Surface Intrusion Recognition Method for Subway Tunnel Security System

Subway is the main means of urban transportation, so its security monitoring is very important. Aiming at the problems of traditional technology, such as low detection resolution, limited monitoring distance and high cost, this paper proposes a method for surface intrusion detection of subway tunnel based on the grating array. The method uses spectral subtraction and short-time Fourier transform to extract the intrusion signal, and combines empirical mode decomposition and permutation entropy to extract the features for identifying. An experimental platform based on grating array vibration sensing is built between Hugong and Yezhihu stations of Wuhan Metro Line 7. For actual sampling data, this method can effectively extract invasion signals. And four common events are distinguished, including subway train traveling in the tunnel, lorry passing, discrete pulse construction, and continuous pulse construction on the ground surface, with an average recognition rate of above 90%.