A fault diagnosis method for motor bearings based on support vector machine (SVM) and particle swarm optimization (PSO) is proposed. The characteristic of the vibration signal is characterized by the time-domain and the wavelet packet energy characteristics, which makes the characteristic of the vibration signal has good reliability and sensitivity and improves the accuracy of fault diagnosis. The PSO algorithm is used to optimize the parameters of the penalty parameter and the radial basis kernel function of SVM, and compared with other parameter-optimization algorithms. Experimental results show that the proposed bearing fault diagnosis method has a very good effect not only on the recognition of motor bearing outer race fault, inner race fault and ball fault, but also on the severity differentiation of every kind of fault. It has strong practicability.