基于拓扑网络的广义城轨信号系统关键组分识别方法

Identification Method of Key Components in Generalized Urban Rail Signaling System Based on Topology Network

信号系统作为城市轨道交通系统运营的大脑,其故障问题是导致城轨运营事故发生的关键因素之一。然而1个事故或者故障的发生往往不是单一的组分出现问题,而是多个组分间相互影响、互相作用的结果。因此其可靠性和安全性可能会受到系统关键组分特性的显著影响。通过调研分析广义城轨信号系统的构成、运营安全特性及影响要素集,并结合城轨信号系统组分间关系,构建了城轨信号系统拓扑网络模型,并利用改进的有限状态机对其进行优化,得到城轨信号系统安全特征拓扑网络模型。基于隐马尔可夫模型的风险文本抽取算法对其关键组分进行识别,最终得到111个信号系统关键组分,并与信号系统国家级风险文件中设备相关风险点清单进行对比,发现覆盖率较高,证明该研究提出的信号系统关键组分辨识方法合理有效。

As the brain of urban rail transit system operation,the fault of signaling system is one of the key factors leading to urban rail operation accidents.However,an accident or fault is often not a problem of a single component,but the result of interaction between multiple components.Therefore,its reliability and safety may be significantly affected by the characteristics of key components of the system.By investigating and analyzing the composition,operation safety characteristics and operation safety influencing factor set of generalized urban rail signaling system,in combination with the relationship between components of urban rail signaling system,a topology network model of urban rail signaling system is constructed,which is optimized by using an improved finite state machine to obtain the safety characteristic topology network model of urban rail signaling system.The risk text extraction algorithm based on Hidden Markov Model is used to identify its key components and 111 key components of the signaling system are obtained finally.Compared with the list of equipment-related risk points in the national risk documents of the signaling system,it is found that the coverage rate is high,which proves that the identification method for key components of the signaling system proposed in this study is reasonable and effective.