Principal Component Analysis Anomaly Detector for Rotor Broken Bars
2015 (English)In: IECON 2014: 40th Annual Conference of the IEEE Industrial Electronics Society, Dallas, TX, USA , Oct. 29 2014 - Nov. 1 2014, Piscataway, NJ: IEEE Communications Society, 2015, 3462-3467 p.Conference paper (Refereed)
In this article a method for the detection of broken rotor bars in asynchronous machines operating under full load is presented. Unlike most Motor Current Signature Analysis (MCSA) approaches, which operate in the frequency domain, our method operates in the time domain. The scheme is based on the use of a Principal Component Analysis (PCA) fault/anomaly detector applied on the three stator currents to calculate the Q statistic which is employed for detecting a fault. The efﬁciency of the proposed scheme was experimentally evaluated using different fault severity levels, ranging from 1/4 of a broken bar to three broken bars. The obtained results indicate that the method can detect the caused asymmetry with a very restricted amount of data.
Place, publisher, year, edition, pages
Piscataway, NJ: IEEE Communications Society, 2015. 3462-3467 p.
Information technology - Automatic control
Informationsteknik - Reglerteknik
Research subject Control Engineering
IdentifiersURN: urn:nbn:se:ltu:diva-34146Local ID: 84337867-8adc-4cc5-906d-be73174a0b07ISBN: 978-1-4799-4033-2OAI: oai:DiVA.org:ltu-34146DiVA: diva2:1007396
Annual Conference of the IEEE Industrial Electronics Society : 29/10/2014 - 01/11/2014
Godkänd; 2015; 20140623 (geonik)2016-09-302016-09-30Bibliographically approved