Fault Detection of Spindle Rolling Bearings in CNC Machine Tools Based on Odorless Kalman Filtering Algorithm

Abstract

Due to the various types of faults in the spindle rolling bearings of CNC machine tools, the accuracy of fault detection is reduced. Therefore, a fault detection method for spindle rolling bearings of CNC machine tools based on odorless Kalman filtering algorithm is proposed. The VB6 vibration signal acquisition analyzer is used to collect the operating data of the spindle rolling bearings of CNC machine tools, and the wavelet analysis method is used to denoise the collected data signals. Based on the denoised rolling bearing operation data, the odorless Kalman filtering algorithm is used to process the spindle operation signal, estimate the status of the rolling bearing in real-time, and compare it with the preset fault standards to achieve online monitoring and judgment of bearing faults. The experimental results show that the proposed method can consistently maintain high fault detection accuracy and shorten fault detection time for different types of faults in rolling bearings.