Aiming at complex features of the fault rotating machinery such as nonstationary and nonlinearity, a new method for fault diagnosis based on multi-fractal was introduced. The vibration signals firstly are analyzed by multi-fractal theory and have multi-fractal characteristics. Then the area of multi-fractal spectrum S and the entropy of multi-fractal spectrum Hm were extracted as new criterions to diagnose machinery faults. Results of experimental analysis indicate that the method is effective and it provides a new way in fault diagnosis of rotating machinery.

Abstract. In order to diagnose the fault of rolling bearing by the vibration signal, a new method of fault diagnosis based on weighted fusion and BP (Back Propagation) neural network was put forward. At first, the vibration signal from the sensors was wave filtered through the method of correlation function, then the fused signal was obtained by the classical adaptive weighted fusion method, the multi-type characteristics parameters was to be as a neural network input. Finally, the fault diagnosis of rolling bearing was realized by the BP neural network, and the results show that the multi-sensor information fusion fault diagnosis method can be proved effectively to achieve the fault diagnosis of rolling bearing.