Initial parameter guided variational mode extraction for damage detection of wind turbine bearing

Abstract

Rolling bearing is the necessary mechanical component of wind turbine, and damage detection of wind turbine bearing is of important significance to effectively prevent long downtime and catastrophic accident. Nevertheless, weak feature extraction of wind turbine bearing in the incipient damage stage is always a challenging task because of severe service environment. Accordingly, an initial parameter guided variational mode extraction (IPGVME) method is put forward to deal with this problem. First, the equivalent filter trait and the iterative convergence trait of VME are investigated, and the influence of center frequency parameter and balance factor parameter on mode extraction behavior is further analyzed. Moreover, a comprehensive evaluation indicator fluctuation spectrum guided center frequency selection scheme and a whale optimization algorithm guided balance factor selection scheme are creatively developed, then the IPGVME method is further put forward to detect bearing damage by fusing with these two specific schemes. The feasibility of this proposed method is approved by the experimental and the engineering signals, and the results indicate that this method is superior to other contrastive methods in damage detection of wind turbine bearing.

Review of Wind Power Bearing Wear Analysis and Intelligent Lubrication Method Research

“…Currently, lubrication methods for bearings can predict the initial stages of spalling in advance. However, the problem of the premature failure of bearings due to improper lubrication (choice of lubricant, lubrication method, insufficient lubrication, and excessive lubrication) still exists [174]. Therefore, it is essential to select the correct lubrication method for the bearing.…”