prikaz prve stranice dokumenta Combining Deep Learning and the Heat Flux Method for In-Situ Thermal-Transmittance Measurement Improvement
  Preuzmi
PDF 5.82 MB
Znanstveni rad - Izvorni znanstveni rad
Combining Deep Learning and the Heat Flux Method for In-Situ Thermal-Transmittance Measurement Improvement
Energies (Basel), 15(14) (2022); 5029. urn:nbn:hr:237:268585
Gumbarević, Sanjin; Milovanović, Bojan; Dalbelo Bašić, Bojana; Gaši, Mergim

Institucijski repozitorij: Repozitorij Građevinskog fakulteta Sveučilišta u Zagrebu

Citirajte ovaj rad

Gumbarević, S., Milovanović, B., Dalbelo Bašić, B. i Gaši, M. (2022). Combining Deep Learning and the Heat Flux Method for In-Situ Thermal-Transmittance Measurement Improvement. Energies (Basel), 15(14).. Preuzeto s https://urn.nsk.hr/urn:nbn:hr:237:268585

Gumbarević, Sanjin, et al. "Combining Deep Learning and the Heat Flux Method for In-Situ Thermal-Transmittance Measurement Improvement." Energies (Basel), vol. 15(14), 2022. https://urn.nsk.hr/urn:nbn:hr:237:268585

Gumbarević, Sanjin, Bojan Milovanović, Bojana Dalbelo Bašić i Mergim Gaši. "Combining Deep Learning and the Heat Flux Method for In-Situ Thermal-Transmittance Measurement Improvement." Energies (Basel) 15(14) (2022). https://urn.nsk.hr/urn:nbn:hr:237:268585

Gumbarević, S., et al. (2022) 'Combining Deep Learning and the Heat Flux Method for In-Situ Thermal-Transmittance Measurement Improvement', Energies (Basel), 15(14). Preuzeto s: https://urn.nsk.hr/urn:nbn:hr:237:268585 (Datum pristupa: 05.10.2024.)

Gumbarević S, Milovanović B, Dalbelo Bašić B, Gaši M. Combining Deep Learning and the Heat Flux Method for In-Situ Thermal-Transmittance Measurement Improvement. Energies (Basel) [Internet]. 2022. [pristupljeno 05.10.2024.];15(14). Dostupno na: https://urn.nsk.hr/urn:nbn:hr:237:268585

S. Gumbarević, B. Milovanović, B. Dalbelo Bašić i M. Gaši, "Combining Deep Learning and the Heat Flux Method for In-Situ Thermal-Transmittance Measurement Improvement", Energies (Basel), vol. 15(14), 2022. [Online]. Dostupno na: https://urn.nsk.hr/urn:nbn:hr:237:268585. [Citirano: 05.10.2024.]

Za citiranje koristite ovu mrežnu adresu: https://urn.nsk.hr/urn:nbn:hr:237:268585
Podaci o radu
Naslov (engleski)Combining Deep Learning and the Heat Flux Method for In-Situ Thermal-Transmittance Measurement Improvement
AutorSanjin Gumbarević
AutorBojan Milovanović
AutorBojana Dalbelo Bašić
AutorMergim Gaši
Autorova ustanovaSveučilište u Zagrebu
Građevinski fakultet
Znanstveno / umjetničko
područje, polje i grana		TEHNIČKE ZNANOSTI
Građevinarstvo
Sažetak (engleski)
Transmission losses through the building envelope account for a large proportion of building energy balance. One of the most important parameters for determining transmission losses is thermal transmittance. Although thermal transmittance does not take into account dynamic parameters, it is traditionally the most commonly used estimation of transmission losses due to its simplicity and efficiency. It is challenging to estimate the thermal transmittance of an existing building element because thermal properties are commonly unknown or not all the layers that make up the element can be found due to technical-drawing information loss. In such cases, experimental methods are essential, the most common of which is the heat-flux method (HFM). One of the main drawbacks of the HFM is the long measurement duration. This research presents the application of deep learning on HFM results by applying long-short term memory units on temperature difference and measured heat flux. This deep-learning regression problem predicts heat flux after the applied model is properly trained on temperature-difference input, which is backpropagated by measured heat flux. The paper shows the performance of the developed procedure on real-size walls under the simulated environmental conditions, while the possibility of practical application is shown in pilot in-situ measurements.
Ključne riječi (engleski)
Jezikengleski
Vrsta publikacijeZnanstveni rad - Izvorni znanstveni rad
Status objaveObjavljen
Vrsta recenzijeRecenziran - međunarodna recenzija
Verzija publikacijeObjavljena verzija rada (izdavačev PDF)
Naslov časopisaEnergies (Basel)
Brojčani podacivol. 15(14), 5029
e-ISSN1996-1073
URN:NBNurn:nbn:hr:237:268585
Datum objave publikacije2022
Vrsta resursaTekst
Prava pristupaOtvoreni pristup
Uvjeti korištenjaIkona licence Zaštićeno autorskim pravom.
Datum i vrijeme pohrane2024-09-05 04:56:19