基于聚类算法的道岔健康度标准值智能分析系统研究  

Research on Intelligent Analysis System of Turnout Health Standard Value Based on Clustering Algorithm

作　　者：韩思远 邱晓莉 熊庆 HAN Siyuan;QIU Xiaoli;XIONG Qing(Guangxi Traffic Control DEVOPS Technology Co.,Ltd.,Nanning Guangxi 530219,China;School of Intelligent Manufacturing and Automobile,Chengdu Vocational&Technical College of Industry,Chengdu Sichuan 611130,China;Vehicle Measurement,Control and Safety Key Laboratory of Sichuan Province,Chengdu Sichuan 611130,China;Key Laboratory of Fluid and Power Machinery,Ministry of Education(Xihua University),Chengdu Sichuan 611130,China)

机构地区：[1]广西交控智维科技发展有限公司,广西南宁530219 [2]成都工业职业技术学院智能制造与汽车学院,四川成都611130 [3]汽车测控与安全四川省重点实验室,四川成都611130 [4]流体及动力机械教育部重点实验室(西华大学),四川成都611130

出　　处：《中国铁路》2024年第2期116-121,共6页China Railway

基　　金：成都工业职业技术学院院级课题(2022YJ-38,2023YJ-5);四川省自然科学基金面上项目(2022NSFSC0400);汽车测控与安全四川省重点实验室开放课题(QCCK2023-003);四川省教育厅项目(GZJG2022-048);流体及动力机械教育部重点实验室(西华大学)开放课题(LTDL-2023010)。

摘　　要：根据专家经验分析道岔曲线特性并设置每组道岔的标准值具有工作量大、专家经验标准值不能覆盖每个道岔特性的问题。在分析道岔特性及健康度评价现状基础上,基于云平台技术,搭建道岔健康度自学习软件架构,阐述了使用专家经验分析道岔数据、三次样条差值曲线算法和K-means聚类算法在道岔健康度标准值智能选取系统中的应用,提出基于聚类算法的道岔健康度标准值智能提取方法。系统可适用于不同类型的道岔,能够有效降低设置不同道岔系统健康度评价参数标准值的工作量。It is a heavy workload to analyze the turnout curve characteristics and set the standard value of each group of turnouts according to expert experience,and there is a problem that expert experience standard value cannot cover each turnout characteristic.On the basis of analyzing the characteristics and health evaluation status of turnouts,this paper builds a self-learning software architecture for turnout health based on cloud platform technology,expounds the application of expert experience analysis of turnout data,cubic spline difference curve calculation algorithm and K-means clustering algorithm in the intelligent selection system of turnout health standard value,and puts forward an intelligent extraction method of turnout health standard value based on clustering algorithm.The system is applicable to different types of turnouts,and can effectively reduce the workload of setting standard values for health evaluation parameters of different turnout systems.

关 键 词：铁路信号 道岔系统 健康度标准值 三次样条法 微分曲线法 K-MEANS聚类算法 

分 类 号：U2847[交通运输工程—交通信息工程及控制]