Reaserch And Application Of Bearing Fault Intelligent Diagnosing Method

The rolling bearing is one of the most ordinary and important mechanical parts in the rotating machinery, and is vulnerable to damage. Many faults of rotating mechanism are related to the state of rolling bearings. Its faults can result in abnormally vibration and noise in machine, equipment damage and personal casualty. Therefore, it is important to study the fault diagnosis of rolling bearing.In this paper, the empirical mode decomposition(EMD) is applied to the signal processing of rolling bearing, and diagnoise the faults of rolling bearing by the BP neural network. It produts a new intelligent diagnosis method of rolling bearing by combining EMD and BP neural network.It explained the importance of studing the rolling bearing faults diagnosis, introduced the general situation of faults diagnosis of the rolling bearing and common faults diagnosis methods for the rolling bearing. It introduced the main failure shapes of rolling bearing; the expression of the feature frequency were given by dynamic annlyzing an mechanism of the rolling bearing; then introduced common characteristic of several fault vibration signals and vibration diagnosis means for the rolling bearing. It introduced EMD's and Hilbert Transformation's basic theories and orthogonal, and then the method had some problems and its solvement. It introduced the history and development of neural network and the constructure and computer method of BP neural network. At last, it is verified that the method of EMD in conjunction with BP neural network can diagnosis the faults of rolling bearing through some experiments The method is testified to be correct by the experiments.It used Matlab and Visual Basic mixture programming languages to develop the rollig bearing's faults diagnosis original system.