A Novel Framework for Centrifugal Pump Fault Diagnosis by Selecting Fault Characteristic Coefficients of Walsh Transform and Cosine Linear Discriminant Analysis

In this paper, we propose a three-stage lightweight framework for centrifugal pump fault diagnosis. First, the centrifugal pump vibration signatures are fast transformed using a Walsh transform, and Walsh spectra are obtained. To overcome the hefty noise produced by macro-structural vibration, the p...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Zahoor Ahmad, Akhand Rai, Md Junayed Hasan, Cheol Hong Kim, Jong-Myon Kim
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Centrifugal pump cosine linear discriminant analysis fault diagnosis walsh transform Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/f4d26df1f24045508ee8c20f2cdd9a62
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f4d26df1f24045508ee8c20f2cdd9a62
record_format	dspace
spelling	oai:doaj.org-article:f4d26df1f24045508ee8c20f2cdd9a622021-11-18T00:01:20ZA Novel Framework for Centrifugal Pump Fault Diagnosis by Selecting Fault Characteristic Coefficients of Walsh Transform and Cosine Linear Discriminant Analysis2169-353610.1109/ACCESS.2021.3124903https://doaj.org/article/f4d26df1f24045508ee8c20f2cdd9a622021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9598825/https://doaj.org/toc/2169-3536In this paper, we propose a three-stage lightweight framework for centrifugal pump fault diagnosis. First, the centrifugal pump vibration signatures are fast transformed using a Walsh transform, and Walsh spectra are obtained. To overcome the hefty noise produced by macro-structural vibration, the proposed method selects the fault characteristic coefficients of the Walsh spectrum. In the second stage, statistical features in the time and Walsh spectrum domain are extracted from the selected fault characteristic coefficients of the Walsh transform. These extracted raw statistical features result in a hybrid high-dimensional space. Not all these extracted features help illustrate the condition of the centrifugal pump. To overcome this issue, novel cosine linear discriminant analysis is introduced in the third stage. Cosine linear discriminant analysis is a dimensionality reduction technique which selects similar interclass features and adds them to the illustrative feature pool, which contains key discriminant features that represent the condition of the centrifugal pump. To achieve maximum between-class separation, linear discriminant analysis is then applied to the illustrative feature pool. This combination of illustrative feature pool creation and linear discriminant analysis forms the proposed application of cosine linear discriminant analysis. The reduced discriminant feature set obtained from cosine linear discriminant analysis is then given as an input to the K-nearest neighbor classifier for classification. The classification results obtained from the proposed method outperform the previously presented state-of-the-art methods in terms of fault classification accuracy.Zahoor AhmadAkhand RaiMd Junayed HasanCheol Hong KimJong-Myon KimIEEEarticleCentrifugal pumpcosine linear discriminant analysisfault diagnosiswalsh transformElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 150128-150141 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Centrifugal pump cosine linear discriminant analysis fault diagnosis walsh transform Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Centrifugal pump cosine linear discriminant analysis fault diagnosis walsh transform Electrical engineering. Electronics. Nuclear engineering TK1-9971 Zahoor Ahmad Akhand Rai Md Junayed Hasan Cheol Hong Kim Jong-Myon Kim A Novel Framework for Centrifugal Pump Fault Diagnosis by Selecting Fault Characteristic Coefficients of Walsh Transform and Cosine Linear Discriminant Analysis
