Fault diagnosis of rotating machinery based on time-frequency decomposition and envelope spectrum analysis

In order to raise the working reliability of rotating machinery in real applications and reduce the loss caused by unintended breakdowns, a new method based on improved ensemble empirical mode decomposition (EEMD) and envelope spectrum analysis is proposed for fault diagnosis in this paper. First, the collected vibration signals are decomposed into a series of intrinsic mode functions (IMFs) by the improved EEMD (IEEMD). Then, the envelope spectrums of the selected decompositions of IEEMD are analyzed to calculate the energy values within the frequency bands around speed and bearing fault characteristic frequencies (CDFs) as features for fault diagnosis based on support vector machine (SVM). Experiments are carried out to test the effectiveness of the proposed method. Experimental results show that the proposed method can effectively extract fault characteristics and accurately realize classification of bearing under normal, inner race fault, ball fault and outer race fault.