Intelligent identification method of UAV measurement and control signal under the condition of strong mutual interference

Abstract

The invention discloses an intelligent identification method for unmanned aerial vehicle measurement and control signals under the condition of strong mutual interference. Radio electronic signal reconnaissance equipment is used to detect space electromagnetic wave signals, and then the received signals are sequentially subjected to low-noise power amplification, filtering, A / D transformation, digital down-conversion, and finally convert the received signal into time-domain IQ data with zero intermediate frequency; use the signal detection and recognition processor to collect and store the received signal, and then perform time-frequency transformation on it to obtain its time-frequency map, The frequency spectrum performs preprocessing operations of taking absolute value and normalization, and then performs target detection based on deep learning on the preprocessed time-frequency spectrum; the signal detection and recognition processor includes a target detection model based on deep learning. The invention adopts the pruning idea of ​​pruning the deep learning model, keeps the accuracy basically unchanged, reduces the computational complexity of the model, improves the model recognition speed, effectively reduces the consumption of computing resources, and is more convenient for the multi-platform transplantation of the model.

Description

technical field [0001] The invention belongs to the technical field of electronic information technology, and in particular relates to an intelligent identification method for UAV measurement and control signals under the condition of strong mutual interference. Background technique [0002] At present, benefiting from the development of flight control and wireless communication technology, the UAV market is growing at an unprecedented rate and is widely used in aerial photography, rescue, power inspection, smart agriculture, cargo transportation and other fields. However, due to the imperfection of relevant supervision technology, drones illegally enter sensitive areas, disrupting civil aviation order and other incidents from time to time. Therefore, how to effectively supervise drones is an important prerequisite for ensuring the sound development of the industry. The premise of effective supervision of drones is to detect and identify drones in a timely manner. [0003]...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problem of using UAV measurement and control signals to detect and identify UAVs in a complex electromagnetic environment, the invention discloses an intelligent identification technology for UAV measurement and control signals under strong mutual interference conditions. Time-frequency transformation, based on deep learning target detection and other methods, to realize the recognition and detection of target signals

Images