| 引用本文: | 鲁永为，师俊朋，周青松，田西兰，郭柏炀，陈沁娴，山世浩，王明壮. 基于CNN-BiLSTM的对ELINT系统杂乱脉冲干扰抑制方法[J]. 雷达科学与技术, 2026, 24(2): 196-204.[点击复制] |
| LU Yongwei, SHI Junpeng, ZHOU Qingsong, TIAN Xilan, GUO Baiyang, CHEN Qinxian, SHAN Shihao, WANG Mingzhuang. Method for Suppressing Chaotic Pulse Interference in ELINT System Based on CNN-BiLSTM[J]. Radar Science and Technology, 2026, 24(2): 196-204.[点击复制] |
|
| 摘要: |
| 针对杂乱脉冲干扰信号严重破坏电子情报系统对雷达信号的分选识别问题，将机器学习算法引入侦察分选过程，提出一种基于卷积神经网络-双向长短期记忆网络的抑制杂乱脉冲干扰方法。该方法利用卷积神经网络捕捉杂乱脉冲干扰信号在多个维度随机分布的局部特征，以及双向长短期记忆网络捕捉混叠信号中雷达信号的周期特征，实现干扰信号和雷达信号的分类识别。仿真实验证明该方法针对不同的测试集准确率达到96%以上，召回率超过92%，有较强的域泛化能力，为提升ELINT系统在复杂电磁环境下的性能提供了一种有效途径。 |
| 关键词: 电子情报系统 卷积神经网络 双向长短期记忆网络 杂乱脉冲干扰 雷达侦察 |
| DOI：DOI:10.3969/j.issn.1672-2337.2026.02.010 |
| 分类号:TN973.3 |
| 基金项目:国家自然科学基金（62301581，62401600）； 中国博士后科学基金面上项目（2023M734313） |
|
| Method for Suppressing Chaotic Pulse Interference in ELINT System Based on CNN-BiLSTM |
|
LU Yongwei, SHI Junpeng, ZHOU Qingsong, TIAN Xilan, GUO Baiyang, CHEN Qinxian, SHAN Shihao, WANG Mingzhuang
|
|
1. Unit 63891 of PLA, Luoyang 471000, China;2. College of Electronic Engineering, National University of Defense Technology, Hefei 230037, China;3. The 38th Research Institute of China Electronics Technology Group Corporation, Hefei 230088, China;4. Unit 96816 of PLA, Qidong 226200, China
|
| Abstract: |
| In response to the serious damage to the sorting and recognition of radar signals by the electronic intelligence（ELINT）system caused by chaotic pulse interference signals, a method based on convolutional neural network-bidirectional long short-term memory network for suppressing chaotic pulse interference is proposed by introducing the machine learning algorithm into the reconnaissance sorting process. This method utilizes the convolutional neural network to capture the locally distributed features of chaotic pulse interference signals in multiple dimensions, and bidirectional long short-term memory network to capture the periodic features of radar signals within the mixed signals, thereby achieving classification and identification of interference signals and radar signals. Simulation experiments have shown that this method achieves an accuracy rate of over 96% and a recall rate of over 92% for different test sets. It has strong domain generalization ability and provides an effective way to improve the performance of ELINT systems in complex electromagnetic environments. |
| Key words: electronic intelligence（ELINT）system convolutional neural network bidirectional long short-term memory network chaotic pulse interference radar reconnaissance |
