Research on rub impact fault diagnosis method of rotating machinery based on EMD and SVM

Rub is a common fault of rotating machinery. It will bring serious damage to mechanical equipment. A new diagnosis method based on empirical mode decomposition (EMD) and support vector machine (SVM) is proposed. Firstly, signals are decomposed into a finite number of intrinsic mode functions (IMFs).Then, the maximal singular values of the every single of IMF are defined as the feature vectors and served as input parameters of SVM classifiers to classify fault patterns of rotating machinery. Meanwhile the way was used on the rub impact fault identification of dual-disk over-hung rotor-bearing system. Experimental results show that the way can be more effectively and accurately than conventional BP and RBF neural networks, and has high robustness, good generalization ability as well.