PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
February 16, 2026Applied Sciences3 citationsOpen Access

A Cooperative Soft-Hard PINN Framework for Decoupling the Thermoelasticity and Thermal Convection Multiphysics

View Full Paper
YLYuxin LiuCZChuyu ZhouGXGuoguo Xin

Key Points

  • The study aims to improve the balance of loss terms in thermally coupled multiphysics problems using a novel PINN framework.
  • Introduced Cooperative Soft-Hard PINNs for managing loss terms
  • Enforced soft constraints on Neumann conditions and hard constraints on others
  • Validated on thermoelasticity and thermal convection scenarios
  • Assessed robustness against Gaussian white noise and different data sampling
  • Achieved a 56% reduction in training time
  • Reduced velocity errors by up to 78% with partial data in thermal convection
  • Maintained high-fidelity predictions under noise interference
  • Outperformed baseline methods in accuracy and robustness

Abstract

Physics-informed neural networks (PINNs) often struggle to balance multiple loss terms in thermally coupled multiphysics problems. We propose Cooperative Soft-Hard PINNs (s-hPINN/s-HB-PINN), which apply soft constraints to fields with Neumann conditions while enforcing hard constraints on others to balance exact boundary enforcement with training stability. Validated on thermoelasticity and thermal convection, our method reduces training time by approximately 56%. In thermal convection experiments, incorporating partial data further reduces velocity errors by up to 78% compared to standard PINNs. We subsequently assessed the framework’s robustness against varying relative Gaussian white noise levels and different data sampling locations. The result demonstrate that s-HB-PINN maintains high-fidelity predictions even under noise interference, consistently outperforming baseline methods. This confirms that the proposed collaborative strategy offers a superior trade-off between accuracy, efficiency, and robustness in complex multiphysics environments.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Liu et al. (2026) studied this question.

synapsesocial.com/papers/6992b3b19b75e639e9b08627https://doi.org/10.3390/app16041885
Ask AI
Helpful
Bookmark
Share
View Full Paper