Weighted parametric model identification of induction motors with variable loads using FNN structure and NN2TF algorithm

Tarek A. Tutunji, Ashraf Saleem

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Induction motors exhibit non-linear behaviour and are difficult to model. Furthermore, load disparities cause speed variations and therefore predicting the motor’s response is challenging. In this paper, feedforward neural networks (FNNs) are used to model induction motors at two load levels (i.e. no-load and full-load). The two FNN models are then transformed into auto-regressive moving-average (ARMA) models using a new NN2TF algorithm. A weighted parametric model is then formulated by combining both ARMA models to provide appropriate transfer functions at different loads ranging from no-load to full-load. In order to validate the developed model, experimental data (with voltage/speed as input/output) is collected from an induction motor plant at five different load levels and used to test the proposed model. Simulation results show that the estimated model produced dynamic responses that follow the experimental data with good accuracy, regardless of the load.

Original languageEnglish
Pages (from-to)1645-1658
Number of pages14
JournalTransactions of the Institute of Measurement and Control
Volume40
Issue number5
DOIs
Publication statusPublished - Mar 1 2018

Fingerprint

induction motors
Feedforward neural networks
Induction motors
Identification (control systems)
autoregressive moving average
dynamic response
transfer functions
Dynamic response
Transfer functions
causes
output

Keywords

  • ARMA models
  • induction motors
  • neural networks
  • robust design
  • system identification

ASJC Scopus subject areas

  • Instrumentation

Cite this

@article{68048a33067046f7aca326f964b3a5a6,
title = "Weighted parametric model identification of induction motors with variable loads using FNN structure and NN2TF algorithm",
abstract = "Induction motors exhibit non-linear behaviour and are difficult to model. Furthermore, load disparities cause speed variations and therefore predicting the motor’s response is challenging. In this paper, feedforward neural networks (FNNs) are used to model induction motors at two load levels (i.e. no-load and full-load). The two FNN models are then transformed into auto-regressive moving-average (ARMA) models using a new NN2TF algorithm. A weighted parametric model is then formulated by combining both ARMA models to provide appropriate transfer functions at different loads ranging from no-load to full-load. In order to validate the developed model, experimental data (with voltage/speed as input/output) is collected from an induction motor plant at five different load levels and used to test the proposed model. Simulation results show that the estimated model produced dynamic responses that follow the experimental data with good accuracy, regardless of the load.",
keywords = "ARMA models, induction motors, neural networks, robust design, system identification",
author = "Tutunji, {Tarek A.} and Ashraf Saleem",
year = "2018",
month = "3",
day = "1",
doi = "10.1177/0142331216688249",
language = "English",
volume = "40",
pages = "1645--1658",
journal = "Transactions of the Institute of Measurement and Control",
issn = "0142-3312",
publisher = "SAGE Publications Ltd",
number = "5",

}

TY - JOUR

T1 - Weighted parametric model identification of induction motors with variable loads using FNN structure and NN2TF algorithm

AU - Tutunji, Tarek A.

AU - Saleem, Ashraf

PY - 2018/3/1

Y1 - 2018/3/1

N2 - Induction motors exhibit non-linear behaviour and are difficult to model. Furthermore, load disparities cause speed variations and therefore predicting the motor’s response is challenging. In this paper, feedforward neural networks (FNNs) are used to model induction motors at two load levels (i.e. no-load and full-load). The two FNN models are then transformed into auto-regressive moving-average (ARMA) models using a new NN2TF algorithm. A weighted parametric model is then formulated by combining both ARMA models to provide appropriate transfer functions at different loads ranging from no-load to full-load. In order to validate the developed model, experimental data (with voltage/speed as input/output) is collected from an induction motor plant at five different load levels and used to test the proposed model. Simulation results show that the estimated model produced dynamic responses that follow the experimental data with good accuracy, regardless of the load.

AB - Induction motors exhibit non-linear behaviour and are difficult to model. Furthermore, load disparities cause speed variations and therefore predicting the motor’s response is challenging. In this paper, feedforward neural networks (FNNs) are used to model induction motors at two load levels (i.e. no-load and full-load). The two FNN models are then transformed into auto-regressive moving-average (ARMA) models using a new NN2TF algorithm. A weighted parametric model is then formulated by combining both ARMA models to provide appropriate transfer functions at different loads ranging from no-load to full-load. In order to validate the developed model, experimental data (with voltage/speed as input/output) is collected from an induction motor plant at five different load levels and used to test the proposed model. Simulation results show that the estimated model produced dynamic responses that follow the experimental data with good accuracy, regardless of the load.

KW - ARMA models

KW - induction motors

KW - neural networks

KW - robust design

KW - system identification

UR - http://www.scopus.com/inward/record.url?scp=85044132430&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044132430&partnerID=8YFLogxK

U2 - 10.1177/0142331216688249

DO - 10.1177/0142331216688249

M3 - Article

VL - 40

SP - 1645

EP - 1658

JO - Transactions of the Institute of Measurement and Control

JF - Transactions of the Institute of Measurement and Control

SN - 0142-3312

IS - 5

ER -