Abstract: As one of the high-speed railway safety assurance systems, the stable operation of the high-speed railway disaster monitoring system (referred to as the disaster monitoring system) is the fundamental guarantee for the safe operation of the train in the event of severe weather and sudden foreign body intrusion. According to the characteristics of the fault data of the disaster monitoring system, this paper constructed a fault analysis table of the disaster monitoring system based on Failure Mode and Effects Analysis(FMEA), and analyzed the fault performance, fault causes and effects of the system. On this basis, the paper proposed a fault diagnosis method of disaster monitoring system based on random forest algorithm. Through comparative analysis, it can be seen that this method is superior to the traditional fault diagnosis method based on C4.5 decision tree, and is helpful for the rapid diagnosis, location and disposal of the fault of the disaster monitoring system, reduces the workload of manual troubleshooting of equipment fault, and provides technical support for the operation and maintenance of the disaster monitoring system.