Por favor, use este identificador para citar o enlazar este ítem: https://repositorio.uci.cu/jspui/handle/123456789/9449
Título : A New Approach for Fault Diagnosis of Industrial Processes During Transitions
Autor : Acevedo Galán, Danyer L.
Quiñones Grueiro, Marcos
Prieto Moreno, Alberto
Llanes Santiago, Orestes
Fecha de publicación : 2018
Editorial : Springer
Citación : Acevedo-Galán D.L., Quiñones-Grueiro M., Prieto-Moreno A., Llanes-Santiago O. (2018) A New Approach for Fault Diagnosis of Industrial Processes During Transitions. In: Hernández Heredia Y., Milián Núñez V., Ruiz Shulcloper J. (eds) Progress in Artificial Intelligence and Pattern Recognition. IWAIPR 2018. Lecture Notes in Computer Science, vol 11047. Springer, Cham. https://doi.org/10.1007/978-3-030-01132-1_39
Resumen : This paper presents a new approach for fault diagnosis of industrial processes during transitions. The proposed diagnosis strategy is based on the combination of the nearest-neighbor classification rule and the multivariate Dynamic Time Warping time series similarity measure. The proposal is compared with four different classification methods: Bayes Classifier, Multi-Layer Perceptron Neural Network, Support Vector Machines and Long Short-Term Memory Network which have high performance in the specialized scientific bibliography. The continuous stirred tank heater benchmark is used under scenarios of faults occurring at different moments of a transition and scarce fault data. The proposed approach achieves a classification performance approximately 20% superior compared to the best results of the four instance-based classifiers.
URI : https://repositorio.uci.cu/jspui/handle/123456789/9449
Aparece en las colecciones: UCIENCIA 2018

Ficheros en este ítem:
Fichero Tamaño Formato  
A020.pdf117.09 kBAdobe PDFVisualizar/Abrir

Los ítems del Repositorio están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.