PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
Synapse
⌘+K
Synapse
July 19, 2026International Journal of Numerical Methods for Heat &amp Fluid Flow

Modified-inverse physics informed neural networks for determination of orthotropic thermal conductivities

View Full Paper
Ask AI
Bookmark
Share

Authors

GKGudipati Sai KrishnaJJJ. JithuMVMuthusaran Coimbatore Vijayakumar

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates improved accuracy for thermal conductivity identification in diverse configurations, suggesting greater efficiency under sparse data conditions.

Key Points

  • The aim is to create a modified inverse physics-informed neural network framework for improving parameter identification in heat conduction problems.
  • Developed a modified inverse-PINN framework incorporating pseudo gradient descent optimization.
  • Validated methodology through five configurations, including numerical simulations and experimental data.
  • Applied the technique to estimate isotropic and orthotropic thermal conductivities for materials such as stainless steel and lithium-ion batteries.
  • Showed enhanced parameter estimation accuracy and computational efficiency compared to conventional methods.
  • Achieved reduced parameter uncertainty and stable convergence behavior under sparse data constraints.
  • Demonstrated effectiveness through comprehensive validation across three-dimensional experimental scenarios.

Cite This Study

Krishna et al. (2026) studied this question.

synapsesocial.com/papers/6a5c6999118b92953e3edd84https://doi.org/10.1108/hff-03-2026-0324
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Mixed convection physical-informed neural networks for flow reconstruction with sparse thermal data and partial physics in a lid-driven cavity2025
  2. 2An enhanced physics-informed deep learning framework for solving variable-coefficient heat conduction problems with temperature-dependent thermal conductivity and nonlinear source terms2026
  3. 3Physics-Informed Neural Networks for Heat Transfer Problems2021 · 1,303 citations
  4. 4Gradient enhanced physics informed neural networks with adaptive loss for 2D heat equations with variable and non smooth conductivity2026
  5. 5Solving backward heat transfer by physics-informed machine learning2026