基于迁移学习的雷达信号类型自动识别方法  

Automatic Recognition of Radar Signal Type Based on Transfer Learning

作　　者：阮国庆 吴蔚[1] 汪霜玲[1] 熊朝华[1] 国强[2] RUAN Guoqing;WU Wei;WANG Shuangling;XIONG Chaohua;GUO Qiang(Key Laboratory of Information System Engineering,No.28 Institute of China Electronics Technology Group Corporation,Nanjing 210007,China;College of Information and Communication Engineering,Harbin Engineering University,Harbin 150000,China)

机构地区：[1]中国电子科技集团公司第二十八研究所信息系统工程重点实验室,南京210007 [2]哈尔滨工程大学信息与通信工程学院,哈尔滨150000

出　　处：《指挥与控制学报》2024年第2期232-237,共6页Journal of Command and Control

摘　　要：针对雷达辐射源信号类型的自动识别方法进行研究,引入迁移学习(transfer learning,TL)思想,将GoogleNet预训练模型迁移到雷达信号数据集中实现信号特征提取,在全连接层中采用极限学习机(extreme learning machine,ELM)作为分类器,完成对雷达信号的自动识别。仿真结果表明,针对9类雷达信号,在信噪比为0 dB的情况下,基于GoogleNet-ELM的识别算法具有很好的识别性能,得到95.7%的正确识别率,验证了所提算法在电子侦察领域应用的有效性。The automatic recognition method of radar emitter signal type is researched.In the complex environment of small sample training data set and limited training time.The transfer learning(TL)concept is introduced and the pre-training GoogleNet models transferred to the radar signal data set to realize the automatic feature extraction.Then,in the full connection layer,Extreme Learning Machine(ELM)is used as classifier to complete the automatic recognition of radar signals.The simulation results show that,for nine kinds of radar signals,the GoogleNet-ELM-based recognition algorithm has good recognition performance when the signal-to-noise ratio is 0 dB,and the correct recognition rate is 95.7%,the effectiveness of the proposed algorithm in the field of electronic reconnaissance is verified.

关 键 词：雷达信号 类型自动识别 迁移学习 极限学习机 

分 类 号：TN95[电子电信—信号与信息处理]