基于级联SVM和全数字接收机的复合调制识别  

Composite Modulation Recognition Based on Cascaded SVM and All-digital Receiver

作　　者：赵永宽 沈雷[1] 王希琳 张铭宏 ZHAO Yongkuan;SHEN Lei;WANG Xilin;ZHANG Minghong(School of Communication Engineering,Hangzhou Dianzi University,Hangzhou Zhejiang 310018,China)

机构地区：[1]杭州电子科技大学通信工程学院,浙江杭州310018

出　　处：《杭州电子科技大学学报（自然科学版）》2020年第5期18-24,共7页Journal of Hangzhou Dianzi University：Natural Sciences

摘　　要：为解决测控系统中FM复合调制信号的识别问题,提出一种基于全数字接收机和支持向量机(Support Vector Machine,SVM)的调制识别算法。通过全数字接收机的鉴相误差提取FM复合信号的内调制信息,使用级联SVM分类器对内调制信号的功率谱和平方谱整体图形特征进行分类识别。仿真实验表明,在信噪比为0 dB时,与传统的基于局部信号特征和决策树分类的识别算法相比,识别率提高了5%以上。In order to solve the problem of FM composite modulation signal recognition in the measurement and control system,a modulation recognition algorithm based on an all-digital receiver and Support Vector Machine(SVM)is proposed.The internal modulation information of the FM composite signal is extracted by phase discrimination error of the all-digital receiver,and the cascaded SVM classifier is used to classify and recognize the overall graphic features of the power spectrum and square spectrum of the internal modulation signal.Simulation experiments show that when the signal-to-noise ratio is 0 dB,compared with the traditional recognition algorithm based on local signal characteristics and decision tree classification,the recognition rate of the proposed method is improved by more than 5%.

关 键 词：复合调制 数字接收机 支持向量机 调制识别 

分 类 号：TN850[电子电信—信息与通信工程]