基于转向架航向角的既有铁路平面线形识别方法研究  

Identification Method of Existing Railway Horizontal Alignment Based on Bogie Heading Angle

作　　者：张晓东[1] 陈静 马超[1] ZHANG Xiaodong;CHEN Jing;MA Chao(Key Laboratory of the Ministry of Education for Road and Railway Engineering Safety Assurance,Shijiazhuang Tiedao University,Shijiazhuang 050043,China;School of Civil Engineering,Shijiazhuang Tiedao University,Shijiazhuang 050043,China)

机构地区：[1]石家庄铁道大学道路与铁道工程安全保障省部共建教育部重点实验室,河北石家庄050043 [2]石家庄铁道大学土木工程学院,河北石家庄050043

出　　处：《石家庄铁道大学学报（自然科学版）》2024年第2期64-70,共7页Journal of Shijiazhuang Tiedao University(Natural Science Edition)

基　　金：国能新朔铁路有限责任公司科技创新项目(SHXS-2020-06)。

摘　　要：轨道平面线形识别是解算轨道不平顺的基础。针对外挂式动态轨道检查仪的实际需要,提出一种基于转向架航向角的铁路平面线形识别方法。首先,通过分段试拟合判定准则自动识别各测点所属线元类型和特征点数量;然后,建立基于转向架航向角的平面线形特征点优化模型;最后,结合云模型改进传统遗传算法的搜索策略提出云遗传算法,实现铁路平面线形精确识别。研究表明,平面线路曲线特征点识别偏差在4 m以内,线形识别准确度均达到97%以上,满足外挂式动态轨道检查仪对轨道不平顺解算的精度要求。The identification of track horizontal alignment is the basis of solving track irregularity.Aiming at the actual needs of the external dynamic track inspection instrument,a railway plane alignment identification method based on the bogie heading angle is proposed.The line element type and the number of feature points of each measuring point are automatically identified by the piecewise fitting criterion.Then the optimization model of plane alignment feature points based on bogie heading angle is established.Finally,combined with the cloud model to improve the search strategy of the traditional genetic algorithm,the cloud genetic algorithm is proposed to realize the accurate identification of the railway plane alignment.The research shows that the identification deviation of the characteristic points of the plane line curve is less than 4 m,and the accuracy of the linear identification is more than 97%,which meets the accuracy requirements of the external dynamic track inspection instrument for the track irregularity solution.

关 键 词：航向角 曲线特征点识别 整体最小二乘法 云模型 遗传算法 

分 类 号：U216.3[交通运输工程—道路与铁道工程]