Transient Modeling of Induction Machine Using Artificial Neural Network Surrogate Models

Mikko Tahkola; Victor Mukherjee; Janne Keränen

doi:10.1109/TMAG.2022.3180176

Transient Modeling of Induction Machine Using Artificial Neural Network Surrogate Models

Mikko Tahkola (Corresponding Author), Victor Mukherjee, Janne Keränen

ABB Oy

Research output: Contribution to journal › Article › Scientific › peer-review

Abstract

A transient model of an induction machine (IM) is developed in this work using an artificial neural network (ANN) surrogate model. The model is suitable to be used for direct-on-line IMs. The finite-element (FE)-based model of IM is used to generate the training, validation, and testing datasets. Different inputs and model configurations are investigated to find an optimal solution in developing the transient model. The proposed transient model is suitable to be used in digital twin services since it can estimate the current and torque accurately in real time based on only voltage and measured shaft speed.

Original language	English
Article number	7402204
Number of pages	4
Journal	IEEE Transactions on Magnetics
Volume	58
Issue number	9
DOIs	https://doi.org/10.1109/TMAG.2022.3180176
Publication status	Published - Sep 2022
MoE publication type	A1 Journal article-refereed

Keywords

artificial neural network , Digital twin , Induction machine , Real time , Surrogate modelling
digital twin
induction machine
real time
surrogate modelling
Torque
Predictive models
Real time
Optimization
Shafts
Training
Digital twin
Surrogate modelling
Induction machine
Artificial neural network
Transient analysis
Testing

Access to Document

10.1109/TMAG.2022.3180176Licence: CC BY

Cite this

@article{7925be04676c4bdbb0488caf2371f5c2,

title = "Transient Modeling of Induction Machine Using Artificial Neural Network Surrogate Models",

abstract = "A transient model of an induction machine (IM) is developed in this work using an artificial neural network (ANN) surrogate model. The model is suitable to be used for direct-on-line IMs. The finite-element (FE)-based model of IM is used to generate the training, validation, and testing datasets. Different inputs and model configurations are investigated to find an optimal solution in developing the transient model. The proposed transient model is suitable to be used in digital twin services since it can estimate the current and torque accurately in real time based on only voltage and measured shaft speed.",

keywords = "artificial neural network , Digital twin , Induction machine , Real time , Surrogate modelling, digital twin, induction machine, real time, surrogate modelling, Torque, Predictive models, Real time, Optimization, Shafts, Training, Digital twin, Surrogate modelling, Induction machine, Artificial neural network, Transient analysis, Testing",

author = "Mikko Tahkola and Victor Mukherjee and Janne Ker{\"a}nen",

note = "This work has been done in the Arrowhead Tools project, funded by the European Commission through the European H2020 Research and Innovation programme, ECSEL Joint Undertaking, and National Funding Authorities from the 18 countries under grant agreement number 826452. ",

year = "2022",

month = sep,

doi = "10.1109/TMAG.2022.3180176",

language = "English",

volume = "58",

journal = "IEEE Transactions on Magnetics",

issn = "0018-9464",

publisher = "IEEE Institute of Electrical and Electronic Engineers",

number = "9",

}

TY - JOUR

T1 - Transient Modeling of Induction Machine Using Artificial Neural Network Surrogate Models

AU - Tahkola, Mikko

AU - Mukherjee, Victor

AU - Keränen, Janne

N1 - This work has been done in the Arrowhead Tools project, funded by the European Commission through the European H2020 Research and Innovation programme, ECSEL Joint Undertaking, and National Funding Authorities from the 18 countries under grant agreement number 826452.

PY - 2022/9

Y1 - 2022/9

N2 - A transient model of an induction machine (IM) is developed in this work using an artificial neural network (ANN) surrogate model. The model is suitable to be used for direct-on-line IMs. The finite-element (FE)-based model of IM is used to generate the training, validation, and testing datasets. Different inputs and model configurations are investigated to find an optimal solution in developing the transient model. The proposed transient model is suitable to be used in digital twin services since it can estimate the current and torque accurately in real time based on only voltage and measured shaft speed.

AB - A transient model of an induction machine (IM) is developed in this work using an artificial neural network (ANN) surrogate model. The model is suitable to be used for direct-on-line IMs. The finite-element (FE)-based model of IM is used to generate the training, validation, and testing datasets. Different inputs and model configurations are investigated to find an optimal solution in developing the transient model. The proposed transient model is suitable to be used in digital twin services since it can estimate the current and torque accurately in real time based on only voltage and measured shaft speed.

KW - artificial neural network , Digital twin , Induction machine , Real time , Surrogate modelling

KW - digital twin

KW - induction machine

KW - real time

KW - surrogate modelling

KW - Torque

KW - Predictive models

KW - Real time

KW - Optimization

KW - Shafts

KW - Training

KW - Digital twin

KW - Surrogate modelling

KW - Induction machine

KW - Artificial neural network

KW - Transient analysis

KW - Testing

UR - http://www.scopus.com/inward/record.url?scp=85131716532&partnerID=8YFLogxK

U2 - 10.1109/TMAG.2022.3180176

DO - 10.1109/TMAG.2022.3180176

M3 - Article

VL - 58

JO - IEEE Transactions on Magnetics

JF - IEEE Transactions on Magnetics

SN - 0018-9464

IS - 9

M1 - 7402204

ER -

Transient Modeling of Induction Machine Using Artificial Neural Network Surrogate Models

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Arrowhead Tools: Arrowhead Tools for Engineering of Digitalisation Solutions

Cite this

Transient Modeling of Induction Machine Using Artificial Neural Network Surrogate Models

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Projects

Arrowhead Tools: Arrowhead Tools for Engineering of Digitalisation Solutions

Cite this