Comparative Study on Wear Particle Colour Classifications Using Various Machine Learning Algorithms

Wear particle assessment is one of state-of-the-art in used lubricant analyses. There are three categories, i.e. shape analysis, surface texture analysis, and particle colour analysis. Especially, an analysis of wear particle colour can be induced to identify the material type from the worn surface when surface failures of component occurred in the most commonly used lubricants. The quantification of wear particle colours is essential, which is readily extracted by the image processing. However, the colours of wear particles are often unrecognised by visual examination of the human, although these are probably indicated via RGB colours by personal computer. This article therefore aims to determine the quantitative colour descriptors of wear particles, and to find out the suitable method to classify the particle colour. In present work, the colours of wear particle images were separated with combined HSI and L*a*b* colour models, and were then classified by using machine learning algorithms as a decision-making tool. These tools consist of the Bayesian classifiers, Tree classifiers, Rule classifiers, Lazy classifiers, Meta-learning classifiers, and Function classifiers. By comparing in their tools, the function classifier tool was performed to accurately distinguish the heated metals, steel particles, dark and red oxides, and copper alloys, resulting in more reliable examination than that of the other tools.