CoChat
Sign Up
Cited by 58Model Reduction and Neural NetworksHeat Transfer and Numerical MethodsAdvanced Battery Technologies Research

Physics-Informed Neural Networks for Advanced Thermal Management in Electronics and Battery Systems: A Review of Recent Developments and Future Prospects

Open access
Du, Zichen, Lu, Renhao·2025·Batteries
DOI 10.3390/batteries11060204

Published version of a preprint

Open this paper in CoChat — free accountOpen PDF

Abstract

The growing complexities, power densities, and cooling demands of modern electronic systems and batteries—such as three-dimensional integrated circuit chip packaging, printed circuit board assemblies, and electronics enclosures—have pushed the urgency for efficient and dynamic thermal management strategies. Traditional numerical methods like computational fluid dynamics (CFD) and the finite element method (FEM) are computationally impractical for large-scale or real-time thermal analysis, especially when dealing with complex geometries, temperature-dependent material properties, and rapidly changing boundary conditions. These approaches typically require extensive meshing and repeated simulations for each new scenario, making them inefficient for design exploration or optimization tasks. Physics-informed neural networks (PINNs) emerge as a powerful alternative approach that incorporates physical principles such as mass and energy conservation equations into deep learning models. This approach delivers rapid and adaptable resolutions to the partial differential equations that govern heat transfer and fluid dynamics. This review examines the basic principle of PINN and its role in thermal management for electronics and batteries, from the small unit scale to the system scale. We highlight recent advancements in PINNs, particularly their superior performance compared to traditional CFD methods. For example, studies have shown that PINNs can be up to 300,000 times faster than conventional CFD solvers, with temperature prediction differences of less than 0.1 K in chip thermal models. Beyond speed, we explore the potential of PINNs in enabling efficient design space exploration and predicting outcomes for previously unseen scenarios. However, challenges such as training convergence in fine-grained or large-scale applications remain. Notably, research combining PINNs with LSTM networks for battery thermal management at a 2.0 C charging rate has achieved impressive results—an R2 of 0.9863, a mean absolute error (MAE) of 0.2875 °C, and a root mean square error (RMSE) of 0.3306 °C—demonstrating high predictive accuracy. Finally, we propose future research directions that emphasize the integration of PINNs with advanced hardware and hybrid modeling techniques to advance thermal management solutions for next-generation electronics and battery systems.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/batteries11060204

Cites

93 of 93 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Data-driven models' effectiveness heavily depends on large, diverse, and high-quality datasets, and they may yield physically inconsistent results under unseen or noisy conditions.

    “Their effectiveness heavily depends on large, diverse, and high-quality datasets, and they may yield physically inconsistent results under unseen or noisy conditions.26,27”

    From State of mission: Battery management with neural networks and electrochemical AI (2025) · cites this paper as [27]

    The Introduction (page not provided) says effective conventional deep-learning models generally require extensive datasets and contrasts them with physics-informed models that incorporate physical laws to improve generalization. It does not specifically say the datasets must be diverse and high-quality or that data-driven models yield physically inconsistent results under unseen or noisy conditions. (LLM, conf=0.85)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 19

