A Novel Feature Extraction and Fault Detection Technique for the Intelligent Fault Identification of Water Pump Bearings

Muhammad Irfan; Abdullah Saeed Alwadie; Adam Glowacz; Muhammad Awais; Saifur Rahman; Mohammad Kamal Asif Khan; Mohammad Jalalah; Omar Alshorman; Wahyu Caesarendra

doi:10.3390/s21124225

A Novel Feature Extraction and Fault Detection Technique for the Intelligent Fault Identification of Water Pump Bearings

Muhammad Irfan^*, Abdullah Saeed Alwadie, Adam Glowacz, Muhammad Awais, Saifur Rahman, Mohammad Kamal Asif Khan, Mohammad Jalalah, Omar Alshorman, Wahyu Caesarendra

^*Corresponding author for this work

Department of Computer Science

Research output: Contribution to journal › Article › peer-review

1 Downloads (Pure)

Abstract

The reliable and cost-effective condition monitoring of the bearings installed in water pumps is a real challenge in the industry. This paper presents a novel strong feature selection and extraction algorithm (SFSEA) to extract fault-related features from the instantaneous power spectrum (IPS). The three features extracted from the IPS using the SFSEA are fed to an extreme gradient boosting (XBG) classifier to reliably detect and classify the minor bearing faults. The experiments performed on a lab-scale test setup demonstrated classification accuracy up to 100%, which is better than the previously reported fault classification accuracies and indicates the effectiveness of the proposed method.

Original language	English
Article number	e4225
Journal	Sensors
Volume	21
Issue number	12
Early online date	20 Jun 2021
DOIs	https://doi.org/10.3390/s21124225
Publication status	E-pub ahead of print - 20 Jun 2021

Keywords

induction motors
stator current sensing
voltage measurement
instantaneous power measurement
vibration measurement
feature selection

Access to Document

10.3390/s21124225

sensors-21-04225.pdfFinal published version, 3.25 MBLicence: CC BY

Cite this

@article{defce8a63d2244808315cbdf07fc7578,

title = "A Novel Feature Extraction and Fault Detection Technique for the Intelligent Fault Identification of Water Pump Bearings",

abstract = "The reliable and cost-effective condition monitoring of the bearings installed in water pumps is a real challenge in the industry. This paper presents a novel strong feature selection and extraction algorithm (SFSEA) to extract fault-related features from the instantaneous power spectrum (IPS). The three features extracted from the IPS using the SFSEA are fed to an extreme gradient boosting (XBG) classifier to reliably detect and classify the minor bearing faults. The experiments performed on a lab-scale test setup demonstrated classification accuracy up to 100%, which is better than the previously reported fault classification accuracies and indicates the effectiveness of the proposed method.",

keywords = "induction motors, stator current sensing, voltage measurement, instantaneous power measurement, vibration measurement, feature selection",

author = "Muhammad Irfan and Alwadie, {Abdullah Saeed} and Adam Glowacz and Muhammad Awais and Saifur Rahman and Khan, {Mohammad Kamal Asif} and Mohammad Jalalah and Omar Alshorman and Wahyu Caesarendra",

year = "2021",

month = jun,

day = "20",

doi = "10.3390/s21124225",

language = "English",

volume = "21",

journal = "Sensors",

issn = "1424-3210",

publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",

number = "12",

}

A Novel Feature Extraction and Fault Detection Technique for the Intelligent Fault Identification of Water Pump Bearings. / Irfan, Muhammad; Alwadie, Abdullah Saeed; Glowacz, Adam; Awais, Muhammad; Rahman, Saifur; Khan, Mohammad Kamal Asif; Jalalah, Mohammad; Alshorman, Omar; Caesarendra, Wahyu.

In: Sensors, Vol. 21, No. 12, e4225, 20.06.2021.

Research output: Contribution to journal › Article › peer-review

TY - JOUR

T1 - A Novel Feature Extraction and Fault Detection Technique for the Intelligent Fault Identification of Water Pump Bearings

AU - Irfan, Muhammad

AU - Alwadie, Abdullah Saeed

AU - Glowacz, Adam

AU - Awais, Muhammad

AU - Rahman, Saifur

AU - Khan, Mohammad Kamal Asif

AU - Jalalah, Mohammad

AU - Alshorman, Omar

AU - Caesarendra, Wahyu

PY - 2021/6/20

Y1 - 2021/6/20

N2 - The reliable and cost-effective condition monitoring of the bearings installed in water pumps is a real challenge in the industry. This paper presents a novel strong feature selection and extraction algorithm (SFSEA) to extract fault-related features from the instantaneous power spectrum (IPS). The three features extracted from the IPS using the SFSEA are fed to an extreme gradient boosting (XBG) classifier to reliably detect and classify the minor bearing faults. The experiments performed on a lab-scale test setup demonstrated classification accuracy up to 100%, which is better than the previously reported fault classification accuracies and indicates the effectiveness of the proposed method.

AB - The reliable and cost-effective condition monitoring of the bearings installed in water pumps is a real challenge in the industry. This paper presents a novel strong feature selection and extraction algorithm (SFSEA) to extract fault-related features from the instantaneous power spectrum (IPS). The three features extracted from the IPS using the SFSEA are fed to an extreme gradient boosting (XBG) classifier to reliably detect and classify the minor bearing faults. The experiments performed on a lab-scale test setup demonstrated classification accuracy up to 100%, which is better than the previously reported fault classification accuracies and indicates the effectiveness of the proposed method.

KW - induction motors

KW - stator current sensing

KW - voltage measurement

KW - instantaneous power measurement

KW - vibration measurement

KW - feature selection

U2 - 10.3390/s21124225

DO - 10.3390/s21124225

M3 - Article

VL - 21

JO - Sensors

JF - Sensors

SN - 1424-3210

IS - 12

M1 - e4225

ER -

A Novel Feature Extraction and Fault Detection Technique for the Intelligent Fault Identification of Water Pump Bearings

Abstract

Keywords

Access to Document

Fingerprint

Cite this