Zhixuan Fan , Yanqiang Di , Yafeng Gao , Qiulei Zhang , Lina Jiang , Shiqian Dong , Hongbo Chen , Yuanyang Li , Mingwen Luo
{"title":"Multi-output model of medium-temperature chillers for digital twins: A comparative study of steady-state and dynamic modeling approaches","authors":"Zhixuan Fan , Yanqiang Di , Yafeng Gao , Qiulei Zhang , Lina Jiang , Shiqian Dong , Hongbo Chen , Yuanyang Li , Mingwen Luo","doi":"10.1016/j.apenergy.2025.126397","DOIUrl":null,"url":null,"abstract":"<div><div>Chiller modeling is essential for ensuring efficient chiller operation. The existing chiller models are mostly single-output steady-state models that cannot accurately capture the dynamic behavior of chillers and cannot meet the needs of digital twins. In this work, a multi-output model framework was proposed to facilitate the development of a digital twin chiller. Subsequently, three steady-state and three dynamic chiller models were developed based on a medium-temperature case. The hyperparameters of the six candidate models were optimized. To systematically evaluate model suitability, we introduced two novel metrics: the univariate error, which quantifies prediction accuracy for individual variables, and the model overall error, which aggregates errors across all variables to assess comprehensive performance. A comparative analysis was then conducted to contrast the best steady-state and dynamic models, evaluating their overall error and dynamic responsiveness. The study results show that: The chiller power consumption of all models exhibit the lowest prediction accuracy, followed by evaporator outlet water temperature and condenser outlet water temperature. The support vector regression (SVR) model is the best of the steady state models with model overall error of 10.84 %, and the gate recurrent unit (GRU) model is the best of the steady state models with model overall error of 3.67 %. Notably, the GRU model demonstrates superior accuracy in predicting evaporator outlet temperature(<span><math><msub><mi>T</mi><mi>eo</mi></msub></math></span>), condenser outlet temperature(<span><math><msub><mi>T</mi><mi>co</mi></msub><mo>)</mo></math></span> and chiller power consumption(<span><math><mi>P</mi><mo>)</mo></math></span> and better captured transient fluctuations in these variables during chiller start-up and load changes compared with the SVR model. The findings provide a methodological foundation for developing digital twin models and optimizing intelligent operation/maintenance strategies for chillers.</div></div>","PeriodicalId":246,"journal":{"name":"Applied Energy","volume":"397 ","pages":"Article 126397"},"PeriodicalIF":11.0000,"publicationDate":"2025-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Applied Energy","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0306261925011274","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENERGY & FUELS","Score":null,"Total":0}
引用次数: 0
Abstract
Chiller modeling is essential for ensuring efficient chiller operation. The existing chiller models are mostly single-output steady-state models that cannot accurately capture the dynamic behavior of chillers and cannot meet the needs of digital twins. In this work, a multi-output model framework was proposed to facilitate the development of a digital twin chiller. Subsequently, three steady-state and three dynamic chiller models were developed based on a medium-temperature case. The hyperparameters of the six candidate models were optimized. To systematically evaluate model suitability, we introduced two novel metrics: the univariate error, which quantifies prediction accuracy for individual variables, and the model overall error, which aggregates errors across all variables to assess comprehensive performance. A comparative analysis was then conducted to contrast the best steady-state and dynamic models, evaluating their overall error and dynamic responsiveness. The study results show that: The chiller power consumption of all models exhibit the lowest prediction accuracy, followed by evaporator outlet water temperature and condenser outlet water temperature. The support vector regression (SVR) model is the best of the steady state models with model overall error of 10.84 %, and the gate recurrent unit (GRU) model is the best of the steady state models with model overall error of 3.67 %. Notably, the GRU model demonstrates superior accuracy in predicting evaporator outlet temperature(), condenser outlet temperature( and chiller power consumption( and better captured transient fluctuations in these variables during chiller start-up and load changes compared with the SVR model. The findings provide a methodological foundation for developing digital twin models and optimizing intelligent operation/maintenance strategies for chillers.
期刊介绍:
Applied Energy serves as a platform for sharing innovations, research, development, and demonstrations in energy conversion, conservation, and sustainable energy systems. The journal covers topics such as optimal energy resource use, environmental pollutant mitigation, and energy process analysis. It welcomes original papers, review articles, technical notes, and letters to the editor. Authors are encouraged to submit manuscripts that bridge the gap between research, development, and implementation. The journal addresses a wide spectrum of topics, including fossil and renewable energy technologies, energy economics, and environmental impacts. Applied Energy also explores modeling and forecasting, conservation strategies, and the social and economic implications of energy policies, including climate change mitigation. It is complemented by the open-access journal Advances in Applied Energy.