Establishment of the Accuracy and Consistency of Using Automatic Image Analysis to Classify Wear Debris Particles

Wear debris particle analysis is an equipment health monitoring technique used to identify possible failure modes in various engine components. One of the first stages in the analysis involves the examination under a microscope of particles collected from the component’s lubrication system on magnetic drain plugs and filters. However, the subjectivity of technicians’ judgements means that diagnosis may not be consistent between technicians. A software tool capable of automatically classifying the images of wear debris particles has been developed and tested using an 800-image database. It is shown that using automatic image analysis for the classification of wear debris particle images is more consistent, accurate and informative when compared to the classifications assigned by wear debris experts.Copyright © 2005 by ASME