Numerically Trained Artificial Neural Network for Experimental Performance Prediction of Air Conditioning Systems

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper presents the development of a method for predicting the performance of air conditioning systems using few accessible and inexpensive input parameters. The cooling capacity is predicted using artificial neural network with four selected refrigerant temperatures measured from the outdoor unit as the inputs. Input output prediction data are obtained numerically and experimentally from two representative variable refrigerant flow (VRF) systems. The two systems have different characteristics and nominal capacity. The training of the ANN model is conducted with the data obtained from numerical simulations. Consequently, the ANN is tested for the prediction of the experimental cooling capacity in a quasi-certified testing equipment. The results indicate that the proposed performance prediction method demonstrates a relative error lower than 10%.

Original languageEnglish
Title of host publication2021 60th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1432-1436
Number of pages5
ISBN (Electronic)9784907764739
Publication statusPublished - 2021 Sep 8
Event60th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2021 - Tokyo, Japan
Duration: 2021 Sep 82021 Sep 10

Publication series

Name2021 60th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2021

Conference

Conference60th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2021
Country/TerritoryJapan
CityTokyo
Period21/9/821/9/10

Keywords

  • Air conditioning
  • Cooling capacity
  • Neural network
  • Refrigerant temperatures

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Control and Optimization
  • Instrumentation

Fingerprint

Dive into the research topics of 'Numerically Trained Artificial Neural Network for Experimental Performance Prediction of Air Conditioning Systems'. Together they form a unique fingerprint.

Cite this