Search Results - "Mello, Lucas Henrique Sousa"

An open source experimental framework and public dataset for vibration-based fault diagnosis of electrical submersible pumps used on offshore oil exploration by Varejão, Flávio Miguel, Sousa Mello, Lucas Henrique, Pellegrini Ribeiro, Marcos, Oliveira-Santos, Thiago, Loureiros Rodrigues, Alexandre

“…An Electrical Submersible Pump (ESP) is an important equipment used in the industry for lifting liquids in various types of wells. An ESP is widely used in the…”
Get full text

An experimental framework for evaluating loss minimization in multi‐label classification via stochastic process by Henrique Sousa Mello, Lucas, Varejão, Flávio M., Rodrigues, Alexandre L.

“…One major challenge multi‐label classification faces, are the conditions for evaluating multi‐label algorithms. Simplistic experimental setups based on…”
Get full text

NP-Hardness of minimum expected coverage by Sousa Mello, Lucas Henrique, Varejão, Flávio M., Rodrigues, Alexandre L., Rauber, Thomas W.

“…•An important complexity result to the multi-label learning literature is presented.•The minimum expected Coverage is shown to be NP-hard.•It is also shown the…”
Get full text

One-Class Classifiers for Novelties Detection in Electrical Submersible Pumps by Baptista, Gabriel Soares, Mello, Lucas Henrique Sousa, Oliveira-Santos, Thiago, Varejao, Flavio Miguel, Ribeiro, Marcos Pellegrini, Rodrigues, Alexandre Loureiros

“…Detecting anomalies and fault novelties is of high interest in the industry due to the scarcity of fault examples to train classification systems. In this…”
Get full text

Ensemble of metric learners for improving electrical submersible pump fault diagnosis by Mello, Lucas Henrique Sousa, Oliveira-Santos, Thiago, Varejão, Flávio Miguel, Ribeiro, Marcos Pellegrini, Rodrigues, Alexandre Loureiros

“…Machine learning classification algorithms play a major role in diagnosing faults in industrial equipment. In this paper, we investigate the use of ensembles…”
Get full text

Active learning for new-fault class sample recovery in electrical submersible pump fault diagnosis by Silva, Luciano Henrique Peixoto da, Mello, Lucas Henrique Sousa, Rodrigues, Alexandre, Varejão, Flávio Miguel, Ribeiro, Marcos Pellegrini, Oliveira-Santos, Thiago

“…Applying effective supervised learning methods is difficult when dealing with complex industrial equipment such as Electrical Submersible Pump as the labeling…”
Get full text

Deep Learning Intelligent Fault Diagnosis of Electrical Submersible Pump Based on Raw Time Domain Vibration Signals by Bonella, Vitor Berger, Ribeiro, Marcos Pellegrini, Mello, Lucas Henrique Sousa, Oliveira-Santos, Thiago, Rodrigues, Alexandre Loureiros, Varejao, Flavio Miguel

“…A major challenge for conventional machine learning algorithms is performing intelligent fault diagnosis based on time domain raw vibrational data, where there…”
Get full text

Metric Learning for Electrical Submersible Pump Fault Diagnosis by Sousa Mello, Lucas Henrique, Pellegrini Ribeiro, Marcos, Santos, Thiago Oliveira, Miguel Varejao, Flavio, Rodrigues, Alexandre Loureiros

“…Machine learning classification algorithms are highly dependent of a dataset composed of high-level features. In this paper, a deep learning approach is…”
Get full text