检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:魏子钧 杨世武[1] 李文涛 崔勇[1] 楚少童 WEI Zijun;YANG Shiwu;LI Wentao;CUI Yong;CHU Shaotong(School of Automation and Intelligence,Beijing Jiaotong University,Beijing 100044,China;Department of Industry and Electricity,China State Railway Group Co.,Ltd.,Beijing 100017,China)
机构地区:[1]北京交通大学自动化与智能学院,北京100044 [2]中国国家铁路集团有限公司工电部,北京100017
出 处:《中国铁道科学》2024年第5期198-208,共11页China Railway Science
基 金:中国国家铁路集团有限公司科技研究开发计划课题(N2023G001)。
摘 要:针对轨道电路设备应用场景多样且复杂电磁骚扰源影响轨道电路信号传输的问题,提出一种基于麻雀搜索算法(Sparrow Search Algorithm,SSA)的优化变分模态分解方法 (Variational Modal Decomposition,VMD),实现轨道电路信号分析处理。首先,通过基于平均包络熵适应度函数的麻雀搜索算法,实现VMD关键参数的优化选取;其次,采用优化参数的VMD方法,分离深度耦合的轨道电路信号和随机骚扰,实现强噪声背景下轨道电路信号的检测以及骚扰成分的提取和降维;最后,基于Matlab生成仿真混叠信号进行验证,对比提出的SSA-VMD轨道电路信号处理方法与现有信号自适应分解方法的处理效果。结果表明:SSA-VMD方法较现有方法在准确性上有较大优势,处理后信号的信噪比提升可达30 dB;同时,使用现场实测含噪数据验证也表明,SSA-VMD方法对于轨道电路信号的分析处理能达到预期的应用效果。Addressing the challenges posed by diverse application scenarios and the influence of complex electromagnetic disturbance sources on signal transmission of track circuit,a track circuit signal processing and analysis method based on Variational Modal Decomposition(VMD)is proposed based on the Sparrow Search Algorithm(SSA)for track circuit signal analysis and processing.This method first realizes the intelligent selection of key parameters of VMD utilizing the average envelope entropy as the fitness function.On this basis,the deeply coupled track circuit signal are separated from random disturbances,enabling the detection of track circuit signal under strong noise background,as well as the extraction and dimensionality reduction of disturbance components.Finally,simulation mixture signals are generated based on Matlab for validation.Compared with the processing effect of existing signal adaptive decomposition methods,SSA-VMD has higher accuracy,and the signal-to-noise ratio of the processed signal can be improved by up to 30 dB.Validation with field-measured noisy data also shows that the proposed method effectively meets the expected application requirements for track circuit signal analysis and processing.
关 键 词:轨道电路 变分模态分解 麻雀搜索算法 信号处理 信噪比
分 类 号:U284.2[交通运输工程—交通信息工程及控制]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.3