Model Releases
Sequential Learning-Based Physics-Informed Neural Network Modeling for Parameter Estimation on a Power Converter
arXiv:2610.20041v1 Announce Type: new Abstract: A staged physics-informed neural network (PINN) is proposed for identifying the inductance, capacitance and parasitic resistances of a DC buck converter
arXiv:2610.20041v1 Announce Type: new Abstract: A staged physics-informed neural network (PINN) is proposed for identifying the inductance, capacitance and parasitic resistances of a DC buck converter from time-domain data. Gradients are released in the order of L to C to rL to rC, a sequence derived from sensitivity analysis. The five-stage schedule recovers L and C to within 5% and the series ESR to 10%, while a three-stage variant attains the same accuracy 11% faster. An 84 factorial sweep confirms that the trained PINN remains accurate for simultaneous 8% perturbations of all four components, achieving a waveform RMSE of 2.6 x 10-2 over 5 ms-an order-of-magnitude better than a simultaneous-training baseline.
Related
- Neuromorphic Parameter Estimation for Power Converter Health Monitoring Using Spiking Neural Networks
- Target-Guided Selective Reweighting for Physics-Informed Neural Network Inverse Problems: A Transfer Learning Approach
- Continual-Learning Physics-Informed Neural Networks for Parameterized Partial Differential Equations
- Beyond Field Accuracy: Two-Axis Diagnosis of Inverse-PINN Parameter Error
Source: arXiv cs.LG | 2026-10-15