In the light of fault identification, a rolling bearing fault diagnosis method is proposed to make full use of the vibration signal. The improvement is based on ensemble empirical mode decomposition (EEMD) singular value entropy criterion. First, the intrinsic mode functions (IMFs) are created based on the EEMD decomposition of the vibration signal of a rolling bearing. The representative fault information is selected from the IMF to reconstruct the original signal in terms of evaluation index, such as kurtosis, mean square error, and Euclidean distance. Then the singular value entropy is obtained by combining the information entropy method to determine the fault category of the rolling. The results show that the proposed method can distinguish the different characteristics of a rolling bearing under different types of work characteristics of the interval with a higher fault diagnosis accuracy than the traditional method.