Please login first
Paulo Rocha   Dr.  University Lecturer 
Timeline See timeline
Paulo Rocha published an article in October 2016.
2
Publications
0
Reads
0
Downloads
3
Citations
Publication Record
Distribution of Articles published per year 

Total number of journals
published in
 
2
 
Publications
Article 0 Reads 3 Citations Classification of imbalance levels in a scaled wind turbine through detrended fluctuation analysis of vibration signals Elineudo Pinho de Moura, Francisco Erivan de Abreu Melo Juni... Published: 01 October 2016
Renewable Energy, doi: 10.1016/j.renene.2016.05.005
DOI See at publisher website
ABS Show/hide abstract
Highlights•We propose the identification of different imbalance levels in a scaled wind turbine.•We use methods to classify vibration signals in order to identify imbalance levels.•As an unsupervised method, k-means groups different classes of imbalance.•Supervised methods are accurate at the classification of vibration signals.•Imbalance levels are well classified for all methods applied. AbstractThis work proposes to identify different imbalance levels in a scaled wind turbine through vibration signals analysis. The experiment was designed in such a way that the acquired signals could be classified in different ways. A combination of detrended fluctuation analysis of acquired signals and different classifiers, supervised and unsupervised, was performed. The optimum number of groups suggested by k-means clustering, an automatic classifier with unsupervised learning algorithm, differs from the number of classes (or subsets) defined during the experimental planning, presenting another approach to the possible classification of vibration signals. Additionally, three supervised learning algorithms (namely neural networks, Gaussian classifier and Karhunen-Loève transform) were employed to this end, classifying the collected data in some predefined amounts of classes. The results obtained for the test data, just a little different regarding the training data, also confirmed their capability to identify new signals. The results presented are promising, giving important contributions to the development of an automatic system for imbalance diagnosis in wind turbines.
Article 0 Reads 0 Citations Estudo e aplicação de simulação computacional em problemas simples de mecânica dos fluidos e transferência de calor Paulo Alexandre Costa Rocha, João Victor Pinto da Silveira Published: 01 December 2012
Revista Brasileira de Ensino de Física, doi: 10.1590/s1806-11172012000400006
DOI See at publisher website
ABS Show/hide abstract
O presente trabalho tem o intuito de apresentar o desempenho da simulação computacional em alguns casos que podem ser considerados clássicos no estudo de mecânica dos fluidos e transferência de calor. Para isso, foi utilizado o software comercial Ansys-CFX 12.1, que utiliza como base o método dos volumes finitos. O desempenho da ferramenta foi avaliado através de comparação com resultados experimentais e dados da literatura. Uma vez que se torna evidente o crescente desenvolvimento dos computadores e a facilitação do acesso aos mesmos e às ferramentas sofisticadas em sala de aula, o conhecimento das limitações destas se torna importante. São apresentados quatro casos que abordam diferentes situações físicas: o estudo do escoamento de ar sobre um perfil aerodinâmico, a simulação de um misturador estático, o funcionamento de um viscosímetro rotacional e o escoamento sobre uma placa plana normal ao fluxo de ar.