A Fault Diagnosis Method based on Improved Synthetic Minority Oversampling Technique and SVM for Unbalanced Data

Minghong Han; Yaman Wu; Yunfeng Huang; Yumin Wang

doi:10.1088/1757-899X/1043/5/052034

A Fault Diagnosis Method based on Improved Synthetic Minority Oversampling Technique and SVM for Unbalanced Data

Minghong Han
, Yaman Wu
, Yunfeng Huang
, Yumin Wang

School of Reliability and Systems Engineering

Beihang University

Research output: Contribution to journal › Conference article › peer-review

7 Scopus citations

Abstract

Equipment usually breaks down suddenly and irregularly, so most of the data sets obtained for fault diagnosis have unbalanced characteristics, and the amount of data varies greatly from different fault types. In this paper, three problems in the application of synthetic minority oversampling technique (SMOTE) are studied, and the improved SMOTE algorithm combined with support vector machine (SVM) is proposed. The validity of the model is verified by CWRU bearing data compared with SVM and SMOTE+SVM methods, and the result of fault diagnosis is satisfactory.

Original language	English
Article number	052034
Journal	IOP Conference Series: Materials Science and Engineering
Volume	1043
Issue number	5
DOIs	https://doi.org/10.1088/1757-899X/1043/5/052034
State	Published - 2 Feb 2021
Event	10th International Conference on Quality, Reliability, Risk, Maintenance,and Safety Engineering, QR2MSE 2020 - Xi'an, Shaanxi, China Duration: 8 Oct 2020 → 11 Oct 2020

Access to Document

10.1088/1757-899X/1043/5/052034

Cite this

@article{6cbac44c5e6446ada11e30af6ca0283c,

title = "A Fault Diagnosis Method based on Improved Synthetic Minority Oversampling Technique and SVM for Unbalanced Data",

abstract = "Equipment usually breaks down suddenly and irregularly, so most of the data sets obtained for fault diagnosis have unbalanced characteristics, and the amount of data varies greatly from different fault types. In this paper, three problems in the application of synthetic minority oversampling technique (SMOTE) are studied, and the improved SMOTE algorithm combined with support vector machine (SVM) is proposed. The validity of the model is verified by CWRU bearing data compared with SVM and SMOTE+SVM methods, and the result of fault diagnosis is satisfactory.",

author = "Minghong Han and Yaman Wu and Yunfeng Huang and Yumin Wang",

note = "Publisher Copyright: {\textcopyright} Published under licence by IOP Publishing Ltd.; 10th International Conference on Quality, Reliability, Risk, Maintenance,and Safety Engineering, QR2MSE 2020 ; Conference date: 08-10-2020 Through 11-10-2020",

year = "2021",

month = feb,

day = "2",

doi = "10.1088/1757-899X/1043/5/052034",

language = "英语",

volume = "1043",

journal = "IOP Conference Series: Materials Science and Engineering",

issn = "1757-8981",

publisher = "IOP Publishing Ltd.",

number = "5",

}

TY - JOUR

T1 - A Fault Diagnosis Method based on Improved Synthetic Minority Oversampling Technique and SVM for Unbalanced Data

AU - Han, Minghong

AU - Wu, Yaman

AU - Huang, Yunfeng

AU - Wang, Yumin

N1 - Publisher Copyright: © Published under licence by IOP Publishing Ltd.

PY - 2021/2/2

Y1 - 2021/2/2

N2 - Equipment usually breaks down suddenly and irregularly, so most of the data sets obtained for fault diagnosis have unbalanced characteristics, and the amount of data varies greatly from different fault types. In this paper, three problems in the application of synthetic minority oversampling technique (SMOTE) are studied, and the improved SMOTE algorithm combined with support vector machine (SVM) is proposed. The validity of the model is verified by CWRU bearing data compared with SVM and SMOTE+SVM methods, and the result of fault diagnosis is satisfactory.

AB - Equipment usually breaks down suddenly and irregularly, so most of the data sets obtained for fault diagnosis have unbalanced characteristics, and the amount of data varies greatly from different fault types. In this paper, three problems in the application of synthetic minority oversampling technique (SMOTE) are studied, and the improved SMOTE algorithm combined with support vector machine (SVM) is proposed. The validity of the model is verified by CWRU bearing data compared with SVM and SMOTE+SVM methods, and the result of fault diagnosis is satisfactory.

UR - https://www.scopus.com/pages/publications/85101641343

U2 - 10.1088/1757-899X/1043/5/052034

DO - 10.1088/1757-899X/1043/5/052034

M3 - 会议文章

AN - SCOPUS:85101641343

SN - 1757-8981

VL - 1043

JO - IOP Conference Series: Materials Science and Engineering

JF - IOP Conference Series: Materials Science and Engineering

IS - 5

M1 - 052034

T2 - 10th International Conference on Quality, Reliability, Risk, Maintenance,and Safety Engineering, QR2MSE 2020

Y2 - 8 October 2020 through 11 October 2020

ER -

A Fault Diagnosis Method based on Improved Synthetic Minority Oversampling Technique and SVM for Unbalanced Data

Abstract

Access to Document

Other files and links

Fingerprint

Cite this