Share

IIR document

A novel physics-guided collaborative modeling method for steady-state simulation of air source heat pump system.

Author(s) : SHAN L., WU Q., WANG M., ZHANG H., LI W., GUO Y., SHAO S., CHEN Z., LIANG Y.

Type of article: IJR article

Summary

It is vital to develop steady-state simulation models for optimizing the design and control of air source heat pump (ASHP) systems. However, existing ASHP modeling methods still face challenges in balancing computational efficiency, high accuracy, and robustness. Therefore, a physics-guided collaborative modeling (PGCM) method is proposed to enhance ASHP simulation. Firstly, a heat exchanger physics-informed neural network (HX-PINN) is established to capture nonlinear relationships in heat transfer processes. Secondly, the coupling residual of thermodynamic cycle is introduced to construct the system-level solver. Finally, a comprehensive validation of the HX-PINN model and PGCM-based system model are conducted under a wide range of operation conditions. Results indicate that the HX-PINN model effectively captures nonlinear relationships in heat transfer processes under small data sample conditions, and the prediction accuracy of pressure drop and enthalpy change in the testing set achieves 99.3 % and 98.5 %, respectively. Furthermore, the PGCM-based system model reduces computational time of the physical baseline model by 86.9 %-95.2 % while maintaining a COP mean absolute percentage error of 1.5 %. The proposed PGCM method improves the reliability of data-driven models for ASHP control optimization.

Available documents

Format PDF

Pages: 15 p.

Available

  • Public price

    20 €

  • Member price*

    Free

* Best rate depending on membership category (see the detailed benefits of individual and corporate memberships).

Details

  • Original title: A novel physics-guided collaborative modeling method for steady-state simulation of air source heat pump system.
  • Record ID : 30034477
  • Languages: English
  • Subject: Technology
  • Source: International Journal of Refrigeration - Revue Internationale du Froid - vol. 181
  • Publication date: 2026/01
  • DOI: http://dx.doi.org/10.1016/j.ijrefrig.2025.10.026

Links


See other articles in this issue (33)
See the source

Indexing