Auto-associative neural network based sensor drift compensation in indirect vector controlled drive system

Luigi Galotto, Bimal K. Bose, Luciana C. Leite, João Onofre Pereira Pinto, Luiz Eduardo Borges Da Silva, Germano Lambert-Torres

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

9 Scopus citations

Abstract

The paper proposes an auto-associative neural network (AANN) based sensor drift compensation in an indirect vector-controlled induction motor drive. The feedback signals from the phase current sensors are given as the AANN input. The AANN then performs the auto-associative mapping of these signals so that its output is an estimate of the sensed signals. Since the AANN exploits the physical and analytical redundancy, whenever a sensor starts to drift, the drift is compensated at the output, and the performance of the drive system is barely affected. The paper describes the drive system, gives a brief overview of the AANN, presents the technical approach, and then gives some performance of the system demonstrating validity of the approach. Although current sensors are considered only in the paper, the same approach can be applied to voltage, speed, torque, flux, or any other type sensor.

Original languageEnglish
Title of host publicationProceedings of the 33rd Annual Conference of the IEEE Industrial Electronics Society, IECON
Pages1009-1014
Number of pages6
DOIs
StatePublished - 2007
Externally publishedYes
Event33rd Annual Conference of the IEEE Industrial Electronics Society, IECON - Taipei, Taiwan, Province of China
Duration: Nov 5 2007Nov 8 2007

Publication series

NameIECON Proceedings (Industrial Electronics Conference)

Conference

Conference33rd Annual Conference of the IEEE Industrial Electronics Society, IECON
Country/TerritoryTaiwan, Province of China
CityTaipei
Period11/5/0711/8/07

Fingerprint

Dive into the research topics of 'Auto-associative neural network based sensor drift compensation in indirect vector controlled drive system'. Together they form a unique fingerprint.

Cite this