In this paper authors introduce a novel procedure for the local damage detection based on the distribution distances and time-frequency decomposition. Local damage in bearings/gearbox provides specific response in the vibration signal. It can be further investigated via time-frequency decomposition where one can track energy distribution change in time. Applying distribution distances to STFT matrix of the vibration signal one can find deviation of subsequent samples from one used as a referential. Combined with appropriate thresholding criterion for the matrix, results can be further enhanced to provide more meaningful information. Analysed real signals were acquired from the belt conveyor driving unit in the mining facility.