Speed-sensorless vector control of an induction motor using neural network speed estimation

Seong Hwan Kim, Tae Sik Park, Ji Yoon Yoo, Gwi Tae Park

Research output: Contribution to journalArticle

127 Citations (Scopus)

Abstract

In this paper, a novel speed estimation method of an induction motor using neural networks (NNs) is presented. The NN speed estimator is trained online by using the error backpropagation algorithm, and the training starts simultaneously with the induction motor working. The estimated speed is then fed back in the speed control loop, and the speed-sensorless vector drive is realized. The proposed NN speed estimator has shown good performance in the transient and steady states, and also at either variable-speed operation or load variation. The validity and the usefulness of the proposed algorithm are thoroughly verified with experiments on fully digitalized 2.2-kW induction motor drive systems.

Original languageEnglish
Pages (from-to)609-614
Number of pages6
JournalIEEE Transactions on Industrial Electronics
Volume48
Issue number3
DOIs
Publication statusPublished - 2001 Jun 1

Fingerprint

directional control
induction motors
Induction motors
Neural networks
estimators
speed control
Backpropagation algorithms
Speed control
education

Keywords

  • Induction motor
  • Neural networks
  • Speed estimation
  • Speed-sensorless vector control

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Instrumentation

Cite this

Speed-sensorless vector control of an induction motor using neural network speed estimation. / Kim, Seong Hwan; Park, Tae Sik; Yoo, Ji Yoon; Park, Gwi Tae.

In: IEEE Transactions on Industrial Electronics, Vol. 48, No. 3, 01.06.2001, p. 609-614.

Research output: Contribution to journalArticle

@article{5e317244af4645a99d0ea4f3a7136919,
title = "Speed-sensorless vector control of an induction motor using neural network speed estimation",
abstract = "In this paper, a novel speed estimation method of an induction motor using neural networks (NNs) is presented. The NN speed estimator is trained online by using the error backpropagation algorithm, and the training starts simultaneously with the induction motor working. The estimated speed is then fed back in the speed control loop, and the speed-sensorless vector drive is realized. The proposed NN speed estimator has shown good performance in the transient and steady states, and also at either variable-speed operation or load variation. The validity and the usefulness of the proposed algorithm are thoroughly verified with experiments on fully digitalized 2.2-kW induction motor drive systems.",
keywords = "Induction motor, Neural networks, Speed estimation, Speed-sensorless vector control",
author = "Kim, {Seong Hwan} and Park, {Tae Sik} and Yoo, {Ji Yoon} and Park, {Gwi Tae}",
year = "2001",
month = "6",
day = "1",
doi = "10.1109/41.925588",
language = "English",
volume = "48",
pages = "609--614",
journal = "IEEE Transactions on Industrial Electronics",
issn = "0278-0046",
publisher = "IEEE Industrial Electronics Society",
number = "3",

}

TY - JOUR

T1 - Speed-sensorless vector control of an induction motor using neural network speed estimation

AU - Kim, Seong Hwan

AU - Park, Tae Sik

AU - Yoo, Ji Yoon

AU - Park, Gwi Tae

PY - 2001/6/1

Y1 - 2001/6/1

N2 - In this paper, a novel speed estimation method of an induction motor using neural networks (NNs) is presented. The NN speed estimator is trained online by using the error backpropagation algorithm, and the training starts simultaneously with the induction motor working. The estimated speed is then fed back in the speed control loop, and the speed-sensorless vector drive is realized. The proposed NN speed estimator has shown good performance in the transient and steady states, and also at either variable-speed operation or load variation. The validity and the usefulness of the proposed algorithm are thoroughly verified with experiments on fully digitalized 2.2-kW induction motor drive systems.

AB - In this paper, a novel speed estimation method of an induction motor using neural networks (NNs) is presented. The NN speed estimator is trained online by using the error backpropagation algorithm, and the training starts simultaneously with the induction motor working. The estimated speed is then fed back in the speed control loop, and the speed-sensorless vector drive is realized. The proposed NN speed estimator has shown good performance in the transient and steady states, and also at either variable-speed operation or load variation. The validity and the usefulness of the proposed algorithm are thoroughly verified with experiments on fully digitalized 2.2-kW induction motor drive systems.

KW - Induction motor

KW - Neural networks

KW - Speed estimation

KW - Speed-sensorless vector control

UR - http://www.scopus.com/inward/record.url?scp=0035366525&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035366525&partnerID=8YFLogxK

U2 - 10.1109/41.925588

DO - 10.1109/41.925588

M3 - Article

VL - 48

SP - 609

EP - 614

JO - IEEE Transactions on Industrial Electronics

JF - IEEE Transactions on Industrial Electronics

SN - 0278-0046

IS - 3

ER -