Abstract Although reconstructed phase space is one of the most powerful methods for analyzing a time series, it can fail in fault diagnosis of an induction motor when the appropriate pre-processing is not performed. Therefore, boundary analysis based a new feature extraction method in phase space is proposed for diagnosis of induction motor faults. The proposed approach requires the measurement of one phase current signal to construct the phase space representation. Each phase space is converted into an image, and the boundary of each image is extracted by a boundary detection algorithm. A fuzzy decision tree has been designed to detect broken rotor bars and broken connector faults. The results indicate that the proposed approach has a higher recognition rate than other methods on the same dataset.
Description
An approach for automated fault diagnosis based on a fuzzy decision tree and boundary analysis of a reconstructed phase space
%0 Journal Article
%1 Aydin2014220
%A Aydin, Ilhan
%A Karakose, Mehmet
%A Akin, Erhan
%D 2014
%J \ISA\ Transactions
%K myown paper
%N 2
%P 220 - 229
%R http://dx.doi.org/10.1016/j.isatra.2013.11.004
%T An approach for automated fault diagnosis based on a fuzzy decision tree and boundary analysis of a reconstructed phase space
%U http://www.sciencedirect.com/science/article/pii/S0019057813001936
%V 53
%X Abstract Although reconstructed phase space is one of the most powerful methods for analyzing a time series, it can fail in fault diagnosis of an induction motor when the appropriate pre-processing is not performed. Therefore, boundary analysis based a new feature extraction method in phase space is proposed for diagnosis of induction motor faults. The proposed approach requires the measurement of one phase current signal to construct the phase space representation. Each phase space is converted into an image, and the boundary of each image is extracted by a boundary detection algorithm. A fuzzy decision tree has been designed to detect broken rotor bars and broken connector faults. The results indicate that the proposed approach has a higher recognition rate than other methods on the same dataset.
@article{Aydin2014220,
abstract = {Abstract Although reconstructed phase space is one of the most powerful methods for analyzing a time series, it can fail in fault diagnosis of an induction motor when the appropriate pre-processing is not performed. Therefore, boundary analysis based a new feature extraction method in phase space is proposed for diagnosis of induction motor faults. The proposed approach requires the measurement of one phase current signal to construct the phase space representation. Each phase space is converted into an image, and the boundary of each image is extracted by a boundary detection algorithm. A fuzzy decision tree has been designed to detect broken rotor bars and broken connector faults. The results indicate that the proposed approach has a higher recognition rate than other methods on the same dataset. },
added-at = {2016-11-15T22:49:15.000+0100},
author = {Aydin, Ilhan and Karakose, Mehmet and Akin, Erhan},
biburl = {https://www.bibsonomy.org/bibtex/23b32e33725879512b43656d51c0c1d8d/iaydin},
description = {An approach for automated fault diagnosis based on a fuzzy decision tree and boundary analysis of a reconstructed phase space},
doi = {http://dx.doi.org/10.1016/j.isatra.2013.11.004},
interhash = {04955138ef03e89aa6b28611bc92a76a},
intrahash = {3b32e33725879512b43656d51c0c1d8d},
issn = {0019-0578},
journal = {\{ISA\} Transactions },
keywords = {myown paper},
number = 2,
pages = {220 - 229},
timestamp = {2016-11-15T22:49:15.000+0100},
title = {An approach for automated fault diagnosis based on a fuzzy decision tree and boundary analysis of a reconstructed phase space },
url = {http://www.sciencedirect.com/science/article/pii/S0019057813001936},
volume = 53,
year = 2014
}