Skip to Main Content
Precise location of a train on the rail network is important to train control system. The general problem of locating a train on closely-spaced parallel tracks is hard to determine the track occupied by train simply relying on GNSS. Hidden Markov model (HMM) is widely used in speech processing of a time series model. This paper applied the HMM to the track occupied automatic identification, established the HMM of tracks, resolved the problem of track occupied identification using GNSS, and progressive studied the impact on identification, when changing the state number of the HMM, GNSS output frequency and train speed, then the optimal parameters are determined.