CORC  > 清华大学
基于置信规则库推理的轨道高低不平顺检测方法
徐晓滨 ; 汪艳辉 ; 文成林 ; 孙新亚 ; 徐冬玲 ; XU Xiao-bin ; WANG Yan-hui ; WEN Cheng-lin ; SUN Xin-ya ; XU Dong-ling
2016-03-30 ; 2016-03-30
关键词轨道不平顺检测 置信规则库 证据推理 优化 solar sail space rendezvous escape energy trajectory optimization U216.3
其他题名Track Vertical Irregularity Detection Based on Inference of Belief Rule Base
中文摘要针对机车振动特征与轨道高低不平顺状态之间存在的复杂非线性关系,提出利用置信规则库推理方法检测轨道高低不平顺故障。建立置信规则库(BRB),通过车厢和车轴测点的垂向振动特征确定不平顺状态。选取两测点的振动幅值作为输入,不平顺的安全等级作为输出,对于被输入激活的置信规则,通过证据推理(ER)算法将被激活规则后项中的置信结构进行融合,从融合结果中换算出不平顺的安全等级。为解决专家给定的初始置信规则库参数不精确问题,采用数值样本优化学习模型训练得到最优参数取值。利用国内某既有干线区段轨道上所获取的实测振动数据,对所提方法进行验证,表明训练后得到的置信规则库系统能够准确描述不平顺与振动特征之间的因果关系,从而给出精确的检测结果。; This paper presents a belief rule based(BRB)inference method for detecting vertical irregularity of rail tracks.The BRB is used to model the complex nonlinear relationship between vibration features of locomotive and vertical irregularity of rail tracks.The inputs of BRB are the vertical vibration amplitudes of compartment and axle.The outputs of BRB are the safety levels of irregularity.The belief rules activated by the inputs are combined by the evidential reasoning(ER)algorithm so as to obtain the fused belief structure about the irregularity,and then,the safety levels of irregularity can be calculated from the fused result.In order to solve the problem of inaccurate parameters of the initial BRB given by experts,the numerical samples-based optimization learning model is used to obtain the optimal parameters by training initial BRB.Finally,the test using the real vibration data collected from a section of a certion existing main line in China shows the trained BRB can precisely describe the causal relationship between irregularity and vibration features to give accurate detection results.
语种中文 ; 中文
内容类型期刊论文
源URL[http://ir.lib.tsinghua.edu.cn/ir/item.do?handle=123456789/146605]  
专题清华大学
推荐引用方式
GB/T 7714
徐晓滨,汪艳辉,文成林,等. 基于置信规则库推理的轨道高低不平顺检测方法[J],2016, 2016.
APA 徐晓滨.,汪艳辉.,文成林.,孙新亚.,徐冬玲.,...&XU Dong-ling.(2016).基于置信规则库推理的轨道高低不平顺检测方法..
MLA 徐晓滨,et al."基于置信规则库推理的轨道高低不平顺检测方法".(2016).
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。


©版权所有 ©2017 CSpace - Powered by CSpace