Neural network modelling of thermal stratification in a solar DHW storage

P. Géczy-Víg, I. Farkas

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

In this study an artificial neural network (ANN) model is introduced for modelling the layer temperatures in a storage tank of a solar thermal system. The model is based on the measured data of a domestic hot water system. The temperatures distribution in the storage tank divided in 8 equal parts in vertical direction were calculated every 5 min using the average 5 min data of solar radiation, ambient temperature, mass flow rate of collector loop, load and the temperature of the layers in previous time steps. The introduced ANN model consists of two parts describing the load periods and the periods between the loads. The identified model gives acceptable results inside the training interval as the average deviation was 0.22 °C during the training and 0.24 °C during the validation.

Original languageEnglish
Pages (from-to)801-806
Number of pages6
JournalSolar Energy
Volume84
Issue number5
DOIs
Publication statusPublished - May 2010

Fingerprint

Thermal stratification
Neural networks
Solar radiation
Temperature
Temperature distribution
Flow rate
Water

Keywords

  • Modelling
  • Neural network
  • Solar thermal system
  • Thermal stratification
  • Water load

ASJC Scopus subject areas

  • Renewable Energy, Sustainability and the Environment
  • Materials Science(all)

Cite this

Neural network modelling of thermal stratification in a solar DHW storage. / Géczy-Víg, P.; Farkas, I.

In: Solar Energy, Vol. 84, No. 5, 05.2010, p. 801-806.

Research output: Contribution to journalArticle

@article{cb8cda5d9d3a4b88be0d6243b6b60788,
title = "Neural network modelling of thermal stratification in a solar DHW storage",
abstract = "In this study an artificial neural network (ANN) model is introduced for modelling the layer temperatures in a storage tank of a solar thermal system. The model is based on the measured data of a domestic hot water system. The temperatures distribution in the storage tank divided in 8 equal parts in vertical direction were calculated every 5 min using the average 5 min data of solar radiation, ambient temperature, mass flow rate of collector loop, load and the temperature of the layers in previous time steps. The introduced ANN model consists of two parts describing the load periods and the periods between the loads. The identified model gives acceptable results inside the training interval as the average deviation was 0.22 °C during the training and 0.24 °C during the validation.",
keywords = "Modelling, Neural network, Solar thermal system, Thermal stratification, Water load",
author = "P. G{\'e}czy-V{\'i}g and I. Farkas",
year = "2010",
month = "5",
doi = "10.1016/j.solener.2010.02.003",
language = "English",
volume = "84",
pages = "801--806",
journal = "Solar Energy",
issn = "0038-092X",
publisher = "Elsevier Limited",
number = "5",

}

TY - JOUR

T1 - Neural network modelling of thermal stratification in a solar DHW storage

AU - Géczy-Víg, P.

AU - Farkas, I.

PY - 2010/5

Y1 - 2010/5

N2 - In this study an artificial neural network (ANN) model is introduced for modelling the layer temperatures in a storage tank of a solar thermal system. The model is based on the measured data of a domestic hot water system. The temperatures distribution in the storage tank divided in 8 equal parts in vertical direction were calculated every 5 min using the average 5 min data of solar radiation, ambient temperature, mass flow rate of collector loop, load and the temperature of the layers in previous time steps. The introduced ANN model consists of two parts describing the load periods and the periods between the loads. The identified model gives acceptable results inside the training interval as the average deviation was 0.22 °C during the training and 0.24 °C during the validation.

AB - In this study an artificial neural network (ANN) model is introduced for modelling the layer temperatures in a storage tank of a solar thermal system. The model is based on the measured data of a domestic hot water system. The temperatures distribution in the storage tank divided in 8 equal parts in vertical direction were calculated every 5 min using the average 5 min data of solar radiation, ambient temperature, mass flow rate of collector loop, load and the temperature of the layers in previous time steps. The introduced ANN model consists of two parts describing the load periods and the periods between the loads. The identified model gives acceptable results inside the training interval as the average deviation was 0.22 °C during the training and 0.24 °C during the validation.

KW - Modelling

KW - Neural network

KW - Solar thermal system

KW - Thermal stratification

KW - Water load

UR - http://www.scopus.com/inward/record.url?scp=77949912761&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77949912761&partnerID=8YFLogxK

U2 - 10.1016/j.solener.2010.02.003

DO - 10.1016/j.solener.2010.02.003

M3 - Article

AN - SCOPUS:77949912761

VL - 84

SP - 801

EP - 806

JO - Solar Energy

JF - Solar Energy

SN - 0038-092X

IS - 5

ER -