Rolling bearing sound signal fault feature extraction method based on STFT and rotation inertia entropy

摘要: The invention discloses a rolling bearing sound signal fault feature extraction method based on an STFT and rotation inertia entropy. A common is vibration signal, however the requirement of sensor by collection data very high, equipment cost increased, intelligent mobile phone taken as important part daily life, recording function can collect signal. provides short time Fourier transform (STFT) entropy, firstly used to then subjected analysis, spectrogram matrix obtained, modulus entropy calculated. test result analysis shows that obtained has excellent classification characteristic support diagnosis bearing.