Text mining in fault analysis for on-board equipment of high-speed train control system

Abstract

The fault diagnosis and analysis of high-speed train is of great significance for train's safe and highly efficient operation. The complexity and quantity of on-train information which is closely related with fault diagnosis and analysis is increasing rapidly as the development of high-speed railway. Onboard system fault recording files contains lots of important fault information described in short-text which is recorded by maintainers in nature language(NL). This paper makes an analysis on operation and fault information of on-board system recorded in NL based on text mining. The fault text dictionary is constructed for word segmentation, and fault text chain is defined as well as the construction method in order to process the fault recording files. At last, the method is applied to segment the on-board system fault recording files and construct fault text chains, therefore the faults of on-board equipment are analyzed and we obtained the faults' distribution.