Dissertações em Engenharia de Infraestrutura e Desenvolvimento Energético (Mestrado) - PPGINDE/NDAE/Tucuruí
URI Permanente para esta coleçãohttps://repositorio.ufpa.br/handle/2011/9401
Navegar
Navegando Dissertações em Engenharia de Infraestrutura e Desenvolvimento Energético (Mestrado) - PPGINDE/NDAE/Tucuruí por Agência de fomento "FADESP - Fundação de Amparo e Desenvolvimento da Pesquisa"
Agora exibindo 1 - 2 de 2
- Resultados por página
- Opções de Ordenação
Item Acesso aberto (Open Access) Desenvolvimento de sistema de diagnóstico de falhas em roletes de transportadores de correia(Universidade Federal do Pará, 2024-03-28) SOARES, João Lucas Lobato; MESQUITA, Alexandre Luiz Amarante; http://lattes.cnpq.br/3605920981600245; https://orcid.org/0000-0001-5605-8381Belt conveyors are essential equipment in mining industry and require constant monitoring to maintain good reliability. In order to support the belt and the material being conveyed, rollers are components that constantly fail during operation, in which they present faults in bearings and surface wear in the shell as the most common failure modes. Thus, monitoring based on predictive maintenance is essential, and machine learning techniques can be used as an alternative for detecting equipment failures. In diagnostics using machine learning, the feature selection step is important to avoid loss of accuracy in the classification of the equipment's condition. The present study analyzes the performance of the decision tree algorithm and Analysis of Variance (ANOVA) as alternative methods for dimensionality reduction. Initially, the vibration signals were collected on the rollers of a belt conveyor bench and the Wavelet Packet Decomposition (WPD) was applied to the signals to obtain the energy ranges, which were used as features for classification. After the determination of the best features, two approaches were analyzed for the selection of features: one with the application of the method without dimensionality reduction and the other with the application of the decision tree. In addition, different classification algorithms were used: Support Vector Machine (SVM), k-Nearest Neighbor (kNN) and Artificial Neural Network (ANN). As a result, it was found a superior performance of diagnostic accuracy in all techniques with a reduction in the dimensionality of the characteristics selected by the decision tree. In addition, SVM, kNN and ANN showed increases in accuracy ranging among the fault diagnosis models approached.Item Acesso aberto (Open Access) Determinação experimental da vazão de despoeiramento na descarga de carvão coqueificável(Universidade Federal do Pará, 2021-02-26) CHAVES, Gabriel Guedes; MESQUITA, André Luiz Amarante; http://lattes.cnpq.br/1331279630816662Dust control mechanisms during industrial processes are often carried out using spray nozzle methods or exhaust systems, equipped with bag filters. The following work aims to develop an experimental method to determine the volume of exhaust in different quantities of materials and different heights of material discharge. A test protocol is presented to design exhaust systems for any material, mass flow and drop height, using an experimental method in which it simulates the material drop in order to evaluate experimental dedust flow rates for an industrial ventilation system. A literature review of the current empirical models of exhaustion volume is presented. The methodology is correlated through the concentration of respirable particles measured by the measurement equipment with the exhaust flow data. The results presented are for coal, comparing existing and suggested correlations with experimental data for three different heights of fall. It is hoped, therefore, to support design engineers in the design of industrial exhaust systems, reducing the damage caused by fine particles in workers and in the population that lives near the polluting source.