Research on COP Prediction Model of Chiller Based on PSO-SVR

Since the difficulty of building mechanism model and the structure of COP model of chiller is complex, greatly affected by operating parameter, a COP prediction model of chiller is proposed based on Support Vector Regression, and the parameters are optimized by Particle Swarm Optimization algorithm....

Full description

Saved in:
Bibliographic Details
Main Authors: Zhou Xuan, Cai Panpan, Lian Sizhen, Yan Junwei
Format: Article
Language:zho
Published: Journal of Refrigeration Magazines Agency Co., Ltd. 2015-01-01
Series:Zhileng xuebao
Subjects:
Online Access:http://www.zhilengxuebao.com/thesisDetails#10.3969/j.issn.0253-4339.2015.05.087
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850232857094520832
author Zhou Xuan
Cai Panpan
Lian Sizhen
Yan Junwei
author_facet Zhou Xuan
Cai Panpan
Lian Sizhen
Yan Junwei
author_sort Zhou Xuan
collection DOAJ
description Since the difficulty of building mechanism model and the structure of COP model of chiller is complex, greatly affected by operating parameter, a COP prediction model of chiller is proposed based on Support Vector Regression, and the parameters are optimized by Particle Swarm Optimization algorithm. In this paper, 396 sets of operating data of chiller of a shopping mall are randomly selected to train and test this model. The results shows that the prediction accuracy of SVR model based on PSO optimization algorithm is higher than that of BP neural network and the relative error is within 3%. At last, operating data of two days in summer and transition season are randomly selected to verify the model. The relative error is within 5%. So this model can provide theoretical basis for the chiller energy efficiency analysis, fault detection and diagnosis and optimizing control.
format Article
id doaj-art-82b17df3ac9c461abcc733a948d2e08e
institution OA Journals
issn 0253-4339
language zho
publishDate 2015-01-01
publisher Journal of Refrigeration Magazines Agency Co., Ltd.
record_format Article
series Zhileng xuebao
spelling doaj-art-82b17df3ac9c461abcc733a948d2e08e2025-08-20T02:03:04ZzhoJournal of Refrigeration Magazines Agency Co., Ltd.Zhileng xuebao0253-43392015-01-013666514560Research on COP Prediction Model of Chiller Based on PSO-SVRZhou XuanCai PanpanLian SizhenYan JunweiSince the difficulty of building mechanism model and the structure of COP model of chiller is complex, greatly affected by operating parameter, a COP prediction model of chiller is proposed based on Support Vector Regression, and the parameters are optimized by Particle Swarm Optimization algorithm. In this paper, 396 sets of operating data of chiller of a shopping mall are randomly selected to train and test this model. The results shows that the prediction accuracy of SVR model based on PSO optimization algorithm is higher than that of BP neural network and the relative error is within 3%. At last, operating data of two days in summer and transition season are randomly selected to verify the model. The relative error is within 5%. So this model can provide theoretical basis for the chiller energy efficiency analysis, fault detection and diagnosis and optimizing control.http://www.zhilengxuebao.com/thesisDetails#10.3969/j.issn.0253-4339.2015.05.087chillerCOPprediction modelsupport vector regressionparticle swarm optimization
spellingShingle Zhou Xuan
Cai Panpan
Lian Sizhen
Yan Junwei
Research on COP Prediction Model of Chiller Based on PSO-SVR
Zhileng xuebao
chiller
COP
prediction model
support vector regression
particle swarm optimization
title Research on COP Prediction Model of Chiller Based on PSO-SVR
title_full Research on COP Prediction Model of Chiller Based on PSO-SVR
title_fullStr Research on COP Prediction Model of Chiller Based on PSO-SVR
title_full_unstemmed Research on COP Prediction Model of Chiller Based on PSO-SVR
title_short Research on COP Prediction Model of Chiller Based on PSO-SVR
title_sort research on cop prediction model of chiller based on pso svr
topic chiller
COP
prediction model
support vector regression
particle swarm optimization
url http://www.zhilengxuebao.com/thesisDetails#10.3969/j.issn.0253-4339.2015.05.087
work_keys_str_mv AT zhouxuan researchoncoppredictionmodelofchillerbasedonpsosvr
AT caipanpan researchoncoppredictionmodelofchillerbasedonpsosvr
AT liansizhen researchoncoppredictionmodelofchillerbasedonpsosvr
AT yanjunwei researchoncoppredictionmodelofchillerbasedonpsosvr