首页|电子通信突变非线性多频干扰检测方法仿真

电子通信突变非线性多频干扰检测方法仿真

扫码查看
电子通信技术最关键特点在于故障危险性高,若电子出现通信障碍,影响范围通常较大。为进一步优化网络通信的抗干扰性能,抵御外来信号的干扰,提出一种电子通信突变非线性多频干扰检测方法。引入调频连续波(Frequency Modulated Continuous Wave,FMCW)原理计算不同信号的之间的距离和移动速度,圈定电子通信突变信号范围,筛选出电子通信过程中的突变非线性多频干扰。采用Wigner-Ville分布对全部多频干扰信号展开谱图变换处理,获取干扰信号真实标签,同时构建突变非线性多频干扰信号对应的谱图。通过卷积神经网络提取谱图特征,将获取的特征向量输入到长短期记忆网络中检测,实现电子通信突变非线性多频干扰检测。实验测试结果表明,提出方法下干扰检测耗时在 20ms内,不会受到通信内容长度阈值以及相似内容覆盖阈值波动影响,漏检率始终低于1。0%。
Simulation of Nonlinear Multi-Frequency Interference Detection Method for Electronic Communication Mutation
The most important feature of electronic communication technology is the high risk of failure.In order to further optimize the anti-jamming performance of network communication,this article puts forward a method of de-tecting abrupt nonlinear multi-frequency interference in electronic communication.The Frequency Modulated Contin-uous Wavec(FMCW)principle was introduced to calculate the distance and speed between different signals and deter-mine the range of abrupt signal,thus screening out the abrupt nonlinear multi frequency interference during electronic communication.Then,Wigner-Ville distribution was used to transform the spectrograms of all multi-frequency inter-ference signals,thus obtaining the true labels of interference signals.Correspondingly,a spectrogram of abrupt nonlin-ear multi frequency interference signals was constructed.Meanwhile,spectral features were extracted by convolution neural networks,and then the feature vectors were input into the long-term and short-term memory network for detec-tion.Finally,the detection of abrupt nonlinear multi frequency interference in electronic communication was comple-ted.Experimental results show that the interference detection cost less than 20ms,and the method is not affected by the fluctuation of the communication content length threshold and the coverage threshold of the similar content.And the missed detection rate is always less than 1.0%.

Electronic communicationAbrupt nonlinear multi-frequency interferenceDetectionConvolutional neural network

郭勤、程扬

展开 >

新疆工程学院信息工程学院,新疆 乌鲁木齐 830023

新疆大学信息科学与工程学院,新疆 乌鲁木齐 830046

电子通信 突变非线性多频干扰 检测 卷积神经网络

新疆自治区自然科学基金

2019D01C073

2024

计算机仿真
中国航天科工集团公司第十七研究所

计算机仿真

CSTPCD
影响因子:0.518
ISSN:1006-9348
年,卷(期):2024.41(1)
  • 15