Physics-Guided Deep Learning for Heat Pump Stress Detection

This paper presents a novel Physics-Guided Deep Neural Network (PG-DNN) approach for heat pump stress classification using the When2Heat dataset. The model integrates physics-guided feature selection and class definition with a deep neural network architecture.

Details

The paper presents a novel approach to heat pump stress detection using a Physics-Guided Deep Neural Network (PG-DNN). The method integrates physics-guided feature selection and class definition with a deep neural network architecture featuring 5 hidden layers and dual regularization strategies. The model was trained and evaluated on the When2Heat dataset, which contains 131,483 samples with 656 features across 26 European countries. The PG-DNN achieved 78.1% test accuracy and 78.5% validation accuracy, demonstrating significant improvements over baseline approaches (+5.0% over shallow networks, +4.0% over limited feature sets, and +2.0% over single regularization strategies). The researchers conducted comprehensive ablation studies to validate the effectiveness of the physics-guided feature selection, variable thresholding for realistic class distribution, and cross-country energy pattern analysis. The proposed system provides a production-ready solution for heat pump stress detection with 181,348 parameters and 720 seconds training time on AMD Ryzen 9 7950X with RTX 4080 hardware.