  1. Battery Operated Devices and Systems; Elsevier, 2009.
  2. Eymard, R.; Gallouët, T.; Herbin, R. Finite Volume Methods. In Handbook of Numerical Analysis; Elsevier, 2000; Vol. 7, pp. 713-1018.
  3. Proceedings of the ASME International Technical Conference and Exhibition on Packaging and Integration of Electronic and Photonic Microsystems -2018: Heterogeneous Integration: Microsystems with Diverse Functionality: Servers of the Future, IoT, and Edge to Cloud: Structural and Physical Health Monitoring: Power Electronics, Energy Conversion, and Storage: Autonomous, Hybrid, and Electric Vehicles: Presented at ASME 2018 International Technical Conference and Exhibition on Packaging and Integration of Electronic and Photonic Microsystems, August Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 2 May 2025 doi:10.20944/preprints202505.0088.v1 27-30, 2018, San Francisco, California, USA; American Society of Mechanical Engineers, American Society of Mechanical Engineers, Eds.; the American Society of Mechanical Engineers: New York, N.Y, 2019. · DOI
  4. Lu, R. Complex Wavelet Mutual Information Loss: A Multi-Scale Loss Function for Semantic Segmentation. ArXiv Prepr. ArXiv250200563 2025.
  5. Lu, R. Steerable Pyramid Weighted Loss: Multi-Scale Adaptive Weighting for Semantic Segmentation. ArXiv Prepr. ArXiv250306604 2025.
  6. Cai, S.; Mao, Z.; Wang, Z.; Yin, M.; Karniadakis, G.E. Physics-Informed Neural Networks (PINNs) for Fluid Mechanics: A Review. Acta Mech. Sin. 2021, 37, 1727-1738.
  7. Cai, S.; Wang, Z.; Wang, S.; Perdikaris, P.; Karniadakis, G.E. Physics-Informed Neural Networks for Heat Transfer Problems. J. Heat Transf. 2021, 143, 060801.
  8. Cai, S.; Mao, Z.; Wang, Z.; Yin, M.; Karniadakis, G.E. Physics-Informed Neural Networks (PINNs) for Fluid Mechanics: A Review. Acta Mech. Sin. 2021, 37, 1727-1738.
  9. Nabian, M.A.; Gladstone, R.J.; Meidani, H. Efficient Training of Physics-Informed Neural Networks via Importance Sampling. Comput.-Aided Civ. Infrastruct. Eng. 2021, 36, 962-977.
  10. Kharazmi, E.; Zhang, Z.; Karniadakis, G.E. Variational Physics-Informed Neural Networks for Solving Partial Differential Equations. ArXiv Prepr. ArXiv191200873 2019.
  11. Incropera, F.P., DeWitt, D.P., Bergman, T.L., Lavine, A.S., Eds.; 6. ed.; Wiley: Hoboken, NJ, 2007; ISBN 978-0-471-45728-2.
  12. Proceedings / CIPS 2012, 7th International Conference on Integrated Power Electronics Systems: March, 6 -8, 2012, Nuremberg, Germany ; Incl. CD-ROM; Energietechnische Gesellschaft, Ed.; ETG-Fachbericht; VDE-Verl: Berlin Offenbach, 2012.
  13. Li, Z.; Luo, H.; Jiang, Y.; Liu, H.; Xu, L.; Cao, K.; Wu, H.; Gao, P.; Liu, H. Comprehensive Review and Future Prospects on Chip-Scale Thermal Management: Core of Data Center's Thermal Management. Appl. Therm. Eng. 2024, 251, 123612.
  14. Chen, L.; Lu, J.; Jin, W.; Tan, S.X.-D. Fast Full-Chip Parametric Thermal Analysis Based on Enhanced Physics Enforced Neural Networks. In Proceedings of the 2023 IEEE/ACM International Conference on Computer Aided Design (ICCAD); IEEE: San Francisco, CA, USA, October 28 2023; pp. 1-8.
  15. Yang, Y.; Wang, Z.; Liao, Y.; Kong, W.; Shi, X.; Hu, R.; Yao, Y. A Parameterized Thermal Simulation Method Based on Physics-Informed Neural Networks for Fast Power Module Thermal Design. IEEE Trans. Power Electron. 2025, 1-11.
  16. Chen, L.; Jin, W.; Zhang, J.; Tan, S.X.-D. Thermoelectric Cooler Modeling and Optimization via Surrogate Modeling Using Implicit Physics-Constrained Neural Networks. IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst. 2023, 42, 4090-4101.
  17. Chen, D.; Chui, C.-K.; Lee, P.S. Adaptive Physically Consistent Neural Networks for Data Center Thermal Dynamics Modeling. Appl. Energy 2025, 377, 124637.
  18. Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 2 May 2025 doi:10.20944/preprints202505.0088.v1 · DOI
  19. Disclaimer/Publisher's Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. Preprints.org (www.preprints.org) | NOT PEER-REVIEWED | Posted: 2 May 2025 doi:10.20944/preprints202505.0088.v1 · DOI

Cited by

Sorted by citations

Related

Authors
Du, Z., & Lu, R.
Affiliations
  • Ansys, Inc., Austin, TX 78758, USA
  • Cornell University (US)
Corresponding author
Du, Zichen
ORCID
Venue
Batteries
Publisher
MDPI AG
Published
2025-05-22
Volume
11
Issue
6
Pages
204
ISSN
2313-0105 (ISSN-L)
DOI
10.3390/batteries11060204
OpenAlex
W4410598251
Cited by
58
References
93
Citations by year
2026: 49 · 2025: 9
FWCI
23.54
Type
journal article
Language
en
Open access
Licence
Locations
  • Batteries (publishedVersion, cc-by)
  • Preprints.org (acceptedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Physical Sciences › Physics and Astronomy › Statistical and Nonlinear Physics › Model Reduction and Neural Networks
  • Physical Sciences › Engineering › Computational Mechanics › Heat Transfer and Numerical Methods
  • Physical Sciences › Engineering › Automotive Engineering › Advanced Battery Technologies Research
Keywords
physics-informed neural networks, thermal management, electronics cooling, battery thermal management, heat transfer, fluid dynamics, integrated circuit packaging, printed circuit boards, electrical enclosures, LSTM, design space exploration, temperature prediction, hybrid modeling

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review