Description of Wear Debris from On-Line Ferrograph Images by Their Statistical Color

Abstract

Analytical ferrography has been proved to be one of the most popular methods for wear characterization. However, it is limited by the real-time requirement of condition-based monitoring. A new wear characterization by on-line ferrograph images is proposed. The color of wear debris was studied based on an on-line visual ferrograph (OLVF) sensor. Generally, the features of on-line ferrograph images included low resolution, high contamination, and wear debris chains. The weak color of the wear debris, especially nonferrous metal debris, in an on-line ferrograph image was unavoidably merged into the mass noises. Accordingly, the on-line images were converted from the initial red, green, blue (RGB) format into hue, saturation, intensity (HSI) for the description of color images. The transmitted image was binarized to locate all wear debris and the wear debris was extracted by their pixels from the corresponding reflected image. The distributions of two HSI components, hue and intensity, were used to characterize the color of on-line ferrograph images. Aiming at the global noise induced by uneven light during sampling, the distributions of the hue and intensity of the wear debris were subtracted by that of the reflected image. As a result, the statistical colors of wear debris were extracted with the hue and intensity from the on-line ferrograph images. A designed experiment with manually prepared oil samples revealed that the wear debris of three common metals could be well differentiated according to their colors via the on-line ferrograph images. The method provides a primary exploration on describing the color of wear debris by on-line ferrograph images.