En Route to the Automated Wear Surface Classification System: Differentiating Between Adhesive, Abrasive, and Corrosive Wear Under Different Load Conditions

Abstract

From the industrial view point, an automated classification system of worn surfaces is highly desirable for the monitoring and prediction of the operational health status of machines and their components. Optical microscopy images of abrasive and adhesive wear surfaces were obtained and analyzed using recently developed directional blanket covering (DBC) and DBC curvature (DBCC) methods. As these methods have the unique ability of to measure the surface roughness and curvature complexity at individual scales and directions, minute differences have been detected. In the present study, both DBC and DBCC methods were evaluated in differentiating between surfaces generated under abrasive, adhesive, and corrosive wear modes under different operating conditions, i.e., exhibiting different wear severity. The wear surfaces were imaged using an optical microscope and a confocal surface profilometer. Results obtained showed that the methods can detect minute differences between the wear modes and different wear severity, regardless of the imaging technique used. This is an important step in the development of machine diagnostic and prognostic systems/tools based on the images of worn surfaces.