dc.contributor
Universitat Politècnica de Catalunya. Departament d'Enginyeria de Sistemes, Automàtica i Informàtica Industrial
dc.contributor
Universitat Politècnica de Catalunya. SAC - Sistemes Avançats de Control
dc.contributor.author
Akielaszek-Witczak, Anna
dc.contributor.author
Mrugalska, Beata
dc.contributor.author
Puig Cayuela, Vicenç
dc.contributor.author
Wyrwicka, Magdalena
dc.identifier
Akielaszek-Witczak, A., Mrugalska, B., Puig, V., Wyrwicka, M. Robust neural-network-based fault detection with sequential D-optimum bounded-error input design. A: IFAC Symposium on Fault Detection, Supervision and Safety of Technical Processes. "IFAC-PapersOnLine (volume 48, issue 21, Pages 1-1496): 9th IFAC Symposium on Fault Detection, Supervision and Safety for Technical Processes SAFEPROCESS 2015 Paris, 2–4 September 2015". París: International Federation of Automatic Control (IFAC), 2015, p. 434-439.
dc.identifier
https://hdl.handle.net/2117/82806
dc.identifier
10.1016/j.ifacol.2015.09.565
dc.description.abstract
A growing demand for technologically advanced systems has contributed to the increase of the awareness of systems safety and reliability. Such a situation requires the development of novel methods of robust fault diagnosis. The application of the analytical redundancy based methods for system fault detection causes that theIr effectiveness depends on model quality. In this paper, a new Methodology for the improvement of the neural model with a D-optimum sequential experimental design technique combined with outer bounding ellipsoid algorithm is proposed. Moreover, a novel method of robust fault detection against neural model uncertainty and disturbances is developed. Such an approach is used for modelling and robust fault detection of the three-screw spindle oil pump.
dc.description.abstract
Postprint (author's final draft)
dc.format
application/pdf
dc.publisher
International Federation of Automatic Control (IFAC)
dc.rights
Restricted access - publisher's policy
dc.subject
Àrees temàtiques de la UPC::Informàtica
dc.subject
Neural networks (Computer science)
dc.subject
Robust control
dc.subject
Neural networks
dc.subject
system identification
dc.subject
optimum experiment design
dc.subject
fault
detection
dc.subject
bounded disturbances
dc.subject
Xarxes neuronals (Informàtica)
dc.subject
Control de robustesa
dc.title
Robust neural-network-based fault detection with sequential D-optimum bounded-error input design
dc.type
Conference report
