key features in a time sequence, converts variable-length trajectory data into fixed-length representation, enables anomaly detection to be carried out in a fixed-length feature space, and improves the universality of the model. On the basis of feature extraction, the SVDD algorithm is introduced to construct a multi-dimensional hypersphere classifier to model normal flight trajectories. Through the model, potential abnormal trajectories can be identified in an unsupervised framework, the dependence on data labels is avoided, and the bottleneck that abnormality cannot be identified in an unsupervised environment is solved. The application first realizes the joint optimization of the LSTM network parameters and the SVDD scoring function, and proposes a gradient-based training method. The method significantly improves the accuracy and calculation efficiency of anomaly detection and improves the detection performance.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Unmanned aerial vehicle flight data abnormity detecting method based on LSTM

    CN108960303A

  • Water treatment time sequence data anomaly detection method based on LSTM

    CN112765896A