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

Baoyu Zhu, Shaojun Ren, Qihang Weng and Fengqi Si ()
Additional contact information
Baoyu Zhu: 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
Shaojun Ren: 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
Qihang Weng: 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
Fengqi Si: 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

Energies, 2025, vol. 18, issue 17, 1-24

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 R 2 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 (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/18/17/4742/pdf (application/pdf)
https://www.mdpi.com/1996-1073/18/17/4742/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:18:y:2025:i:17:p:4742-:d:1743201

Access Statistics for this article

Energies is currently edited by Ms. Cassie Shen

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().