2026-08-272026-08-272026-07-14CONCEIÇÃO, Jade Melo da. Aprendizado de máquina para análise de óleo na manutenção preditiva de equipamentos móveis na indústria de mineração. Orientador: Raphael Barros Teixeira. 2026. 79 f. Trabalho de Curso (Bacharelado em Engenharia Elétrica) – Faculdade de Engenharia Elétrica, Campus Universitário de Tucuruí, Universidade Federal do Pará, Tucuruí, 2026. Disponível em: https://bdm.ufpa.br/handle/prefix/10040. Acesso em:.https://bdm.ufpa.br/handle/prefix/10040Lubricating oil analysis is an important tool for identifying premature equipment failures, extending component lifespan, and reducing maintenance costs. In this context, it is necessary to develop methods that contribute to the improvement of diagnostic quality and the anticipation of potential failures. Thus, thiswork proposes the application of machine learning techniques to classify the results of oil analyses in mobile equipment within the mining industry, identifying the oil condition based on parameters established by asset management. For this study, diagnostic data collected through daily sampling over two years were used. The dataset underwent preprocessing stages and was divided into training (80%) and validation (20%) subsets, allowing for the training andevaluation of different classification algorithms, including Random Forest, K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Tree, and Multilayer Perceptron (MLP). The models were applied with the objective of identifying data patterns and classifying the oil state according to the defined parameters into normal, monitor, and critical classes. The evaluated algorithms presented competitive predictive performance, with emphasis on the Random Forest, which achieved the best overall performance, reaching an accuracy of 83.25%, a Macro F1-score of 82.02%, and high stability in the Precision-Recall curve (Average Precision of 0.84 for the critical class). Thus, the study validates the effectiveness of machine learning as a robust decision-support tool predictive maintenance strategies.Acesso AbertoAnálise de óleoAprendizado de máquinaClassificação de dadosManutenção preditivaEquipamentos móveisOil analysisMachine learningData classificationPredictive maintenanceMobile equipmentCNPQ::ENGENHARIASCNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO::METODOLOGIA E TECNICAS DA COMPUTACAOTrabalho de Curso - Graduação - MonografiaAttribution-NonCommercial-NoDerivs 3.0 Brazil