This paper presents the establishing of intelligent system for broken-rotor-bar (BRB) diagnosis based on a novel combination of both, pitch synchronous wavelet transform (PSWT) and multiclass wavelet support vector machines (MWSVM). Most often, broken rotor bar frequency components are hardly detected in the stator current due to its low magnitude and its closeness to the supply frequency component. To overcome this drawback, the PSWT is applied to filter out the fundamental frequency. In order to optimize the cost and the computation time of the diagnosis system, PSWT is implemented under lower sampling rate. MWSVM is developed to perform the faults recognition. Different binary Multiclass SVM strategies are compared with various wavelet kernel functions in terms of classification accuracy, training and testing complexity. The experimental results show that the Directed Acyclic Graph SVM (DAG) gives the best classification accuracy of 99%.