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

Author

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

Author_Institution

Sch. of Electr. & Control Instrum. Eng., Mokpo Nat. Univ., Chonnam, South Korea

Volume

48

Issue

3

fYear

2001

fDate

6/1/2001 12:00:00 AM

Firstpage

609

Lastpage

614

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

angular velocity control; backpropagation; electric machine analysis computing; induction motor drives; machine vector control; neural nets; parameter estimation; 2.2 kW; digitalized induction motor drive systems; error backpropagation algorithm; induction motor; load variation; neural network speed estimation; speed control loop; speed-sensorless vector control; speed-sensorless vector drive; steady state; training; transient state; variable-speed operation; Associate members; Backpropagation algorithms; Induction motors; Industrial training; Machine vector control; Mechanical sensors; Neural networks; Nonhomogeneous media; Robustness; Velocity control;

fLanguage

English

Journal_Title

Industrial Electronics, IEEE Transactions on

Publisher

ieee

ISSN

0278-0046

Type

jour

DOI

10.1109/41.925588

Filename

925588