An aircraft abnormal event detection method, system and storage medium for different voyage scenarios

By combining the UDTW algorithm and the attention mechanism, the problem of anomaly detection in flight data from different voyages was solved, achieving high-precision anomaly localization on a unified time scale and improving the robustness and interpretability of the detection model.

CN121075183BActive Publication Date: 2026-01-06HANGZHOU INTERNATIONAL INNOVATION INSTITUTE OF BEIHANG UNIVERSITY
7 Cites 0 Cited by

Patent Information

Application Number
CN202511613225.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-11-06
Publication Date
2026-01-06
Estimated Expiration
2045-11-06

AI Technical Summary

Technical Problem

Existing technologies struggle to achieve accurate anomaly detection in flight data across different voyages, primarily due to the high dimensionality, non-uniform length, and complex variable types of flight data. Furthermore, the data is susceptible to external environmental disturbances and differences in pilot operations, resulting in insufficient accuracy and robustness of the detection models.

Method used

The Uniform Dynamic Time Warping (UDTW) algorithm is adopted with flight altitude as a reference. It introduces equal length and surjective constraints to dynamically match scene information of different flights. Combined with a weakly supervised anomaly detection model based on attention mechanism, it outputs event-level labels and instance-level anomaly probabilities to achieve anomaly localization across flights.

Benefits of technology

It significantly improves the comparability and anomaly localization accuracy across voyage scenarios. The experimental results show that the precision, recall, F1 score and accuracy are 0.7601±0.0574, 0.7321±0.1052 and 0.7208±0.1430, respectively, which verifies the comprehensive improvement of UDTW under the linkage of scene dynamic matching and weak supervision detection.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The present application belongs to the field of aircraft monitoring and detection, and particularly relates to a kind of aircraft abnormal event detection method, system and storage medium for different voyage scenarios.The present application takes flight height as reference, proposes uniform dynamic time warping (UDTW), obtains mapping matrix {I,v',R,Q'} from DTW under full shot and equal length constraint, and synchronously acts on multivariate flight data with the mapping to output uniform length sequence;Then input the equal length sequence into the weak supervision detector based on attention, output event level label Y, differential feature weight Δβ and instance level probability p ins , realize accurate positioning and explainable analysis of cross voyage anomaly.The method is suitable for high-dimensional, non-equal length and mixed variable data, and improves detection accuracy and robustness.
Need to check novelty before this filing date? Find Prior Art