面向高速列车控制数据的推测并行检测算法  

Speculative parallel detection algorithm for high-speed train control data

作　　者：马强[1] MA Qiang(BIM Engineering Laboratory of China Railway Construction,China Railway First Survey and Design Institute Group Co.,Ltd,Xi’an 710043,China)

机构地区：[1]中铁第一勘察设计院集团有限公司中国铁建BIM工程实验室,陕西西安710043

出　　处：《计算机工程与设计》2025年第3期762-769,共8页Computer Engineering and Design

基　　金：国家自然科学基金项目(61902304);中铁第一勘察设计院集团有限公司科研课题基金项目(2021KY43ZD(CYH)-07、KY23-B033)。

摘　　要：针对传统检测方法难以高效处理轨道交通中海量列控数据的问题,设计一种面向高速列车控制数据的推测并行检测算法。分析高速列车控制数据的结构,进行尝试性的数据划分,消解数据内部依赖;利用推测技术,对传统的检测算法展开并行化改造,规避传统方法中内联关系对检测顺序的影响;在分布式平台上使用并行化的算法对划分数据展开检测,借助推测并行技术和分布式平台,提高面向列车控制数据的检测效率。基于西安铁路局的列控数据进行实验,其结果表明,与传统检测方法和其它并行检测方法相比,所提并行算法具有更好的检测效率、良好的可扩展,能够对海量的高速列车控制数据展开及时有效的检测。To handle the issue that traditional measure methods cannot effectively check the massive train control data in rail transportation,a speculative parallel detection algorithm for high speed train control data was raised.The structure of the train control data was analyzed and divided tentatively into small chunks,to eliminate the inside dependencies.The traditional detection algorithm on train control data was reformed by speculative optimization,so that the influences of inline relationship which affected the detection order could be avoided.The divided data chunks were inspected using the speculative parallel detection algorithm on distributed platforms.With the help of the speculative parallel technique and the distributed platform,the detection deficiency for train control data was improved significantly.Experimental results based on train control data of Xi'an Railway show that compared with the traditional detection method and other parallel detection methods,the parallel algorithm proposed has better detection efficiency and good scalability,and it can detect the massive high speed train control data effectively.

关 键 词：轨道交通 高速列车 列控数据 异常检测 分布式计算 推测并行 并行算法 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]