Papers for

power electronics engineers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Physics-informed neural networks improve power converter parameter estimation

Sequential Learning-Based Physics-Informed Neural Network Modeling for Parameter Estimation on a Power Converter

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.

Wed 14 OctMachine Learning
The gist
Measuring exact electrical properties in devices like power converters can be hard, especially when small resistances affect performance. This paper presents a step-by-step machine learning method that uses physics knowledge to accurately estimate these properties from voltage and current data. The authors show that their method is more precise and faster than training all parameters at once, even when multiple properties change at the same time. This approach helps better understand and model power converters without complicated equipment.
Open → 2610.20041v1

Explainable machine learning improves multilayer planar winding inductance estimation

Explainable Machine Learning for Multilayer Planar Winding Inductance Estimation

Abstract: Rapid and accurate self-inductance estimation for multilayer rectangle-shaped planar windings is essential for modern high-frequency power converters, yet traditional workflows rely on complex mathematical equations, rigid monomial formulas or unexplainable black-box machine learning (ML) models that degrade severely outside their training domain. This paper introduces an explainable ML framework unifying post-hoc feature attribution (SHAP and permutation importance) with Kolmogorov-Arnold Network-guided symbolic regression via the SR-KAN framework to discover closed-form analytical equations without prior structural assumptions. Evaluated on a new open-source dataset of over 10,000 Finite Element Analysis (FEA) simulations across seven out-of-distribution (OOD) classes, standard tree-based ensembles exhibit severe extrapolation errors (> 36%), whereas the unconstrained SR-KAN expression achieves a robust OOD relative error of 8.22%. Experimental verification across 55 physical printed circuit board prototypes (up to 8 layers, with inductances from 4.11 μH to 559.27 μH) confirms that the KAN-discovered expression translates effectively to real-world hardware, predicting inductance with a mean absolute relative error of 6.26%. To support reproducible research, the complete FEA simulation dataset and prototype measurements are released open-source.

Tue 29 SeptMachine Learning
The gist
Estimating the inductance of multilayer planar windings quickly and accurately is important for modern electronics but is usually done with complex math or black-box models that can be unreliable. The authors combine explainable machine learning techniques with symbolic regression to discover simple, interpretable formulas that predict inductance well. Tested on a large simulated dataset and real hardware prototypes, their method greatly reduces error compared to traditional approaches. They also provide their simulation data and measurements openly for others to use.
Open → 2609.37211v1