Abstract: Aiming at the problem of fault diagnosis for rolling bearing of metro vehicle, a method combined empirical mode decomposition (EMD), with support vector machine (SVM) was proposed. Firstly, the collected vibration signal was de-noised by using wavelet method. Then, the obtained signals were decomposed into a finite number of intrinsic mode functions (IMF) whose energy feature parameters were calculated to construct feature vectors. Finally, a certain SVM classifier was built to recognize the fault pattern.The experiment results indicated that the proposed method could identify fault patterns for ruling bearing accurately and effectively.