Wear Characterization by an On-Line Ferrograph Image

Abstract

Wear characterization with ferrography is an effective off-line method for monitoring a machine's wear condition. The new challenge of real-time wear reporting appeared in condition-based maintenances. Newly developed on-line technologies focus on wear debris concentration rather than on ferrograph images. However, wear rate and wear mechanism are two necessary aspects in describing the wear condition. An on-line ferrograph image provided by an on-line visual ferrograph sensor gives a new solution. By analysing the features of an on-line ferrograph image, new wear characterization with rapid and statistical analysis was investigated for on-line wear reporting. The focus of this method is wear debris chains rather than single wear debris as focused on in traditional ferrography. First, an on-line ferrograph image is preprocessed into a binary image with improved quality. Then the binary image is transformed into a projection curve by parallel radon transformation. The low-frequency component characterizing wear debris chains is extracted from the projection curve by wavelet transformation, which shifts the focus on wear debris chains other than single wear debris. Spectrum analysis is performed to extract the wear characteristics from the low-frequency component of the projection curve. As the main result, two statistical indexes are constructed, as value of point to point and equivalent diameter of larger wear debris, representing the statistical wear debris concentration and the equivalent diameter of larger wear debris, respectively. The indexes correspond qualitatively to wear rate and wear mechanism, respectively. The method was further examined with on-line images from the bench tests of the Eaton engine and the gear reducer of the mine scraper conveyor. The results show that the indexes are effective and independent in describing wear condition, which are promising prospects for on-line wear monitoring with ferrography.