Equivalent Circuit Design for Inductors with Artificial Neural Networks

Conference: PCIM Conference 2025 - International Exhibition and Conference for Power Electronics, Intelligent Motion, Renewable Energy and Energy Management
05/06/2025 - 05/08/2025 at Nürnberg, Germany

doi:10.30420/566541356

Proceedings: PCIM Conference 2025

Pages: Language: englishTyp: PDF

Personal VDE Members are entitled to a 10% discount on this title

Authors:
Talits, Kevin; Lazarowicz, Nathan; Tebruegge, Claas; Post, Martin

Abstract:
Accurate determination of parasitic capacitance, inductance, and resistance is essential for high-frequency circuit design and performance. Traditional methods, including numerical field solvers and analytical calculations, are limited by computational load and accuracy. This paper introduces a novel approach using Artificial Neural Networks (ANNs) to determine inductor parameters. An ANN trained with data from over 200 measured inductors demonstrates high accuracy in predicting the desired parameters with an error under 5% in average and under 3% for single electrical parameter. The proposed method provides a fast and accurate alternative for designing equivalent circuits with the possibility for extensive parameter studies.