Unmanned aerial vehicle detection method based on radio frequency spectrum identification and deep learning

By combining multi-scale convolutional neural networks and LSTM networks with reinforcement learning, the problem of signal-to-noise ratio sensitivity of traditional machine learning models is solved, achieving high accuracy in UAV detection and optimization of jamming strategies, thereby improving the robustness and accuracy of UAV detection and jamming.

CN121090915APending Publication Date: 2025-12-09NANJING YUNXI INTELLIGENT TECHNOLOGY CO LTD
0 Cites 5 Cited by

Patent Information

Application Number
CN202511346025.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-09-19
Publication Date
2025-12-09

AI Technical Summary

Technical Problem

Existing technologies based on shallow features in traditional machine learning models are sensitive to signal-to-noise ratio and cannot fully utilize deep information in complex signals, resulting in insufficient accuracy and robustness in UAV detection.

Method used

Multi-scale convolutional neural networks are used to extract multi-scale signal features, combined with multi-layer LSTM networks for time-series signal feature extraction, and interference strategies are optimized through reinforcement learning. Nonlinear harmonic response features and a comprehensive reward function are constructed to achieve spectrum situation prediction and interference space optimization.

Benefits of technology

It significantly improves the accuracy of UAV detection and the scientific nature and robustness of jamming strategies, and enhances the precision and environmental adaptability of UAV jamming effects.

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

Abstract

The invention discloses an unmanned aerial vehicle detection method based on radio frequency spectrum identification and deep learning, and relates to the technical field of unmanned aerial vehicle monitoring, and the method comprises the steps: deploying a radio receiving station to collect radio signals, converting the radio signals into a time-frequency graph, extracting multi-scale signal features, carrying out the global average pooling of the multi-scale signal features, and carrying out the global average pooling of the multi-scale signal features; calculating a scale adjustment coefficient to generate a weighted feature, extracting a time sequence signal feature to generate a fusion feature, constructing a full connection layer to perform multi-task processing on the fusion feature, and outputting an unmanned aerial vehicle detection result; a state space is defined, an action space is defined according to environmental parameters, nonlinear harmonic response characteristics in a current state are measured to construct a nonlinear reward function, a comprehensive reward function is formed in combination with action interference effects, and a final interference strategy is output through reinforcement learning. According to the invention, the scientificity and robustness of the identification and interference strategy are significantly improved, the accuracy of the interference strategy is improved, and the interference effect of the unmanned aerial vehicle is effectively improved.
Need to check novelty before this filing date? Find Prior Art