Mostra el registre d'ítem simple
Combining learning in model space fault diagnosis with data validation/reconstruction: Application to the Barcelona water network
dc.contributor.author | Quevedo Casín, Joseba Jokin |
dc.contributor.author | Chen, Heran |
dc.contributor.author | Cugueró Escofet, Miquel Àngel |
dc.contributor.author | Tino, Peter |
dc.contributor.author | Puig Cayuela, Vicenç |
dc.contributor.author | García Valverde, Diego |
dc.contributor.author | Sarrate Estruch, Ramon |
dc.contributor.author | Yao, Xin |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament d'Enginyeria de Sistemes, Automàtica i Informàtica Industrial |
dc.date.accessioned | 2014-05-21T14:31:01Z |
dc.date.available | 2014-05-21T15:10:15Z |
dc.date.created | 2014-02-14 |
dc.date.issued | 2014-02-14 |
dc.identifier.citation | Quevedo, J. [et al.]. Combining learning in model space fault diagnosis with data validation/reconstruction: Application to the Barcelona water network. "Engineering applications of artificial intelligence", 14 Febrer 2014, vol. 30, p. 18-29. |
dc.identifier.issn | 0952-1976 |
dc.identifier.uri | http://hdl.handle.net/2117/23031 |
dc.description.abstract | In this paper, an integrated data validation/reconstruction and fault diagnosis approach is proposed for critical infrastructure systems. The proposed methodology is implemented in a two-stage approach. In the first stage, sensor communication faults are detected and corrected, in order to facilitate a reliable dataset to perform system fault diagnosis in the second stage. On the one hand, sensor validation and reconstruction are based on the combined use of spatial and time series models. Spatial models take advantage of the (mass-balance) relation between different variables in the system, whilst time series models take advantage of the temporal redundancy of the measured variables by means of Holt-Winters time series models. On the other hand, fault diagnosis is based on the learning-in-model-space approach that is implemented by fitting a series of models using a series of signal segments selected with a sliding window. In this way, each signal segment can be represented by one model. To rigorously measure the ‘distance’ between models, the distance in the model space is defined. The deterministic reservoir computing approach is used to approximate a model with the input–output dynamics that exploits spatial–temporal correlations existing in the original data. Finally, the proposed approach is successfully applied to the Barcelona water network. |
dc.format.extent | 12 p. |
dc.language.iso | eng |
dc.subject | Àrees temàtiques de la UPC::Informàtica::Automàtica i control |
dc.subject.lcsh | Diagnostic errors |
dc.subject.lcsh | Automatic control |
dc.subject.lcsh | Time-series analysis |
dc.subject.other | Learning in model space |
dc.subject.other | Sensor data validation/reconstruction |
dc.subject.other | Time series |
dc.subject.other | Fault diagnosis |
dc.subject.other | Reservoir computing |
dc.title | Combining learning in model space fault diagnosis with data validation/reconstruction: Application to the Barcelona water network |
dc.type | Article |
dc.subject.lemac | Errors de diagnòstic |
dc.subject.lemac | Control automàtic |
dc.subject.lemac | Sèries temporals--Anàlisi |
dc.contributor.group | Universitat Politècnica de Catalunya. SAC - Sistemes Avançats de Control |
dc.contributor.group | Universitat Politècnica de Catalunya. SIC - Sistemes Intel·ligents de Control |
dc.identifier.doi | 10.1016/j.engappai.2014.01.008 |
dc.description.peerreviewed | Peer Reviewed |
dc.rights.access | Restricted access - publisher's policy |
local.identifier.drac | 14127553 |
dc.description.version | Postprint (published version) |
dc.relation.projectid | info:eu-repo/grantAgreement/EC/FP7/270428/EU/Making Sense of Nonsense/ISENSE |
dc.date.lift | 10000-01-01 |
local.citation.author | Quevedo, J.; Chen, H.; Cuguero, M.; Tino, P.; Puig, V.; Garcia, D.; Sarrate, R.; Yao, X. |
local.citation.publicationName | Engineering applications of artificial intelligence |
local.citation.volume | 30 |
local.citation.startingPage | 18 |
local.citation.endingPage | 29 |
Fitxers d'aquest items
Aquest ítem apareix a les col·leccions següents
-
Articles de revista [133]
-
Articles de revista [1.391]
-
Articles de revista [507]