Feature selection techniques for increasing reliability of fault diagnosis of bearings

MdR. Islam; M.M.M. Islam; J.-M. Kim

doi:10.1109/ICECE.2016.7853940

Feature selection techniques for increasing reliability of fault diagnosis of bearings

MdR. Islam, M.M.M. Islam, J.-M. Kim

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

11 Citations (Scopus)

Abstract

Features selection (FS) techniques have an apparent need in many complex engineering applications especially the bearing fault diagnosis of low-speed industrial motor. The main goal of an FS algorithm is to select the most discriminant features subset from a high-dimension features vector that increases the model performance by reducing the redundant and irrelevant fault features. This paper proposes an efficient fault diagnosis model of bearing by incorporating the optimal feature selection approach for increasing the reliability of fault diagnosis of bearing. Also, this paper investigates the feature selection approaches including sequential forward selection (SFS), sequential floating forward selection (SFFS), and genetic algorithm (GA) for identifying the most discriminant subset. The effectiveness of this discriminant features subset is verified with a low-speed bearing fault diagnosis application for identifying bearing failures. The experimental shows up-to-mark diagnosis performance using GA based optimal feature selection method.

Original language	English
Title of host publication	Proceedings of 9th International Conference on Electrical and Computer Engineering, ICECE 2016
Publisher	IEEE
Pages	1-4
Number of pages	4
ISBN (Electronic)	978-1-5090-2963-1, 978-1-5090-2962-4
ISBN (Print)	978-1-5090-2964-8
DOIs	https://doi.org/10.1109/ICECE.2016.7853940
Publication status	Published (in print/issue) - 16 Feb 2017
Event	9th International Conference on Electrical and Computer Engineering - Dhaka, Bangladesh Duration: 20 Dec 2016 → 22 Dec 2016 Conference number: 2016 https://ieeexplore.ieee.org/xpl/conhome/7845247/proceeding

Conference

Conference	9th International Conference on Electrical and Computer Engineering
Abbreviated title	ICECE
Country/Territory	Bangladesh
City	Dhaka
Period	20/12/16 → 22/12/16
Internet address	https://ieeexplore.ieee.org/xpl/conhome/7845247/proceeding

Keywords

Acoustic emission (AE)
signal processing
feature selection
machine learning
Fault detection and diagnosis

Access to Document

10.1109/ICECE.2016.7853940

Cite this

@inproceedings{79e78847da73473991f0998eb6d5dba7,

title = "Feature selection techniques for increasing reliability of fault diagnosis of bearings",

abstract = "Features selection (FS) techniques have an apparent need in many complex engineering applications especially the bearing fault diagnosis of low-speed industrial motor. The main goal of an FS algorithm is to select the most discriminant features subset from a high-dimension features vector that increases the model performance by reducing the redundant and irrelevant fault features. This paper proposes an efficient fault diagnosis model of bearing by incorporating the optimal feature selection approach for increasing the reliability of fault diagnosis of bearing. Also, this paper investigates the feature selection approaches including sequential forward selection (SFS), sequential floating forward selection (SFFS), and genetic algorithm (GA) for identifying the most discriminant subset. The effectiveness of this discriminant features subset is verified with a low-speed bearing fault diagnosis application for identifying bearing failures. The experimental shows up-to-mark diagnosis performance using GA based optimal feature selection method.",

keywords = "Acoustic emission (AE), signal processing, feature selection, machine learning, Fault detection and diagnosis",

author = "MdR. Islam and M.M.M. Islam and J.-M. Kim",

year = "2017",

month = feb,

day = "16",

doi = "10.1109/ICECE.2016.7853940",

language = "English",

isbn = "978-1-5090-2964-8",

pages = "1--4",

booktitle = "Proceedings of 9th International Conference on Electrical and Computer Engineering, ICECE 2016",

publisher = "IEEE",

address = "United States",

note = "9th International Conference on Electrical and Computer Engineering , ICECE ; Conference date: 20-12-2016 Through 22-12-2016",

url = "https://ieeexplore.ieee.org/xpl/conhome/7845247/proceeding",

}

Islam, M, Islam, MMM & Kim, J-M 2017, Feature selection techniques for increasing reliability of fault diagnosis of bearings. in Proceedings of 9th International Conference on Electrical and Computer Engineering, ICECE 2016. IEEE, pp. 1-4, 9th International Conference on Electrical and Computer Engineering , Dhaka, Bangladesh, 20/12/16. https://doi.org/10.1109/ICECE.2016.7853940

TY - GEN

T1 - Feature selection techniques for increasing reliability of fault diagnosis of bearings

AU - Islam, MdR.

AU - Islam, M.M.M.

AU - Kim, J.-M.

N1 - Conference code: 2016

PY - 2017/2/16

Y1 - 2017/2/16

N2 - Features selection (FS) techniques have an apparent need in many complex engineering applications especially the bearing fault diagnosis of low-speed industrial motor. The main goal of an FS algorithm is to select the most discriminant features subset from a high-dimension features vector that increases the model performance by reducing the redundant and irrelevant fault features. This paper proposes an efficient fault diagnosis model of bearing by incorporating the optimal feature selection approach for increasing the reliability of fault diagnosis of bearing. Also, this paper investigates the feature selection approaches including sequential forward selection (SFS), sequential floating forward selection (SFFS), and genetic algorithm (GA) for identifying the most discriminant subset. The effectiveness of this discriminant features subset is verified with a low-speed bearing fault diagnosis application for identifying bearing failures. The experimental shows up-to-mark diagnosis performance using GA based optimal feature selection method.

AB - Features selection (FS) techniques have an apparent need in many complex engineering applications especially the bearing fault diagnosis of low-speed industrial motor. The main goal of an FS algorithm is to select the most discriminant features subset from a high-dimension features vector that increases the model performance by reducing the redundant and irrelevant fault features. This paper proposes an efficient fault diagnosis model of bearing by incorporating the optimal feature selection approach for increasing the reliability of fault diagnosis of bearing. Also, this paper investigates the feature selection approaches including sequential forward selection (SFS), sequential floating forward selection (SFFS), and genetic algorithm (GA) for identifying the most discriminant subset. The effectiveness of this discriminant features subset is verified with a low-speed bearing fault diagnosis application for identifying bearing failures. The experimental shows up-to-mark diagnosis performance using GA based optimal feature selection method.

KW - Acoustic emission (AE)

KW - signal processing

KW - feature selection

KW - machine learning

KW - Fault detection and diagnosis

UR - http://www.scopus.com/inward/record.url?eid=2-s2.0-85016187845&partnerID=MN8TOARS

U2 - 10.1109/ICECE.2016.7853940

DO - 10.1109/ICECE.2016.7853940

M3 - Conference contribution

SN - 978-1-5090-2964-8

SP - 1

EP - 4

BT - Proceedings of 9th International Conference on Electrical and Computer Engineering, ICECE 2016

PB - IEEE

T2 - 9th International Conference on Electrical and Computer Engineering

Y2 - 20 December 2016 through 22 December 2016

ER -

Feature selection techniques for increasing reliability of fault diagnosis of bearings

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this