Please use this identifier to cite or link to this item:
Title: Steady-state operating performance modelling and prediction for a direct expansion air conditioning system using artificial neural network
Authors: Li, N
Xia, L
Deng, S 
Xu, X
Chan, MY 
Issue Date: 2012
Source: Building services engineering research and technology, 2012, v. 33, no. 3, p. 281-292
Abstract: A two-in two-out steady-state artificial neural network (ANN)-based model for an experimental variable speed direct expansion (DX) air conditioning (A/C) system has been developed for simulating its total output cooling capacity and equipment sensible heat ratio under different combinations of compressor and supply fan speeds. Experiments were carried out, and totally 169 sets of experimental data were obtained for ANN training and testing. An ANN-based model having the configuration of 2 neurons in the input layer, 2 neurons in the output layer and 6 neurons in each of the 2 hidden layers, i.e. 2-6-6-2 configuration, was thus developed. The ANN-based model developed can be used to predict the operating performance of the DX A/C system with a higher accuracy. It is expected that the model developed can help design a multivariable-input multivariable-output strategy to simultaneously control indoor air temperature and humidity.Practical applications: The work reported in this paper demonstrates that the operating performance of a DX A/C system under different compressor and supply fan speeds can well be represented using ANN model technique, as an alternative to traditional physical-based modelling techniques, with a higher predicting accuracy and less computational effort. The ANN-based model for the DX A/C system is expected to be very useful in developing an efficient control algorithm for simultaneous indoor temperature and humidity using the ANN technique.
Publisher: SAGE Publications
Journal: Building services engineering research and technology 
ISSN: 0143-6244
EISSN: 1477-0849
DOI: 10.1177/0143624411408802
Appears in Collections:Journal/Magazine Article

View full-text via PolyU eLinks SFX Query
Show full item record


Last Week
Last month
Citations as of Sep 6, 2020


Last Week
Last month
Citations as of Sep 26, 2020

Page view(s)

Last Week
Last month
Citations as of Sep 28, 2020

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.