Loading...
Loading...

Go to the content (press return)

Data-based fault detection in chemical processes: Managing records with operator intervention and uncertain labels

Author
Askarian, M.; Benitez, R.; Graells, M.; Zarghami, R.
Type of activity
Journal article
Journal
Expert systems with applications
Date of publication
2016-06-23
Volume
63
First page
35
Last page
48
DOI
https://doi.org/10.1016/j.eswa.2016.06.040 Open in new window
Repository
http://hdl.handle.net/2117/97335 Open in new window
URL
http://www.sciencedirect.com/science/article/pii/S0957417416303219 Open in new window
Abstract
Developing data-driven fault detection systems for chemical plants requires managing uncertain data labels and dynamic attributes due to operator-process interactions. Mislabeled data is a known problem in computer science that has received scarce attention from the process systems community. This work introduces and examines the effects of operator actions in records and labels, and the consequences in the development of detection models. Using a state space model, this work proposes an iterati...
Citation
Askarian, M., Benitez, R., Graells, M., Zarghami, R. Data-based fault detection in chemical processes: Managing records with operator intervention and uncertain labels. "Expert systems with applications", 23 Juny 2016, vol. 63, p. 35-48.
Keywords
Interactive learning, Label noise, Mislabeling, Operational intelligence, Underlying states
Group of research
ANCORA - Anàlisi i control del ritme cardíac
CEPIMA - Centre d'Enginyeria de Processos i Medi Ambient
CREB - Biomedical Engineering Research Centre

Participants

Attachments