表紙画像

Physics-Informed Neural Networks for Parameter Identification of Equivalent Thermal Parameters in Residential Buildings During Winter Electric Heating

保存先:
出版年:Processes vol. 13, no. 9 (2025), p. 2860-2872
第一著者: Liu, Sijia
その他の著者: An, Qi, Yuan Ziyi, Pengchao, Lei
出版事項:
MDPI AG
主題:
Energy management
Accuracy
Regression analysis
Parameter identification
Optimization techniques
Equivalence
Thermodynamic properties
Residential buildings
Heuristic
Heuristic methods
Efficiency
Heat transfer
Residential energy
Data integrity
Physics
Neural networks
Inverse problems
Temperature
Winter
Electric heating
Problem solving
Learning
Statistical methods
Computing time
オンライン･アクセス:Citation/Abstract
Full Text + Graphics
Full Text - PDF
タグ: タグ追加
タグなし, このレコードへの初めてのタグを付けませんか!
抄録:Accurate identification of equivalent thermal parameters (ETPs) is crucial for optimizing energy efficiency in residential buildings during winter electric heating. This study proposes a physics-informed neural network (PINN) approach to estimate ETP model parameters, integrating physical constraints with data-driven learning to enhance robustness. The method is validated using real-world measurements from seven rural residences, with indoor and outdoor temperatures and heating power sampled every 15 min. The PINN is compared with linear regression (LR), heuristic methods (GA, PSO, TROA), and data-driven methods (RF, XGBoost, LSTM). The results show that the PINN reduces MAE by over 90% compared to LR, 42% compared to heuristic methods, and 75% compared to pure data-driven methods, with similar improvements in RMSE and MAPE, while maintaining moderate computational time. This work highlights the potential of PINNs as an efficient and reliable tool for building energy management, offering a promising solution for parameter identification within the specific context of the studied residences, with future work needed to confirm scalability across diverse climates and building types.
ISSN:2227-9717
DOI:10.3390/pr13092860
ソース:Materials Science Database