A novel approach to fault diagnosis of rolling bearings based on Weibull distribution model and support vector machine is proposed. Firstly, Weibull distribution model for original vibration signal of rolling bearings is set up, and its shape parameters and scale parameters are extracted. Then the extracted feature vectors are transmitted to the classifier of support vector machine for fault diagnosis and recognition. It is compared to the common feature extraction methods based on wavelet decomposition and wavelet packet decomposition. The experimental simulation results show that the proposed method has the higher accuracy for fault recognition.