DocumentCode
1801681
Title
Sensorless control of induction motor using a neural network for speed estimation
Author
Kazmierkowski, M.P. ; Sobczuk, D.L. ; Filipek, P.Z.
Author_Institution
Inst. of Control & Ind. Electron., Warsaw Univ. of Technol., Poland
fYear
1997
fDate
7-11 Jul 1997
Firstpage
1242
Abstract
In the paper the application of an on-line trained neural network working as a speed estimator is presented. Three different speed estimation algorithms: backpropagation, conjugate gradient as well as least squares are investigated and compared. Some oscillograms which illustrate properties and sensitivity to parameter changes of the speed estimation techniques are presented
Keywords
angular velocity control; backpropagation; conjugate gradient methods; electric machine analysis computing; induction motors; least squares approximations; machine control; neural nets; parameter estimation; backpropagation; conjugate gradient; induction motor; least squares; neural network; on-line trained neural network; oscillograms; parameter changes sensitivity; sensorless control; speed estimation; IEEE catalog; Induction motors; Industrial electronics; Mechanical sensors; Neural networks; Sensorless control; Stators; Synchronous motors; Velocity measurement; Voltage;
fLanguage
English
Publisher
ieee
Conference_Titel
Industrial Electronics, 1997. ISIE '97., Proceedings of the IEEE International Symposium on
Conference_Location
Guimaraes
Print_ISBN
0-7803-3936-3
Type
conf
DOI
10.1109/ISIE.1997.648921
Filename
648921
Link To Document