摘要
为实现对线性调频(LFM)信号的实时波形识别和瞬时频率估计,引入采样池计算(RC)进行逐点运算.将生成的初始频率和啁啾率不同的两组LFM信号组合成随机序列,并对200个节点的储备池进行训练.通过测试得到,池计算可以快速、准确地识别和区分出两组LFM信号,并可对未知LFM信号的瞬时频率进行估计.
For waveform recognition and parameter evaluation of linear frequency modulation(LFM)signal,the reservoir computing(RC)was used for calculation point-by-point.The sequence generated by random array of LFM signals with different chirp and initial frequency,was used for training the reservoir with 200 nodes.The testing result shows the RC can distinguish the LFM signals and estimate the parameters of unknown LFM signals.
作者
景宁
杨振泽
余晨
谷建星
JING Ning;YANG Zhen-ze;YU Chen;GU Jian-xing(School of Information and Communication Engineering, North University of China, Taiyuan 030051, China;Shanxi Provincial Research Center for Opto-Electronic Information and Instrument Engineering Technology, Taiyuan 030051, China)
出处
《中北大学学报（自然科学版）》
CAS
2021年第1期40-43,共4页
Journal of North University of China(Natural Science Edition)
基金
国家留学基金委资助项目(201908140065)
山西省高等学校科技创新计划资助项目(2019L0519)。
关键词
线性调频
信号识别
参数估计
池计算
linear frequency modulation
signal recognition
parameters estimation
reservoir computing
