数字调制信号制式识别新方法  

A Novel Identification Method for Digital Modulations

作　　者：周敏[1] 冯全源[1] 

机构地区：[1]西南交通大学微电子研究所,成都610031

出　　处：《电讯技术》2012年第4期518-522,共5页Telecommunication Engineering

基　　金：国家自然科学基金资助项目(60990320;60990323);国家高技术研究发展计划(863计划)项目(2012AA012305)~~

摘　　要：通过分析数字调制信号功率谱及高阶谱特征,对高阶谱的求取方法作了改进,并在此基础上提出新的特征参数,结合瞬时统计特征,采用支持向量机分类器,实现了AWGN信道下数字通信信号的制式自动识别。仿真表明,所提取的特征参数具有较好的抗噪性能,对调制参数的变化具有稳健性。考虑脉冲成形的影响,在信噪比大于12 dB时,单种信号最低正确识别率大于98.5%,平均识别率达99.5%以上。By analysing the characteristics of digital modulations＇ power spectrum and higher order spectral, the method to calculate the higher spectrum is improved. On this base, new feature parameters are proposed. Com- bined with the instantaneous statistical feature parameter and support vector machine（SVM） classifier, the automatic identification of digital communication signals in the AWGN channel is achieved. Simulation results show that the extracted feature parameters have good anti - noise performance as well as robustness to the change of modulation parameters. In consideration of the impact of pulse shaping, when the SNR value is greater than 12 dB, the lowest correct identification rate of the single- type signal is greater than 98.5%, and the average recognition rate is above 99.5 %.

关 键 词：调制方式识别 谱分析 特征参数提取 支持向量机 脉冲成形 

分 类 号：TN911.72[电子电信—通信与信息系统]