The invention relates to a
rail transit fault diagnosis method and
system based on a decision-making tree. The method includes the steps of firstly, determining various fault
modes and various monitoring quantities of a
rail transit device by analyzing a circuit and a mechanical structure model of the
rail transit device; secondly, obtaining standard fault sample data according to various historical monitoring quantities of the rail transit device, then, analyzing the standard fault sample data through the decision-making tree generating
algorithm, and conducting construction to obtain the decision-making tree of a fault; thirdly, collecting the various real-time monitoring quantities of the rail transit device, taking the decision-making tree as a classification model of the fault
modes to conduct classification, and thereby determining the type of the fault. The
system comprises a data collection device, a
database unit, a
data analysis unit and a
knowledge base unit. The method and the device solve the technical problems that in the prior art, when the rail
signal system fault is manually diagnosed, workloads are large, efficiency is low and the risks are high, and efficiency and accuracy of rail transit
data analysis and fault diagnosis are improved.