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

Sholahudin, Niccolo Giannetti, Yoichi Miyaoka, Jeongsoo Jeong, Kiyoshi Saito

研究成果: Conference contribution

抄録

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%.

本文言語English
ホスト出版物のタイトル2021 60th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2021
出版社Institute of Electrical and Electronics Engineers Inc.
ページ1432-1436
ページ数5
ISBN(電子版)9784907764739
出版ステータスPublished - 2021 9月 8
イベント60th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2021 - Tokyo, Japan
継続期間: 2021 9月 82021 9月 10

出版物シリーズ

名前2021 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
国/地域Japan
CityTokyo
Period21/9/821/9/10

ASJC Scopus subject areas

  • 人工知能
  • コンピュータ サイエンスの応用
  • 制御と最適化
  • 器械工学

フィンガープリント

「Numerically Trained Artificial Neural Network for Experimental Performance Prediction of Air Conditioning Systems」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル