基于深度学习算法的铁路无线通信干扰信号自动化识别系统  

Automatic Identification System for Railway Wireless Communication Interference Signals Based on Deep Learning Algorithms

作　　者：任国彬 REN Guobin(School of Railway Transportation,Shaanxi College of Communications Technology,Xi’an 710018,China)

机构地区：[1]陕西交通职业技术学院轨道交通学院,西安710018

出　　处：《自动化与仪表》2024年第5期40-44,共5页Automation & Instrumentation

基　　金：陕西省教育厅2021年专项课题(21JK0528);陕西交通职业技术学院校级科研项目(YJ21002)。

摘　　要：针对铁路无线通信过程中,信号干扰杂乱且自动化识别精确度不高、类型判别较难的问题,该文提出基于深度学习算法的铁路无线通信干扰信号自动化识别系统。无线通信干扰信号自动化识别系统主要针对铁路无线通信过程中面临的噪声调幅、射频噪声以及噪声调频等干扰信号问题。系统通过改进天牛须算法进行BP神经网络的优化,将域矩偏度以及域矩峰度作为特征参数进行自动化识别判定。经过实验验证,该文设计的干扰信号自动化识别系统快速准确,自动化识别精度高。A railway wireless communication interference signal automatic recognition system based on deep learning algorithm is proposed to address the problems of chaotic signal interference,low accuracy of automatic recognition,and difficulty in type discrimination in the process of railway wireless communication.The automatic identification system for wireless communication interference signals mainly targets the interference signal problems faced by railway wireless communication processes,such as noise amplitude modulation,radio frequency noise,and noise frequency modulation.The system optimizes the BP neural network by improving the beetle antennae algorithm,using domain moment skewness and domain moment kurtosis as feature parameters for automated recognition and judgment.After actual experimental verification,the interference signal automatic recognition system designed in this article is faster and more accurate,and the automation recognition accuracy is higher.

关 键 词：天牛须算法 BP神经网络 域矩偏度 域矩峰度 铁路通信干扰 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TP391[自动化与计算机技术—控制科学与工程]