利用新型卷积神经网络识别MPSK信号调制方式

王爱丽; 张佳烤; 姜开元; 吴海滨; 岩崛祜之

doi:10.15938/j.jhust.2021.05.013

Chinese

您当前的位置：

首页 >

文章列表页 >

利用新型卷积神经网络识别MPSK信号调制方式

测控技术与通信工程 | 更新时间：2026-08-31

- 利用新型卷积神经网络识别MPSK信号调制方式
- Modulation Recognition of MPSK Signals Based on Novel Convolutional Neural Network
- 哈尔滨理工大学学报 2021年26卷第5期页码：97-103
- 作者机构：
  
  1. I 哈尔滨理工大学测控技术与通信工程学院,哈尔滨,150080
  2. 中部大学计算机科学学院，日本爱知487,8501
- 作者简介：
- 基金信息：
- DOI：10.15938/j.jhust.2021.05.013
  中图分类号： TP391.4
- 纸质出版：2021
- 稿件说明：
移动端阅览
王爱丽, 张佳烤, 姜开元, 等. 利用新型卷积神经网络识别MPSK信号调制方式[J]. 哈尔滨理工大学学报, 2021,26(5):97-103.

WANG Ai-li, ZHANG Jia-wei, ]JANG Kai-yuan, et al. Modulation Recognition of MPSK Signals Based on Novel Convolutional Neural Network[J]. 2021, 26(5): 97-103.
王爱丽, 张佳烤, 姜开元, 等. 利用新型卷积神经网络识别MPSK信号调制方式[J]. 哈尔滨理工大学学报, 2021,26(5):97-103. DOI： 10.15938/j.jhust.2021.05.013.

WANG Ai-li, ZHANG Jia-wei, ]JANG Kai-yuan, et al. Modulation Recognition of MPSK Signals Based on Novel Convolutional Neural Network[J]. 2021, 26(5): 97-103. DOI： 10.15938/j.jhust.2021.05.013.

摘要

摘要：随着人工智能技术的快速发展，卷积神经网络越来越多地应用到通信信号调制识别领域。针对数字信号在低信啋比的识别准确率较低的问题，采用lnceptionResNetV2网络与迁移适配相结合的方法，研究了一种调制识别模型，称之为lnceptionResnetV2-TA

对MPSK信号的调制方式进行识别。结果表明，信啋比为3dB时，lnceptionResnetV2-TA对BPSK的识别率达到99. 33%

比次优模型InceptionResNet V2高出3%。对QPSK的识别率达到95. 33%

比lnceptionResNetV2高出 2%。对8PSK的识别率达到86. 33%

比InceptionResNetV2高出5%。综上，结合了迁移适配的InceplionResnel V2-T A

对BPSK、QPSK和8PSK在低信啋比的识别准确率高于其他对比方法。同时验证了这种调制识别模型的有效性。

Abstract

With the rapid development of 釭tificial intelligence

convolutional neural network is more and more applied to the field of communication signal modulation recognition. Aiming at the problem of low recognition accuracy of digital signals at low SNR

a modulation recognition model named lnceptionresnetV2-TA was studied by combining InceptionresnetV2 network with migration adaptation to identify the modulation mode of MPSK signals. The results show that when the SNR is 3d8

the recognition rate of InceptionresnetV2-TA for BPSK is99. 33%

which is 3% higher than that of the suboptimal model lnceptionresnetV2. The recognition rate of QPSK is 95. 33%

which is 2% higher than lnceptionresnetV2. The recognition rate of 8PSK is 86. 33%

which is 5%higher than that of Inceptionresnetv2. The above results indicate that InceptionresnetV2-TA combined with migration adaptation has higher identification accuracy of BPSK

QPSK and 8PSK at low SNR than other comparison methods. At the same time

the validity of the modulation recognition model is verified.

关键词

Keywords

references

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

不同温度环氧纳米复合材料击穿机制

面向半监督血管分割的深度学习方法

连续结构分布动载荷的离散等效加载方法

基于区块链的电力系统最优潮流分布式求解算法

混频级联 H 桥 SVG 纹波抑制方法