Machine learning-based method for linearization and error compensation of a novel absolute rotary encoder
JournalArticle (Originalarbeit in einer wissenschaftlichen Zeitschrift)
 
ID 4606463
Author(s) Iafolla, Lorenzo; Filipozzi, Massimiliano; Freund, Sara; Zam, Azhar; Rauter, Georg; Cattin, Philippe Claude
Author(s) at UniBasel Iafolla, Lorenzo
Filipozzi, Massimiliano
Freund, Sara
Zam, Azhar
Rauter, Georg
Cattin, Philippe Claude
Year 2021
Title Machine learning-based method for linearization and error compensation of a novel absolute rotary encoder
Journal Measurement
Volume 169
Pages / Article-Number 108547
Abstract The main objective of this work is to develop a miniaturized, high accuracy, single-turn absolute, rotary encoder called ASTRAS360. Its measurement principle is based on capturing an image that uniquely identifies the rotation angle. To evaluate this angle, the image first has to be classified into its sector based on its color, and only then can the angle be regressed. Inspired by machine learning, we built a calibration setup, able to generate labeled training data automatically. We used these training data to test, characterize, and compare several machine learning algorithms for the classification and the regression. In an additional experiment, we also characterized the tolerance of our rotary encoder to eccentric mounting. Our findings demonstrate that various algorithms can perform these tasks with high accuracy and reliability; furthermore, providing extra-inputs (e.g. rotation direction) allows the machine learning algorithms to compensate for the mechanical imperfections of the rotary encoder.
Publisher Elsevier
ISSN/ISBN 0263-2241
edoc-URL https://edoc.unibas.ch/79329/
Full Text on edoc No
Digital Object Identifier DOI 10.1016/j.measurement.2020.108547
Document type (ISI) article
 
   

MCSS v5.8 PRO. 0.404 sec, queries - 0.000 sec ©Universität Basel  |  Impressum   |    
30/11/2021