Publication detail

Comparison of machine learning training sampling schemes for induction machine modeling

BÍLEK, V.

Original Title

Comparison of machine learning training sampling schemes for induction machine modeling

Type

conference paper

Language

English

Original Abstract

The aim of the paper is to demonstrate the modeling of an induction machine using a chosen machine learning technique, followed by a comparison of the training sampling schemes for this technique. A simple 3-phase induction machine with an axially slitted solid rotor has been selected for the case study, where FEM-based program Ansys Electronics Desktop has been used for its calculation. A total of 3 training schemes were considered and compared with each other for the machine learning technique. Some of the comparison results are given and discussed at the end of this paper. The described methodology can be used to accelerate the design and optimization of any type of electrical machine.

Keywords

FEA, Finite element method, Gaussian process regression, Induction machine, Machine learning, Solid rotor, Surrogate modeling

Authors

BÍLEK, V.

Released

25. 4. 2023

Publisher

Brno University of Technology, Faculty of Elektronic Engineering and Communication

Location

Brno

ISBN

978-80-214-6154-3

Book

PROCEEDINGS II OF THE 29TH STUDENT EEICT 2023 Selected papers

Edition

1

Pages from

188

Pages to

192

Pages count

5

URL

https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2023_sbornik_2_v2.pdf

BibTex

@inproceedings{BUT183430,
  author="Vladimír {Bílek}",
  title="Comparison of machine learning training sampling schemes for induction machine modeling",
  booktitle="PROCEEDINGS II OF THE 29TH STUDENT EEICT 2023 Selected papers",
  year="2023",
  series="1",
  pages="188--192",
  publisher="Brno University of Technology, Faculty of Elektronic Engineering and Communication",
  address="Brno",
  isbn="978-80-214-6154-3",
  url="https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2023_sbornik_2_v2.pdf"
}