Fault Diagnosis Method Based on Embedded Acquisition Equipment and SVM

Abstract

Fault diagnosis method based on embedded acquisition equipment and SVM is proposed in the paper.The function of the module mainly includes data acquisition, data processing and data storage.SVM is trained by the features and the five states of rolling bearing. The structure of diagnostic model by SVM is defined as 5 input nodes and 5 output nodes,among which 5 input nodes are the features including peak factor,waveform factor,impulse factor,margin factor and kurtosis factor and 5 output nodes are the five states of rolling bearing include normal state, housing washer failure, retainer failure, rolling element failure and inner ring failure.The experimental results show that the diagnostic performance of SVM is effective.