Dynamic indoor thermal comfort model identification based on neural computing PMV index

This paper focuses on modelling and simulation of building dynamic thermal comfort control for non-linear HVAC system. Thermal comfort in general refers to temperature and also humidity. However in reality, temperature or humidity is just one of the factors affecting the thermal comfort but not the...

Full description

Bibliographic Details
Main Authors: Sahari, K.S.M., Jalal, M.F.A., Homod, R.Z., Eng, Y.K.
Format: Article
Language:English
Published: 2018
id uniten-123456789-6989
recordtype eprints
spelling uniten-123456789-69892018-01-23T03:48:12Z Dynamic indoor thermal comfort model identification based on neural computing PMV index Sahari, K.S.M. Jalal, M.F.A. Homod, R.Z. Eng, Y.K. This paper focuses on modelling and simulation of building dynamic thermal comfort control for non-linear HVAC system. Thermal comfort in general refers to temperature and also humidity. However in reality, temperature or humidity is just one of the factors affecting the thermal comfort but not the main measures. Besides, as HVAC control system has the characteristic of time delay, large inertia, and highly nonlinear behaviour, it is difficult to determine the thermal comfort sensation accurately if we use traditional Fanger's PMV index. Hence, Artificial Neural Network (ANN) has been introduced due to its ability to approximate any nonlinear mapping. Using ANN to train, we can get the input-output mapping of HVAC control system or in other word; we can propose a practical approach to identify thermal comfort of a building. Simulations were carried out to validate and verify the proposed method. Results show that the proposed ANN method can track down the desired thermal sensation for a specified condition space. © Published under licence by IOP Publishing Ltd. 2018-01-11T08:27:45Z 2018-01-11T08:27:45Z 2013 Article 10.1088/1755-1315/16/1/012113 en
repository_type Digital Repository
institution_category Local University
institution Universiti Tenaga Nasional
building UNITEN Institutional Repository
collection Online Access
language English
description This paper focuses on modelling and simulation of building dynamic thermal comfort control for non-linear HVAC system. Thermal comfort in general refers to temperature and also humidity. However in reality, temperature or humidity is just one of the factors affecting the thermal comfort but not the main measures. Besides, as HVAC control system has the characteristic of time delay, large inertia, and highly nonlinear behaviour, it is difficult to determine the thermal comfort sensation accurately if we use traditional Fanger's PMV index. Hence, Artificial Neural Network (ANN) has been introduced due to its ability to approximate any nonlinear mapping. Using ANN to train, we can get the input-output mapping of HVAC control system or in other word; we can propose a practical approach to identify thermal comfort of a building. Simulations were carried out to validate and verify the proposed method. Results show that the proposed ANN method can track down the desired thermal sensation for a specified condition space. © Published under licence by IOP Publishing Ltd.
format Article
author Sahari, K.S.M.
Jalal, M.F.A.
Homod, R.Z.
Eng, Y.K.
spellingShingle Sahari, K.S.M.
Jalal, M.F.A.
Homod, R.Z.
Eng, Y.K.
Dynamic indoor thermal comfort model identification based on neural computing PMV index
author_facet Sahari, K.S.M.
Jalal, M.F.A.
Homod, R.Z.
Eng, Y.K.
author_sort Sahari, K.S.M.
title Dynamic indoor thermal comfort model identification based on neural computing PMV index
title_short Dynamic indoor thermal comfort model identification based on neural computing PMV index
title_full Dynamic indoor thermal comfort model identification based on neural computing PMV index
title_fullStr Dynamic indoor thermal comfort model identification based on neural computing PMV index
title_full_unstemmed Dynamic indoor thermal comfort model identification based on neural computing PMV index
title_sort dynamic indoor thermal comfort model identification based on neural computing pmv index
publishDate 2018
first_indexed 2018-09-05T07:49:55Z
last_indexed 2018-09-05T07:49:55Z
_version_ 1610753031225212928