Accelerating 2d fault diagnosis of an induction motor using a graphics processing unit

This article was published in the Journal of Applied Mathematics [© 2015 SERSC] and the definite version is available at :http://dx.doi.org/10.14257/ijmue.2015.10.1.32 The Journal's website is at:http://www.sersc.org/journals/IJMUE/vol10_no1_2015/32.pdf

書誌詳細
主要な著者:	Uddin, Jia, Van, Dinh Nguyen, Kim, Jong-Myon
その他の著者:	Department of Computer Science and Engineering, BRAC University
フォーマット:	論文
言語:	English
出版事項:	© 2015 Science and Engineering Research Support Society 2016
主題:	Fault diagnosis Global dominant neighborhood structure (GNS) Graphics processing unit Induction motor Local neighborhood structure (LNS)
オンライン･アクセス:	http://hdl.handle.net/10361/7004

id	10361-7004
record_format	dspace
spelling	10361-70042016-12-27T05:27:21Z Accelerating 2d fault diagnosis of an induction motor using a graphics processing unit Uddin, Jia Van, Dinh Nguyen Kim, Jong-Myon Department of Computer Science and Engineering, BRAC University Fault diagnosis Global dominant neighborhood structure (GNS) Graphics processing unit Induction motor Local neighborhood structure (LNS) This article was published in the Journal of Applied Mathematics [© 2015 SERSC] and the definite version is available at :http://dx.doi.org/10.14257/ijmue.2015.10.1.32 The Journal's website is at:http://www.sersc.org/journals/IJMUE/vol10_no1_2015/32.pdf This paper presents a computationally efficient graphics processing unit (GPU) implementation of a reliable fault diagnosis method using two-dimensional (2D) representation of vibration signals. The fault diagnosis method first converts time-domain vibration signals into 2D gray-level images to exploit texture information from the converted images. Then, the global dominant neighborhood structure (GNS) map is utilized to extract texture features by averaging local neighborhood structure (LNS) maps of central pixels. In addition, the principle component analysis (PCA) algorithm is employed to select only the most dominant features. Finally, the selected features are used as inputs to a one-against-all multi-class support vector machine (OAA-MCSVM) to identify each fault of the induction motor. Despite the fact that the 2D fault diagnosis methodology shows satisfactory classification accuracy, its computational complexity limits its use in real-time applications. To accelerate the 2D fault diagnosis method, this paper utilizes an NVIDIA GeForce GTX 580 GPU, where all tasks are executed in parallel. The experimental results indicate that the proposed GPU-based approach achieves about 118.5 faster operation than the equivalent sequential CPU implementation while maintaining 100% classification accuracy. Published 2016-11-28T04:36:39Z 2016-11-28T04:36:39Z 2015 Article Uddin, J., Nguyen Van, D., & Kim, J. -. (2015). Accelerating 2d fault diagnosis of an induction motor using a graphics processing unit. International Journal of Multimedia and Ubiquitous Engineering, 10(1), 341-352. doi:10.14257/ijmue.2015.10.1.32 19750080 http://hdl.handle.net/10361/7004 :http://dx.doi.org/10.14257/ijmue.2015.10.1.32 en http://www.sersc.org/journals/IJMUE/vol10_no1_2015/32.pdf © 2015 Science and Engineering Research Support Society
institution	Brac University
collection	Institutional Repository
language	English
topic	Fault diagnosis Global dominant neighborhood structure (GNS) Graphics processing unit Induction motor Local neighborhood structure (LNS)
spellingShingle	Fault diagnosis Global dominant neighborhood structure (GNS) Graphics processing unit Induction motor Local neighborhood structure (LNS) Uddin, Jia Van, Dinh Nguyen Kim, Jong-Myon Accelerating 2d fault diagnosis of an induction motor using a graphics processing unit
description	This article was published in the Journal of Applied Mathematics [© 2015 SERSC] and the definite version is available at :http://dx.doi.org/10.14257/ijmue.2015.10.1.32 The Journal's website is at:http://www.sersc.org/journals/IJMUE/vol10_no1_2015/32.pdf
author2	Department of Computer Science and Engineering, BRAC University
author_facet	Department of Computer Science and Engineering, BRAC University Uddin, Jia Van, Dinh Nguyen Kim, Jong-Myon
format	Article
author	Uddin, Jia Van, Dinh Nguyen Kim, Jong-Myon
author_sort	Uddin, Jia
title	Accelerating 2d fault diagnosis of an induction motor using a graphics processing unit
title_short	Accelerating 2d fault diagnosis of an induction motor using a graphics processing unit
title_full	Accelerating 2d fault diagnosis of an induction motor using a graphics processing unit
title_fullStr	Accelerating 2d fault diagnosis of an induction motor using a graphics processing unit
title_full_unstemmed	Accelerating 2d fault diagnosis of an induction motor using a graphics processing unit
title_sort	accelerating 2d fault diagnosis of an induction motor using a graphics processing unit
publisher	© 2015 Science and Engineering Research Support Society
publishDate	2016
url	http://hdl.handle.net/10361/7004
work_keys_str_mv	AT uddinjia accelerating2dfaultdiagnosisofaninductionmotorusingagraphicsprocessingunit AT vandinhnguyen accelerating2dfaultdiagnosisofaninductionmotorusingagraphicsprocessingunit AT kimjongmyon accelerating2dfaultdiagnosisofaninductionmotorusingagraphicsprocessingunit
_version_	1814308665809698816

Accelerating 2d fault diagnosis of an induction motor using a graphics processing unit

類似資料