Computational BIM and Intelligent Operations

Hybrid Approach for Digital Twins in the Built Environment

Yu-Wen Lin, Tsz Ling Elaine Tang, Costas J. Spanos

Published 2021

Thumbnail for Hybrid Approach for Digital Twins in the Built Environment
📄 Paper
In recent years, several countries have created policies to enforce Zero Energy Building (ZEB) standards for new building construction. Achieving this for new buildings is feasible, but it may be difficult to transform existing buildings to ZEBs. Digital twins provide a promising approach to monitor existing buildings and further increase their energy efficiency. A digital twin (DT) is a virtual representation of a physical entity. It has several applications in product design, product cycle, and fault detection. This paper presents a hybrid approach that combines physics-based and machine learning methods to create a DT for the built environment. A case study for a digital twin of a single room is also discussed. The initial comparison of cooling energy between the physical testbed and the DT model shows promising results for future development. The limitations, challenges, and future development of the approach are also addressed in the paper.

Abstract

In recent years, several countries have created policies to enforce Zero Energy Building (ZEB) standards for new building construction. Achieving this for new buildings is feasible, but it may be difficult to transform existing buildings to ZEBs. Digital twins provide a promising approach to monitor existing buildings and further increase their energy efficiency. A digital twin (DT) is a virtual representation of a physical entity. It has several applications in product design, product cycle, and fault detection. This paper presents a hybrid approach that combines physics-based and machine learning methods to create a DT for the built environment. A case study for a digital twin of a single room is also discussed. The initial comparison of cooling energy between the physical testbed and the DT model shows promising results for future development. The limitations, challenges, and future development of the approach are also addressed in the paper.

Topics

AI building automationAI for Energy Performance OptimizationPredictive Analytics and Performance OptimizationQuality Control and ValidationSmart Building Systems and IoT Integrationbig data in buildingsbuilding energy forecastingbuilding energy simulationbuilding performance dashboarddigital twinspredictive analyticssensor data integration

Cite this paper

@inproceedings{a5679725,
author = {Lin, Yu-Wen and Tang, Tsz Ling Elaine and Spanos, Costas J.},
title = {Hybrid Approach for Digital Twins in the Built Environment},
year = {2021},
isbn = {9781450383332},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3447555.3466585},
doi = {10.1145/3447555.3466585},
abstract = {In recent years, several countries have created policies to enforce Zero Energy Building (ZEB) standards for new building construction. Achieving this for new buildings is feasible, but it may be difficult to transform existing buildings to ZEBs. Digital twins provide a promising approach to monitor existing buildings and further increase their energy efficiency. A digital twin (DT) is a virtual representation of a physical entity. It has several applications in product design, product cycle, and fault detection. This paper presents a hybrid approach that combines physics-based and machine learning methods to create a DT for the built environment. A case study for a digital twin of a single room is also discussed. The initial comparison of cooling energy between the physical testbed and the DT model shows promising results for future development. The limitations, challenges, and future development of the approach are also addressed in the paper.},
booktitle = {Proceedings of the Twelfth ACM International Conference on Future Energy Systems},
pages = {450–457},
numpages = {8},
keywords = {hybrid models, digital twin, building modeling},
location = {Virtual Event, Italy},
series = {e-Energy '21}
}