Title :
Grey Prediction of Urban Rail Transit Machine-Electric Equipment Fault Based on Data Mining
Author_Institution :
Huazhong Univ. of Sci. & Technol., Wuhan, China
Abstract :
Through the characteristic analysis of the urban rail transit machine-electric equipment fault alarm, mining the type, frequency and multi-source heterogeneous characteristics of fault data, the paper forms the corresponding data system and knowledge discovery while it builds the mathematical modeling of machine electric equipment fault prediction based on grey theory, carries on the design and implementation of the corresponding system and algorithm. Besides, the paper does a city track traffic machine-electric equipment alarm data as a case which application results show that it can analyze the characteristic of machine-electric equipment fault data correctly and formats the early warning information auxiliary operation maintenance and overhaul.
Keywords :
data mining; electric machines; fault diagnosis; grey systems; maintenance engineering; railway engineering; transportation; city track traffic machine-electric equipment alarm data; data mining; early warning information auxiliary operation maintenance; early warning information auxiliary operation overhaul; fault alarm; fault prediction; grey prediction; grey theory; knowledge discovery; mathematical modeling; urban rail transit machine-electric equipment fault; Analytical models; Data mining; Data models; Maintenance engineering; Monitoring; Predictive models; Rails; Data Mining; Fault modeling; Grey Prediction; Machine-electric Equipment; Urban Rail Transit;
Conference_Titel :
Intelligent Computation Technology and Automation (ICICTA), 2014 7th International Conference on
Conference_Location :
Changsha
Print_ISBN :
978-1-4799-6635-6
DOI :
10.1109/ICICTA.2014.76
