FN ISI Export Format VR 1.0 PT J AU Sedano, J Corchado, E Curiel, L Villar, JR de la Cal, E AF Sedano, Javier Corchado, Emilio Curiel, Leticia Ramon Villar, Jose de la Cal, Enrique TI DETECTION OF HEAT FLUX FAILURES IN BUILDING USING A SOFT COMPUTING DIAGNOSTIC SYSTEM SO NEURAL NETWORK WORLD LA English DT Article DE Computational intelligence; soft computing; identification systems; artificial neural networks; non-linear systems; energetic efficiency ID INFRARED THERMOGRAPHY; THERMAL INSULATION; PROJECTION PURSUIT; MISSING VALUES; IDENTIFICATION; ALGORITHM; MAXIMUM; SPACE; MODEL AB The detection of insulation failures in buildings could potentially conserve energy supplies and improve future designs. Improvements to thermal insulation in buildings include the development of models to assess fabric gain -heat flux through exterior walls in the building- and heating processes. Thermal insulation standards are now contractual obligations in new buildings, and the energy efficiency of buildings constructed prior to these regulations has yet to be determined. The main assumption is that it will be based on heat flux and conductivity measurement. Diagnostic systems to detect thermal insulation failures should recognize anomalous situations in a building that relate to insulation, heating and ventilation. This highly relevant issue in the construction sector today is approached through a novel intelligent procedure that can be programmed according to local building and heating system regulations and the specific features of a given climate zone. It is based on the following phases. Firstly, the dynamic thermal performance of different variables is specifically modeled. Secondly, an exploratory projection pursuit method called Cooperative Maximum-Likelihood Hebbian Learning extracts the relevant features. Finally, a supervised neural model and identification techniques constitute the model for the diagnosis of thermal insulation failures in building due to the heat flux through exterior walls, using relevant features of the data set. The reliability of the proposed method is validated with real datasets from several Spanish cities in winter time. C1 [Sedano, Javier] Technol Inst Castilla & Leon, Dept Artificial Intelligence & Appl Elect, Burgos 09001, Spain. [Corchado, Emilio] Univ Salamanca, Dept Informat & Automat, E-37008 Salamanca, Spain. [Curiel, Leticia] Univ Burgos, EPS Politecn, Dept Civil Engn, Burgos 09001, Spain. [Ramon Villar, Jose; de la Cal, Enrique] Univ Oviedo, Dept Comp Sci, Gijon 33204, Spain. RP Sedano, J, Technol Inst Castilla & Leon, Dept Artificial Intelligence & Appl Elect, C Lopez Bravo 70, Burgos 09001, Spain. EM javier.sedano@itcl.es escorchado@usal.es lcuriel@ubu.es villarjose@uniovi.es delacal@uniovi.es FU Junta of Castilla and Leon (JCyL) [BU006A08]; Spanish Ministry of Science and Innovation [TIN2010-21272-C02-01]; Spanish Ministry and Innovation [PID 560300-2009-11]; Spanish Ministry of Education and Innovation [CIT-020000-2008-2, CIT-020000-2009-12]; Spanish Ministry of Science and Technology [TIN2008-06681-006-04]; Grupo Antolin Ingenieria, S.A. [MAGNO2008 - 1028]; Government Ministry FX We would like to extend our thanks to PhD. Magnus Norgaard for his freeware version of Mat lab Neural Network Based System Identification Toolbox. This research has been partially supported through projects of the Junta of Castilla and Leon (JCyL): [BU006A08], TIN2010-21272-C02-01 from the Spanish Ministry of Science and Innovation, the project of the Spanish Ministry and Innovation [PID 560300-2009-11], the project of the Spanish Ministry of Education and Innovation [CIT-020000-2008-2] and [CIT-020000-2009-12], the project of the Spanish Ministry of Science and Technology [TIN2008-06681-006-04] and Grupo Antolin Ingenieria, S.A., within the framework of project MAGNO2008 - 1028.- CENIT, also funded by the same Government Ministry. NR 51 TC 1 PU ACAD SCIENCES CZECH REPUBLIC, INST COMPUTER SCIENCE PI 182 07 PRAGUE 8 PA POD VODARENSKOU VEZI 2, 182 07 PRAGUE 8, 00000, CZECH REPUBLIC SN 1210-0552 J9 NEURAL NETW WORLD JI Neural Netw. World PY 2010 VL 20 IS 7 SI Sp. Iss. SI BP 883 EP 898 PG 16 SC Computer Science, Artificial Intelligence GA 727FO UT ISI:000287783300007 ER EF