Go to main content
Inductor design optimization using FEA supervised machine learning
Cajander, David; Viarouge, Isabelle; Viarouge, Philippe; Aguglia, Davide
2022
Download
Formats
Format
BibTeX
MARCXML
TextMARC
MARC
DublinCore
EndNote
NLM
RefWorks
RIS

Files

Abstract

An optimal inductor design methodology using dimensioning models derived from Finite Element Analysis (FEA) supervised Artificial Neural Networks (ANN) is presented. The efficiency of such trained ANN dimensioning models in terms of compromise between precision and computing time is demonstrated for the cylindrical inductor topology with air and magnetic material core including saturation.

Details

Title
Inductor design optimization using FEA supervised machine learning
Author(s)
Cajander, David (School of Engineering and Architecture (HEIA-FR), HES-SO University of Applied Sciences Western Switzerland ; Laval University, Qubec, QC, Canada)
Viarouge, Isabelle (Electrotechnologies Selem Inc, Quebec, QC, Canada)
Viarouge, Philippe (Laval University, Quebec, QC, Canada)
Aguglia, Davide (Laval University, Quebec, QC, Canada ; CERN, Geneva, Switzerland)
Date
2022-09
Published in
Proceedings of EPE'22 ECCE Europe, 5-9 September 2022, Hannover, Germany
Publisher
Hannover, Germany, 5-9 September 2022
Pagination & equivalents
11 p.
Presented at
EPE'22 ECCE Europe, Hannover, Germany, 2022-09-05, 2022-09-09
Keywords
magnetic device ; machine learning ; deep learning ; design optimization ; finite-element analysis ; data analysis ; neural network ; passive component
Paper type
published full paper
Faculty
Ingénierie et Architecture
School
HEIA-FR
Institute
Energy - Institut de recherche appliquée en systèmes énergétiques
Record Appears in
Conference materials
Global

Actions