The safety management of urban rail transit based on operation fault log

With the rapid development of China's rail transit, the safety of Metro has roused the society's concern more and more widespread. So deeply mining the massive dispatching log data is of great significance to the safety management of Metro operation. For the purposes of risk early-warning and promoting the safety management level of Metro, a dispatching fault log management and analysis database system (DFLMIS) is designed, which contains almost all kinds of accidents that have occurred in the operation of Metro. Taking the compatibility and safety into consideration, the Visual studio 2010 and SQL-sever 2005 are used to develop the DFLMIS. First, changing operation fault log is regarded as a state machine, which describes the data from three dimensions: time, value of information, frequency, and forms the operation scheduling database with data management as the visual angle. Second, the probability space cut algorithm is presented for pruning strategy of probability space, which is suitable for high frequent update of the environment of grid technology as index structure. Finally, the procedures are demonstrated to how DFLMIS can be used to early-warn and identify the risk sources. The research and design of DFLMIS would be of great help to the Metro operators to identify the risk and promote the safety management level.