Engineering PapersSearch

DOE OSTI · 3017016

Deep learning–based digital twins for heat pumps

Abstract

Heat pumps are effective cooling and heating appliances to save energy in buildings. However, traditional heat pump models are challenging to integrate with building demands in a co-simulation environment because of the nonlinear thermodynamics of refrigerants. Developing digital twin representatives for heat pumps capable of faster calculations with good accuracy is desirable. This study aimed to establish a generic deep learning–based digital twin for heat pumps with a large amount of high-fidelity data. Two refrigerants for two different heat pumps were considered: an air source heat pump with refrigerant R-410A, an air source heat pump with refrigerant CO 2 , a water source heat pump with refrigerant R-410A, and a water source heat pump with refrigerant CO 2 . Furthermore, results showed that the deep learning (long short-term memory) models effectively represented these four heat pumps as a digital twin: (a) accuracy for training and testing showed smaller than 0.02 for heating electricity and heating demands, and (b) the digital twins showed good consistency with original data for heating electricity and heating demands (root mean square errors of less than 0.12 W and 0.19 W, respectively). Therefore, deep learning–based heat pump models can be used in the co-simulation of building mechanical systems.

Explore related subjects

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Li, Yanfei [Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)] (ORCID:0000000345220034), Sun, Jian [Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)] (ORCID:0000000302874302), Lian, Jamie [Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)] (ORCID:0000000312705350), Nawaz, Kashif [Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)] (ORCID:0000000251612491). 2026-01-23. Deep learning–based digital twins for heat pumps. https://doi.org/10.1016/j.enconman.2026.121112

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related reports

Heating performance of an air source heat pump with a portable thermoelectric subcooler

This study investigates the heating performance of an integrated air-source heat pump (ASHP) with a thermoelectric subcooler (TES) module, revealing significant performance enhancements, particularly in colder temperatures. Results show that adding the portable TES boosts the ASHP's heating capacity, making it feasible for residential applications. The coefficient of performance (COP) for the TE system, which is influenced by condensing temperatures and ambient conditions, ranges from 1.51 to 2.07. If condensing temperatures are consistently maintained above 35 °C, a TE COP of approximately 2.07 is achievable, supporting system downsizing and reducing supplemental heating. When coupled with an oversized indoor coil, the TES-ASHP system delivers comparable heating to a baseline unit while achieving a 10 % higher COP. Capacity increases by 8.7 %–24 % with TES in colder conditions, though COP declines by 9 %–18 %, diminishing as temperatures drop. Compared to systems with supplemental heating, this setup achieves a COP 10 %–17 % higher. Future work will involve extended field testing in various climates, exploration of advanced materials for thermal efficiency, and assessment of alternative refrigerants to improve performance and sustainability. This integrated ASHP-TES system holds promise for increased efficiency and reduced environmental impact in cold climates.

Air source heat pump