description	In this paper, we propose a three-stage lightweight framework for centrifugal pump fault diagnosis. First, the centrifugal pump vibration signatures are fast transformed using a Walsh transform, and Walsh spectra are obtained. To overcome the hefty noise produced by macro-structural vibration, the proposed method selects the fault characteristic coefficients of the Walsh spectrum. In the second stage, statistical features in the time and Walsh spectrum domain are extracted from the selected fault characteristic coefficients of the Walsh transform. These extracted raw statistical features result in a hybrid high-dimensional space. Not all these extracted features help illustrate the condition of the centrifugal pump. To overcome this issue, novel cosine linear discriminant analysis is introduced in the third stage. Cosine linear discriminant analysis is a dimensionality reduction technique which selects similar interclass features and adds them to the illustrative feature pool, which contains key discriminant features that represent the condition of the centrifugal pump. To achieve maximum between-class separation, linear discriminant analysis is then applied to the illustrative feature pool. This combination of illustrative feature pool creation and linear discriminant analysis forms the proposed application of cosine linear discriminant analysis. The reduced discriminant feature set obtained from cosine linear discriminant analysis is then given as an input to the K-nearest neighbor classifier for classification. The classification results obtained from the proposed method outperform the previously presented state-of-the-art methods in terms of fault classification accuracy.
format	article
author	Zahoor Ahmad Akhand Rai Md Junayed Hasan Cheol Hong Kim Jong-Myon Kim
author_facet	Zahoor Ahmad Akhand Rai Md Junayed Hasan Cheol Hong Kim Jong-Myon Kim
author_sort	Zahoor Ahmad
title	A Novel Framework for Centrifugal Pump Fault Diagnosis by Selecting Fault Characteristic Coefficients of Walsh Transform and Cosine Linear Discriminant Analysis
title_short	A Novel Framework for Centrifugal Pump Fault Diagnosis by Selecting Fault Characteristic Coefficients of Walsh Transform and Cosine Linear Discriminant Analysis
title_full	A Novel Framework for Centrifugal Pump Fault Diagnosis by Selecting Fault Characteristic Coefficients of Walsh Transform and Cosine Linear Discriminant Analysis
title_fullStr	A Novel Framework for Centrifugal Pump Fault Diagnosis by Selecting Fault Characteristic Coefficients of Walsh Transform and Cosine Linear Discriminant Analysis
title_full_unstemmed	A Novel Framework for Centrifugal Pump Fault Diagnosis by Selecting Fault Characteristic Coefficients of Walsh Transform and Cosine Linear Discriminant Analysis
title_sort	novel framework for centrifugal pump fault diagnosis by selecting fault characteristic coefficients of walsh transform and cosine linear discriminant analysis
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/f4d26df1f24045508ee8c20f2cdd9a62
work_keys_str_mv	AT zahoorahmad anovelframeworkforcentrifugalpumpfaultdiagnosisbyselectingfaultcharacteristiccoefficientsofwalshtransformandcosinelineardiscriminantanalysis AT akhandrai anovelframeworkforcentrifugalpumpfaultdiagnosisbyselectingfaultcharacteristiccoefficientsofwalshtransformandcosinelineardiscriminantanalysis AT mdjunayedhasan anovelframeworkforcentrifugalpumpfaultdiagnosisbyselectingfaultcharacteristiccoefficientsofwalshtransformandcosinelineardiscriminantanalysis AT cheolhongkim anovelframeworkforcentrifugalpumpfaultdiagnosisbyselectingfaultcharacteristiccoefficientsofwalshtransformandcosinelineardiscriminantanalysis AT jongmyonkim anovelframeworkforcentrifugalpumpfaultdiagnosisbyselectingfaultcharacteristiccoefficientsofwalshtransformandcosinelineardiscriminantanalysis AT zahoorahmad novelframeworkforcentrifugalpumpfaultdiagnosisbyselectingfaultcharacteristiccoefficientsofwalshtransformandcosinelineardiscriminantanalysis AT akhandrai novelframeworkforcentrifugalpumpfaultdiagnosisbyselectingfaultcharacteristiccoefficientsofwalshtransformandcosinelineardiscriminantanalysis AT mdjunayedhasan novelframeworkforcentrifugalpumpfaultdiagnosisbyselectingfaultcharacteristiccoefficientsofwalshtransformandcosinelineardiscriminantanalysis AT cheolhongkim novelframeworkforcentrifugalpumpfaultdiagnosisbyselectingfaultcharacteristiccoefficientsofwalshtransformandcosinelineardiscriminantanalysis AT jongmyonkim novelframeworkforcentrifugalpumpfaultdiagnosisbyselectingfaultcharacteristiccoefficientsofwalshtransformandcosinelineardiscriminantanalysis
_version_	1718425261535395840

A Novel Framework for Centrifugal Pump Fault Diagnosis by Selecting Fault Characteristic Coefficients of Walsh Transform and Cosine Linear Discriminant Analysis

Ejemplares similares