Publicação: Development of a machine learning model to predict construction machinery gearboxes’ health status
Carregando...
Tipo do documento
Data
Direito de acesso
Coleções
Programa
Área do conhecimento
CNPQ::ENGENHARIAS
Título da Revista
ISSN da Revista
Título de Volume
Orientador
Coorientador
Resumo
As industries increasingly turn to data-driven methods in their maintenance strategies, the need for advanced predictive maintenance techniques becomes increasingly evident. This study focuses on the application of Machine Learning (ML) algorithms to enhance the reliability and efficiency of vehicle transmission systems, with a focus on monitoring the health of powershift transmissions for construction machinery, at ZF Friedrichshafen, a global automotive technology company. By utilizing ML algorithms, this project aims to identify patterns in operational data, facilitating the prediction of potential failures and enabling timely interventions. The goal of the study was to compare the ML ML algorithms, Random Forest, K Nearest Neighbors (KNN), and Support Vector Machines (SVM) to identify the most effective in predicting transmission failures. The research involved stages ranging from data collection and pre-processing to model optimization and evaluation, using machine learning metrics. The results revealed that the Random Forest algorithm outperformed the others in terms of precision, recall, and F1 score for the studied use case. Its robust ability to accurately classify positive and negative instances was particularly significant in the analysis of vehicle operational data.
Abstract
Palavras-chave
Machine learning algorithms, Vehicle transmission systems, Predictive maintenance, Operational data analysis, Algoritmos de aprendizado de máquina, Sistemas de transmissão de veículos, Manutenção preditiva, Análise de dados operacionais
Citação
ALMEIDA, Camila Aparecida. Development of a machine learning model to predict construction machinery gearboxes’ health status. 2024. 66 f. Trabalho de Conclusão de Curso (Graduação em Engenharia Aeronáutica) – Universidade Federal de Uberlândia, Uberlândia, 2024.