A feature extraction method for engine block using the empirical mode decomposition (EMD) technique has been proposed in this paper. The EMD technique is developed to break the limitations of conventional signal processing techniques in some extent and to perform further decomposition of signals. In order to extract feature information of engine block, the vibration response will first be processed by the EMD to generate the intrinsic mode functions (IMFs), and then identified by the Fourier transform. Then the same procedure will be adopted to extract the vibration response characteristic from FEM model of block, which is compared between the original and improved engine block. To verify the feasibility of such an approach, the vibration response generated by the finite element simulation will be analyzed, with results compared with the experimental ones. The results demonstrated that the EMD technique made the vibration characteristic more visible by the sifting process, and using the IMFs computed from vibration response, rather than based on the original data, the vibration sources of engine can be successfully identified. And we can also further confirm the structural weak regions of engine block and the main vibration sources, which are benefited to the engine block optimization.