Este trabalho apresenta o desenvolvimento de uma ferramenta open-source para a classificação e contagem automática de partículas em óleos industriais. As análises são realizadas através da filtragem do óleo por membranas onde as imagens são obtidas por uma câmera ligada a um microscópio óptico conforme a norma ISO4407:2002. Para a codificação dos resultados, foi utilizada a norma ISO4406:1999 que descreve o método utilizado para sua nomenclatura. O framework foi elaborado em torno do software ImageJ que possui vasta literatura na área e possibilita a extensão futura da ferramenta para outras áreas. Os resultados obtidos demonstram o potencial da ferramenta para a contagem de partículas de forma rápida e eficaz fornecendo, ao especialista, informações importantes sobre as características do particulado analisado. / This work presents the development of an open-source tool for automatic classification and counting of particles in industrial oils. Analyses are performed by filtering the oil through a membrane where the images are obtained by a camera connected to an optical microscope according to the standard ISO4407: 2002. For coding the results, the standard ISO4406 was used and describes the method used to its nomenclature. The framework was developed around the software ImageJ which has vast literature in the field and enables the tool for further extension to other areas. The results demonstrate the potential of the tool for quickly and effectively count particles, giving to the specialist important information about the analyzed particulate characteristics.

Monitoring wear particles in lubricating oils allows specialists to evaluate thehealth and functionality of a mechanical system. The main analysis techniquesavailable today are manual particle analysis and automatic optical analysis. Man-ual particle analysis is effective and reliable since the analyst continuously seeswhat is being counted . The drawback is that the technique is quite time demand-ing and dependent of the skills of the analyst. Automatic optical particle countingconstitutes of a closed system not allowing for the objects counted to be observedin real-time. This has resulted in a number of sources of error for the instrument.In this thesis a new method for counting particles based on light microscopywith image analysis is proposed. It has proven to be a fast and effective methodthat eliminates the sources of error of the previously described methods. Thenew method correlates very well with manual analysis which is used as a refer-ence method throughout this study. Size estimation of particles and detectionof metallic particles has also shown to be possible with the current image analy-sis setup. With more advanced software and analysis instrumentation, the imageanalysis method could be further developed to a decision based machine allowingfor declarations about which wear mode is occurring in a mechanical system.