Interference detection device and method based on depth support vector data description

Abstract

The invention discloses an interference detection device and method based on deep support vector data description. The device comprises a data preprocessing module, a deep learning training module, an interference detection module and an interference identification module. The method comprises the following steps of: acquiring a space signal through an antenna, performing IQ modulation, and converting a one-dimensional data format of the signal into a four-dimensional matrix data format through frequency mixing, digital filtering, down-sampling and FFT (Fast Fourier Transform); constructing, optimizing and training a deep learning network architecture to obtain optimal network parameters; calling a corresponding algorithm according to requirements, and realizing online interference detection and modulation identification on an operating system based on a CPU (Central Processing Unit); and finally, outputting a result on a display control interface based on pyQT. According to the method, the advantages of deep support vector description and modulation recognition are combined, so that the problems that interference patterns are unknown and signal features are difficult to extract in a complex environment are solved, open set recognition with high detection rate and low false alarm rate is realized, and interference detection and recognition effects in a complex channel environment are ensured.

Description

technical field [0001] The invention belongs to the technical field of signal perception of communication systems, and more specifically relates to an interference detection device and method based on deep support vector data description. Background technique [0002] In space-constrained combat platforms such as tanks, aircraft, and warships, a large number of radar communication and electronic warfare equipment with different functions are deployed, and the space is crowded. In addition to receiving useful communication signals from friendly parties, the communication receiver located on the combat platform also receives electromagnetic signals leaked from other electronic equipment on the platform, as well as electromagnetic interference signals from enemy platforms, and the electromagnetic environment is complex. Interference detection and identification are the premise of communication anti-interference and the basis of interference cognition. Research on interference d...

AI Technical Summary

Problems solved by technology

[0008] Aiming at the problems of poor detection performance and real-time performance under complex channels existing in existing interference detection and identification methods, the present invention provides an interference detection device and method based on deep support vector data description, which converts radio frequency signals to For the baseband signal, construct the training data set through signal preprocessing and introduce channel noise, design and optimize the deep support vector description network and deep convolutional neural network architecture, iteratively optimize the network weights, and complete the communication system interference detection and identification

Images