Aircraft landing stage short-time abnormal risk early warning and visual simulation adaptive method based on deep learning

Through deep learning methods, high-frequency impact and low-frequency wind shear features are separated and integrated in real time during aircraft landing, solving the problems of insufficient synchronization accuracy and limited real-time adaptability of risk assessment in existing technologies. The high-frequency impact peak fidelity and low-frequency aerodynamic slow change tracking are achieved, improving the adaptability of aircraft landing risk warning and the reliability of visual simulation.

CN120670985APending Publication Date: 2025-09-19SHENYANG AEROSPACE UNIVERSITY
0 Cites 7 Cited by

Patent Information

Application Number
CN202510764957.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-06-10
Publication Date
2025-09-19

AI Technical Summary

Technical Problem

Existing aircraft landing risk monitoring systems suffer from insufficient synchronization accuracy, compromised filtering bandwidth, difficulty in identifying shock-wind shear coupling, and limited real-time adaptability in risk assessment. These systems make it difficult to simultaneously maintain high-frequency shock peak fidelity and low-frequency aerodynamic slow-changing tracking throughout the entire aircraft landing process, and to provide high-confidence hard landing risk warnings in real time under conditions of sudden changes in multiple environmental parameters.

Method used

A deep learning-based method is adopted to extract high-frequency impact and low-frequency wind shear features through cubic spline kernel function mapping and dynamic switching of complementary filters. Causal dilation convolution and multi-scale graph convolution are used to learn spatiotemporal correlation features. A dual-channel attention decoder and a policy network are combined to perform real-time risk assessment and visual simulation, realizing feature mapping and fusion of aircraft nodes, runway nodes and wind field nodes, and generating a highly reliable hard landing risk warning.

Benefits of technology

It realizes the real-time separation and fusion of high-frequency impact and low-frequency wind shear during the aircraft landing process, improves the adaptive ability of risk warning and the consistency of scene perception, supports graded warning and ensures the high reliability and real-time performance of visual simulation.

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

Abstract

The invention provides an aircraft landing stage short-time abnormal risk early warning and visual simulation adaptive method based on deep learning, and the method comprises the following steps: synchronizing a multi-source sensor signal, separating the multi-source sensor signal into an impact channel, a wind shear channel and a residual channel, and mapping the multi-source sensor signal into aircraft-runway-wind field graph node features; features are extracted through a space-time diagram convolutional network, and a future trajectory is predicted in combination with a dual-channel attention decoder under physical constraints such as an energy attenuation template; high-risk actions are rapidly inhibited on the basis of real-time risks, the risk probability is calculated through weighted submerged space sampling, graded alarms are output, meanwhile, the alarms drive visual simulation to be adaptively updated, and model online safety iteration is achieved through hard sample mining after landing. According to the method, physical driving modeling, space-time fusion perception and probabilistic risk assessment are adopted, the dependence of a traditional method on an empirical threshold value is overcome, and the early warning precision, the confidence coefficient and the landing safety are remarkably improved.
Need to check novelty before this filing date? Find Prior Art