Abstract: A fault diagnosis approach based on intrinsic mode singular value decomposition and support vector machines is put forward. Firstly, the EMD method is used to decompose the rotating machinery vibration signals into a number of intrinsic mode functions by which the initial feature vector matrixes are formed automatically. Secondly, by applying the singular value decomposition technique to the initial feature vector matrixes, the singular values are obtained. Finally, the singular values serve as the fault characteristic vectors to be input to the support vector machine classifier and the work conditions and fault patterns are identified by the output of the classifier. The analysis results from gear vibration signals show that the fault diagnosis method based on intrinsic mode singular value decomposition and support vector machines can extract fault features effectively and classify working conditions and fault patterns of gears accurately even when the number of samples is small.