Generalized PINN-Based Inverse Estimation of Spatially Varying Heat Transfer Coefficients with Transfer Learning
Abstract
This study investigates generalized boundary representations and transfer learning for physics-informed neural-network (PINN) estimation of spatially varying convective heat transfer coefficients (HTCs) in jet impingement cooling. Piecewise-linear (PWL) and neural-network boundary estimators are inferred from transient interior-temperature measurements and evaluated against CFD-CHT reference HTC profiles at Reynolds numbers of 5000, 10000 and 15000. A discrete Adjoint-FEM formulation with gradient regularization based on the H1-seminorm provides an independent inverse-method comparison. Transfer learning is investigated under two source-target conditions: transfer between noise levels at the same Reynolds number, and transfer from a controlled Gaussian-profile problem to CFD-CHT-derived target problems at different Reynolds numbers. For the representative Re = 5000 target with 5% measurement noise, quadratic, PWL, and neural-network PINNs achieve relative HTC-profile errors of 5.08, 5.31 and 5.19%, respectively, while generalized representations reduce the error for the Re = 15000 target from 16.76% for the quadratic PINN to 14.41% and 14.46%. Transfer learning reduces target-training time by 57.86-81.71% for fixed-Reynolds-number transfer and by 50.59-84.94% for Gaussian-to-CHT transfer. Its effect on reconstruction accuracy is target dependent: fixed-profile PWL transfer remains within 0.30 percentage points of scratch training, whereas Gaussian-to-CHT transfer produces differences of 0.10-1.52 percentage points across targets and representations. These results demonstrate that generalized PINN representations can accommodate spatially varying HTC profiles without a prescribed quadratic form, while transfer learning can substantially reduce target-training cost for repeated inverse estimation, with the resulting reconstruction accuracy depending on source-target compatibility.
Related
- Decay Rates and Domain Dependence of a Coupled Wave-Heat System with Spatially Dependent Heat Coefficients
- Identifying unknown time delay and spatially varying coefficients in a reaction-diffusion equation from boundary measurements
- Multilevel Monte Carlo for Polytopic DG Discretisations with Spatially Represented Random Coefficients
- Solvability of the L2 Dirichlet problem for parabolic operators with spatially periodic coefficients
- Lp-extrapolation via non-local decay estimates: theory and applications to the generalized Stokes operator with rough coefficients
BibTeX
@misc{maitra2026generalized,
title = {{Generalized PINN-Based Inverse Estimation of Spatially Varying Heat Transfer Coefficients with Transfer Learning}},
author = {Pradipan Maitra and Jariful Hassan and Arijit Hazra},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.14008},
eprint = {2610.14008},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.14008},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Generalized PINN-Based Inverse Estimation of Spatially Varying Heat Transfer Coefficients with Transfer Learning
AU - Pradipan Maitra
AU - Jariful Hassan
AU - Arijit Hazra
PY - 2026
DA - 2026/10/01
PB - arXiv
DO - 10.48550/arxiv.2610.14008
UR - https://arxiv.org/abs/2610.14008
AB - This study investigates generalized boundary representations and transfer learning for physics-informed neural-network (PINN) estimation of spatially varying convective heat transfer coefficients (HTCs) in jet impingement cooling. Piecewise-linear (PWL) and neural-network boundary estimators are inferred from transient interior-temperature measurements and evaluated against CFD-CHT reference HTC profiles at Reynolds numbers of 5000, 10000 and 15000. A discrete Adjoint-FEM formulation with gradient regularization based on the H^1-seminorm provides an independent inverse-method comparison. Transfer learning is investigated under two source-target conditions: transfer between noise levels at the same Reynolds number, and transfer from a controlled Gaussian-profile problem to CFD-CHT-derived target problems at different Reynolds numbers. For the representative Re = 5000 target with 5% measurement noise, quadratic, PWL, and neural-network PINNs achieve relative HTC-profile errors of 5.08, 5.31 and 5.19%, respectively, while generalized representations reduce the error for the Re = 15000 target from 16.76% for the quadratic PINN to 14.41% and 14.46%. Transfer learning reduces target-training time by 57.86-81.71% for fixed-Reynolds-number transfer and by 50.59-84.94% for Gaussian-to-CHT transfer. Its effect on reconstruction accuracy is target dependent: fixed-profile PWL transfer remains within 0.30 percentage points of scratch training, whereas Gaussian-to-CHT transfer produces differences of 0.10-1.52 percentage points across targets and representations. These results demonstrate that generalized PINN representations can accommodate spatially varying HTC profiles without a prescribed quadratic form, while transfer learning can substantially reduce target-training cost for repeated inverse estimation, with the resulting reconstruction accuracy depending on source-target compatibility.
ER -