Machine Sound Using Wavelet and Application in Rolling Bearing Fault Diagnosis

Machine sound always carries information about the working of the machine. But in many cases, the sound has a very low SNR, so it is very difficult to make time-frequency analyse of sound signal. A denoising method based on wavelet technology is given. Based on wavelet decomposition, sound signal caused by mechanical diagnosis can be separated. Experimentation tests that this is an effective method to diagnose fault of rolling bearing comparing with other fault diagnosis methods.