Por favor, use este identificador para citar o enlazar este ítem:http://uvadoc.uva.es/handle/10324/40565
Título
Machine learning and the digital era from a Process Systems Engineering perspective
Congreso
10th EUROSIM Congress on Modelling and Simulation
Año del Documento
2019
Editorial
ARGESIM
Descripción Física
12
Descripción
Producción Científica
Documento Fuente
Emilio Jiménez, Juan Ignacio Latorre (eds.), 10th EUROSIM Congress, La Rioja, Logroño, Spain, July 1-5, 2019
Abstract
Modern sensorization, communication and computational technolo-gies provide collecting and storing huge amounts of raw data from large cyber-physical systems. These data should serve as the basis to take better decisions at all levels (from the design to operation and management). Nevertheless, raw data needs to be transformed in useful information, usually in the form of prediction models. Machine learning plays thus a key role in this task. The process industry is not alien to this digital transformation, although large processing plants present particularities that differentiate them from other systems. These differences, if neglected, can make machine learning for general purpose fail in extracting the right information from data, leading thus to unreliable process models. As such models are the basis on which the ideas towards the cognitive plant rely, this issue is of key importance for a successful full digitalization of the process industry. Here we discuss these aspects, as well as the more suitable machine-learning ap-proaches, through our experience in an industrial case study.
Materias (normalizadas)
Modelling
Simulation
Machine learning
Palabras Clave
Data conditioning
Process modeling
Data reconciliation
Constrained regression
Grey-box models
ISBN
978-3-901608-92-6
DOI
Patrocinador
This research received funding from the EU Horizon 2020 research and innovation programme under Grant No. 723575 (CoPro) and from the Spanish MICINN with FEDER funds (PGC2018-099312-B-C31)
Patrocinador
info:eu-repo/grantAgreement/EC/H2020/723575
Idioma
eng
Tipo de versión
info:eu-repo/semantics/acceptedVersion
Derechos
openAccess
Collections
Files in this item
![CC0 1.0 Universal](/themes/Mirage2//images/creativecommons/cc-zero.png)