Fault Diagnosis Of Rolling Element Bearings Based On Wavelet Analysis And OS-ELM

With the rotating machinery tending to be large scale, high efficiency and integration, requirement of safety and reliability of machinery is increasing. Rolling bearing is the crucial parts of rotating machinery, but it is easy damaged. So, running status of rolling bearing influences the operation state of mechanical equipment directly. Fault diagnosis of rolling element bearing is significant to avoid serious accidents and huge economic losses effectively.In-depth research on theory and key technology of the method used in fault diagnose of rolling bearing is conducted in this thesis, the main work is as follows:Through the system analysis of rolling bearing fault diagnosis method and the research status at home and abroad in this field, it can be found that rapid and accurate bearing fault diagnosis technology has become a research focus. In the numerous diagnostic methods, the vibration diagnosis method has been widely adopted. Three categories of the vibration diagnosis method are analyzed, the emphasis are wavelet transform and its improved method and empirical mode decomposition method.The basic theory of wavelet analysis method in the time-frequency domain method are studied, the basic principle and the characteristics of DTCWPT are mainly studied.In view of the non-stationary and nonlinear of the rolling bearing vibration signal and deficiency of various classic methods, this thesis proposes a fault feature extraction method based on improved DTCWPT. Improved DTCWPT is improvement of DTCWPT, which is constructed based on EMD and two step screening processes. This method can not only effectively extract the fault feature frequency components but also can remove noise, which has been demonstrated by simulated experiment.The theory of OS-ELM is studied intensively. OS-ELM is the constructed based on ELM, this algorithm can deal with the data which arrived in succession.The effectiveness of the proposed bearing fault diagnosis technique is demonstrated by applying it to both simulated signals and practical bearing vibration signals under different conditions. The results show that the proposed method is effective for the fault diagnosis of rolling element bearings.