Abstract: In view of the problem that the existing fault diagnosis methods based on feature frequency identification for mineral transmission equipments are susceptible to strong noise, a new fault diagnosis method based on sparse classification algorithm for mineral transmission equipment was proposed. Firstly, vibration signals for the known fault types of equipment are collected by computer and transformed by Fourier transformation. Then, the Fourier transformation coefficient vectors of test vibration signal are sparsely coded on a dictionary, which is constructed by merging the Fourier transformation coefficient vectors of the known vibration signals, so as to get sparse coefficient. At last, the fault types of the test samples are labeled by identifying their minimal reconstruction errors. The simulation and test results demonstrate that the method can effectively diagnose the fault type of bearing of mineral transmission equipment, which provides a novel method for fault monitoring of transmission equipment in coal mine.