Generalized PINN-Based Inverse Estimation of Spatially Varying Heat Transfer Coefficients with Transfer Learning
The study uses physics-informed neural networks (PINNs) and generalized boundary representations to estimate spatially varying heat transfer coefficients in jet impingement cooling from temperature measurements. It compares different PINN structures and tests transfer learning techniques, showing that these methods can accurately reconstruct complex heat transfer profiles and significantly reduce the time needed for repeated estimation.