A Comparative Study of Surrogate Modeling Techniques for Parasitic Inductance Estimation in Power Modules

Khan AU, Umar Z, Botazzoli P, Fischer G (2026)

Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2026

Publisher: IEEE

Event location: Valencia Conference Center Avda. Cortes Valencianas, nº 60, 46015 València(Spain) palcongres-vlc.com ES

URI: https://www.ecce-europe.org/2026/

Abstract

This paper presents an automated finite element method (FEM)-driven surrogate modeling framework for rapid
prediction of parasitic inductances in power module commutation loops. Parasitic inductance critically affects switching transients, voltage overshoot, and electromagnetic interference in high frequency converters. Although FEM based extraction provides high fidelity results, it becomes computationally prohibitive for large
scale parametric design exploration. A parameterized half-bridge power module was developed in
Ansys Q3D and automated through a Python based PyAEDT workflow for systematic dataset generation. Latin hypercube sampling was employed to explore geometric variations, and inductance matrices were extracted for multiple configurations. Linear regression, artificial neural networks, and Gaussian process regression (GPR) were evaluated as surrogate models. Across all investigated case studies, the optimized GPR model
achieved an average mean absolute error of 0.0224 nH, a root mean square error of 0.0351 nH, and an average R2 of 0.983. Additionally, the surrogate framework provided approximately 4.0 × 105 reduction in per-sample computation time relative to full wave analysis, enabling scalable AI assisted power module
design optimization. 

Authors with CRIS profile

Zeeshan Umar Department Elektrotechnik-Elektronik-Informationstechnik (EEI) Georg Fischer Professur für Technische Elektronik

Involved external institutions

Siemens AG DE Germany (DE)

How to cite

APA:

Khan, A.U., Umar, Z., Botazzoli, P., & Fischer, G. (2026). A Comparative Study of Surrogate Modeling Techniques for Parasitic Inductance Estimation in Power Modules. In Proceedings of the ECCE Europe - Energy Conversion Congress & Expo. Valencia Conference Center Avda. Cortes Valencianas, nº 60, 46015 València(Spain) palcongres-vlc.com, ES: IEEE.

MLA:

Khan, Asad Ullah, et al. "A Comparative Study of Surrogate Modeling Techniques for Parasitic Inductance Estimation in Power Modules." Proceedings of the ECCE Europe - Energy Conversion Congress & Expo, Valencia Conference Center Avda. Cortes Valencianas, nº 60, 46015 València(Spain) palcongres-vlc.com IEEE, 2026.

BibTeX: Download