Coal Gangue Interface Detection based on IMF Energy and SVM

A new method to detect coal gangue interface by utilizing vibration signal of coal and gangue is presented for coal and gangue interface detection on fully mechanized mining face. Because of non-stationary characteristics contained in response signals under complicated environment, empirical mode decomposition algorithm was used to decompose the original vibration signal into the intrinsic mode components. We extracted the energy feature of the first seven intrinsic mode components as inputs of support vector machine for simulation experiment. The results show that the method based on Hilbert-Huang transform and support vector machine can be served as coal gangue interface detection effectively.