Early Fault Diagnosis of the Rolling Bearing Based on the Weak Signal Detection Technology

The effective bearing early faults diagnosis is the technical premise to realize the safety production and big accident avoid. In this paper, we use high precision acceleration sensor to collect the bearing vibration signals and wavelet threshold de-noising method to eliminate the noise during the testing process to improve the signal-to-noise ratio of the collected signal. Based on wavelet singularity detection technology, it is discussed in this paper the method of early fault characteristics extraction from the submerged in the noise background, as well as the shortages of traditional Fourier transform are pointed out. Research shows that the method is effective, the extracted fault characteristic frequency and the fault characteristic frequency from theoretical calculation are basically the same. Research results provide a new way for early rolling bearing fault diagnosis.