Using Short-time Fourier Transform in Machinery Diagnosis

Diagnostic of machine using the timefrequency representation of vibration is becoming widely used by many companies and experts. In recent years, the preventive maintenance is no more desirable and in fact it has evolved into the prediction maintenance. The current methods of machine diagnosis can not provide detailed diagnostics and condition prediction. This paper proposes the application of ShortTime Fourier Transform (STFT) as a timefrequency method, which can provide more information about a signal in time and in frequency and gives a better representation of the signal than the conventional methods in machinery diagnosis. In this paper, we review the machine diagnosis techniques based on the verification of classical vibration parameters. Then the necessity of using time-frequency analysis in machinery diagnostics is discussed. Finally, the theory of the Short-Time Fourier Transform is briefly studied and its advantages are shown by some practical examples.