A Machine Learning Clustering Algorithm for Sensorless Multilevel Converters

Faete J.T. Filho, Parker Zieg, Burak Ozpineci, Nicholas Hill, Leon M. Tolbert

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

1 Scopus citations

Abstract

A method to determine the individual cell voltage in a multilevel converter through the output voltage is introduced. This technique can estimate the cell voltages without any knowledge of the controller switching sequence and can provide updated voltages within a quarter cycle. Estimates are obtained by using k-means algorithm to cluster the measured output data and determine cell voltage levels. Experimental results show that this technique can be applied in real time applications to add resiliency or reduce number of voltage sensors.

Original languageEnglish
Title of host publicationECCE 2020 - IEEE Energy Conversion Congress and Exposition
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1973-1976
Number of pages4
ISBN (Electronic)9781728158266
DOIs
StatePublished - Oct 11 2020
Event12th Annual IEEE Energy Conversion Congress and Exposition, ECCE 2020 - Virtual, Detroit, United States
Duration: Oct 11 2020Oct 15 2020

Publication series

NameECCE 2020 - IEEE Energy Conversion Congress and Exposition

Conference

Conference12th Annual IEEE Energy Conversion Congress and Exposition, ECCE 2020
Country/TerritoryUnited States
CityVirtual, Detroit
Period10/11/2010/15/20

Keywords

  • clustering
  • k-means
  • machine learning
  • multilevel inverter
  • sensorless

Fingerprint

Dive into the research topics of 'A Machine Learning Clustering Algorithm for Sensorless Multilevel Converters'. Together they form a unique fingerprint.

Cite this