Mostrando 4 resultados de: 4
Filtros aplicados
Subtipo de publicación
Article(4)
Publisher
Applied Sciences (Switzerland)(1)
IEEE/ASME Transactions on Mechatronics(1)
ISA Transactions(1)
Mathematics(1)
Área temáticas
Instrumentos de precisión y otros dispositivos(1)
Métodos informáticos especiales(1)
Otras ramas de la ingeniería(1)
Adversarial Fault Detector Guided by One-Class Learning for a Multistage Centrifugal Pump
ArticleAbstract: The data unavailability of critical machinery is an open issue in the field of condition-based maintPalabras claves:Anomaly detection, Condition-Based Maintenance, Fault Detection, Feature Extraction, Generative Adversarial Network, Generative Adversarial Networks, hydraulic pump, mathematical models, Pumps, Task analysis, VibrationsAutores:Diego Cabrera Mendieta, Diego R. Cabrera, Estupinan E., Li C., Long J., Mariela Cerrada Lozada, Mauricio Leonardo Villacís, René-Vinicio Sánchez Loja, Sancho F.Fuentes:googlescopusFrom fault detection to one-class severity discrimination of 3D printers with one-class support vector machine
ArticleAbstract: The lack of faulty condition data reduces the feasibility of supervised learning for fault detectionPalabras claves:3D printer, Bidirectional generative adversarial network, Fault Detection, One-Class Support Vector Machine, Severity discriminationAutores:Diego Cabrera Mendieta, Diego R. Cabrera, Estupinan E., Fernando Sancho-Caparrini, Li C., Mariela Cerrada Lozada, René-Vinicio Sánchez LojaFuentes:googlescopusFault Classification in a Reciprocating Compressor and a Centrifugal Pump Using Non-Linear Entropy Features
ArticleAbstract: This paper describes a comparison of three types of feature sets. The feature sets were intended toPalabras claves:approximate entropy, fault classification, Non-linear systems, phase space reconstruction, random forest, SUPPORT VECTOR MACHINESAutores:Diego Cabrera Mendieta, Diego R. Cabrera, Estupinan E., Mariela Cerrada Lozada, René-Vinicio Sánchez Loja, Ruben Medina Molina, Yang S.Fuentes:googlescopusReciprocating compressor multi-fault classification using symbolic dynamics and complex correlation measure
ArticleAbstract: Prognostics and Health Management technologies are useful for early fault detection and optimizationPalabras claves:Complex correlation measure, Fault Detection, Poincaré plot, random forest, Reciprocating compressor, Statistical features, Symbolic dynamics, Valve faultAutores:Diego Cabrera Mendieta, Diego R. Cabrera, Estupinan E., Jean Carlo Macancela Poveda, Mariela Cerrada Lozada, René-Vinicio Sánchez Loja, Ruben Medina MolinaFuentes:googlescopus