Next Article in Journal
Discharge-Based DC-Bus Voltage Link Capacitor Monitoring with Repetitive Recursive Least Squares Method for Hybrid-Electric Aircraft
Previous Article in Journal
Influence of Solar Radiation on the Thermal Load of an External Wall Taking into Account Its Material Properties
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

A Physics-Informed Variational Autoencoder for Modeling Power Plant Thermal Systems

Key Laboratory of Energy Thermal Conversion and Control of Ministry of Education, School of Energy and Environment, Southeast University, No.2 Sipailou, Nanjing 210096, China
*
Author to whom correspondence should be addressed.
Energies 2025, 18(17), 4742; https://doi.org/10.3390/en18174742
Submission received: 3 August 2025 / Revised: 30 August 2025 / Accepted: 4 September 2025 / Published: 5 September 2025
(This article belongs to the Section F5: Artificial Intelligence and Smart Energy)

Abstract

Data-driven models for complex thermal systems face two main challenges: a heavy dependence on high-quality training datasets and a “black-box” nature that makes it difficult to align model predictions with fundamental physical laws. To address these issues, this study introduces a novel physics-informed variational autoencoder (PI-VAE) framework for modeling thermal systems. The framework formalizes the mechanistic relationships among state parameters and establishes mathematical formulations for multi-level physical constraints. These constraints are integrated into the training loss function of the VAE as physical inconsistency losses, steering the model to comply with the system’s underlying physical principles. Additionally, a synthetic sample-generation strategy using latent variable sampling is introduced to improve the representation of physical constraints. The effectiveness of the proposed framework is validated through numerical simulations and an engineering case study. Simulation results indicate that as the complexity of embedded physical constraints increases, the test accuracy of the PI-VAE progressively improves, with R2 increasing from 0.902 (standard VAE) to 0.976. In modeling a high-pressure feedwater heater system in a thermal power plant, the PI-VAE model achieves high prediction accuracy while maintaining physical consistency under previously unseen operating conditions, thereby demonstrating superior generalization capability and interpretability.
Keywords: thermal system modeling; machine learning; physics-informed neural network; power plant; high-pressure feed water heater thermal system modeling; machine learning; physics-informed neural network; power plant; high-pressure feed water heater

Share and Cite

MDPI and ACS Style

Zhu, B.; Ren, S.; Weng, Q.; Si, F. A Physics-Informed Variational Autoencoder for Modeling Power Plant Thermal Systems. Energies 2025, 18, 4742. https://doi.org/10.3390/en18174742

AMA Style

Zhu B, Ren S, Weng Q, Si F. A Physics-Informed Variational Autoencoder for Modeling Power Plant Thermal Systems. Energies. 2025; 18(17):4742. https://doi.org/10.3390/en18174742

Chicago/Turabian Style

Zhu, Baoyu, Shaojun Ren, Qihang Weng, and Fengqi Si. 2025. "A Physics-Informed Variational Autoencoder for Modeling Power Plant Thermal Systems" Energies 18, no. 17: 4742. https://doi.org/10.3390/en18174742

APA Style

Zhu, B., Ren, S., Weng, Q., & Si, F. (2025). A Physics-Informed Variational Autoencoder for Modeling Power Plant Thermal Systems. Energies, 18(17), 4742. https://doi.org/10.3390/en18174742

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop