GGC: Gray-granger causality method for sensor correlation network structure mining on high-speed train

Vehicle information on high-speed trains can not only determine whether the various parts of train are working normally, but also predict train's future operating status. How to obtain valuable from massive vehicle data is a difficult point. First, we divide into 13 subsystem datasets, according functions collection components. Then, gray theory and Granger causality test, propose Gray-Granger Causality (GGC) model, which construct network basis correlation between By using complex mine its networks, find that networks have characteristics scale-free network. In addition, weak against attacks, closely connected strong attacks.