Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Fault diagnosis of chemical processes with incomplete observations: A comparative study

Autor
Askarian, M.; Escudero, G.; Graells, M.; Zarghami, R.; Jalali Farahani, F.; Mostoufi, N.
Tipus d'activitat
Article en revista
Revista
Computers & chemical engineering
Data de publicació
2016-01-04
Volum
84
Pàgina inicial
104
Pàgina final
116
DOI
https://doi.org/10.1016/j.compchemeng.2015.08.018 Obrir en finestra nova
Projecte finançador
Centre d'enginyeria de processos, energia i medi ambient
EXTENDIENDO LOS HORIZONTES PRODUCTIVOS FRENTE A LA PARADOJA DE LA INTEGRACIÓN
Sistema integrado de la gestión de la energía y los recursos ambientales para procesos industriales económicamente sostenibles
Repositori
http://hdl.handle.net/2117/82031 Obrir en finestra nova
URL
http://www.sciencedirect.com/science/article/pii/S0098135415002793 Obrir en finestra nova
Resum
An important problem to be addressed by diagnostic systems in industrial applications is the estimation of faults with incomplete observations. This work discusses different approaches for handling missing data, and performance of data-driven fault diagnosis schemes. An exploiting classifier and combined methods were assessed in Tennessee-Eastman process, for which diverse incomplete observations were produced. The use of several indicators revealed the trade-off between performances of the diff...
Citació
Askarian, M., Escudero, G., Graells, M., Zarghami, R., Jalali Farahani, F., Mostoufi, N. Fault diagnosis of chemical processes with incomplete observations: A comparative study. "Computers & chemical engineering", 04 Gener 2016, vol. 84, p. 104-116.
Paraules clau
Classification, Fault diagnosis, Imputation, Incomplete observations, Machine learning, Missing data, algorithms, classification, inference, information, issing data, pca, pls, soft sensors, tolerant control, values
Grup de recerca
CEPIMA - Center for Process and Environment Engineering
GPLN - Grup de Processament del Llenguatge Natural
IDEAI-UPC Intelligent Data Science and Artificial Intelligence
TALP - Centre de Tecnologies i Aplicacions del Llenguatge i la Parla

Participants

Arxius