The Theory And Method Of Fault Discovery Based On Text Information Extraction For On-board Vehicle Equipment Of High Speed Railway

Chinese Train Control System(CTCS)consists of a ground equipment system and an on-board vehicle equipment system.As an important part of CTCS,the stability of on-board vehicle equipment(referred to as "vehicle equipment")plays a crucial role in the operation of high-speed railway.Log files formed in the process of the on-board computer and staff shift records include a large amount of information reflecting the operation status of vehicle equipment,which are important data source for vehicle equipment fault discovery.However,the existing way of utilization of these data still depends on the staff experience and manual record and query,which is inefficient,subjective,and lack of theoretical basis and guidance for fault discovery.In this thesis,based on extracting the Log files and staff shift records,a fault dictionary about vehicle equipment of high speed railway is made,the automatic positioning of faults in Log files statement is achieved,and the automatic fault discovery platform is established based on the Matlab simulation tools,which have guiding significance for further study,reduces the manual operation of staff and improves the work efficiency greatly.The whole research work is mainly from the following aspects.Firstly,the structure of vehicle equipment and information extraction algorithms are mentioned in the thesis.Then the characteristics of Log files and the staff shift records are analyzed.Based on WEKA data mining tool and SQL Server database,the text data mining is studied.The results show that WEKA and SQL Server are not suitable for the data.Based on the characteristics of the data,a research framework of fault discovery automatic location is established.Secondly,the Maximum Matching(MM)algorithm and Term Frequency&Inverse Documentation Frequency(TFIDF)algorithm are selected to extract information from two kinds of data and a standardized fault dictionary is built.The automatic positioning of fault statement in Log file is realized by using regular expression algorithm.Finally,based on the Matlab simulation tool,a human-computer interaction platform,suitable for Windows system,is created with the help of established framework.By dealing with Log files formed during April,the usage of platform process,module function and results are shown in this thesis.