Fault diagnosis of rolling bearing with small samples based on wavelet packet theory and random forest

Hongmei Yan; Huina Mu; Xiaojian Yi; Yuanyuan Yang; Guangliang Chen

doi:10.1109/SDPC.2019.00062

Fault diagnosis of rolling bearing with small samples based on wavelet packet theory and random forest

Hongmei Yan, Huina Mu, Xiaojian Yi^*, Yuanyuan Yang, Guangliang Chen

^*Corresponding author for this work

School of Mechatronical Engineering

Beijing Institute of Technology

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

3 Citations (Scopus)

Abstract

In order to solve the problem of non-stationary vibration signals of rolling bearings and large sample size, a small sample fault diagnosis method based on wavelet packet theory and Random Forest algorithm was proposed in this paper. Firstly, the signal was preprocessed, then three-layer wavelet packet decomposition was carried out, and the decomposition coefficients are extracted as feature vectors, which were used to train BP Neural Network, Support Vector Machine (SVM) and Random Forest model. Through the diagnosis of multi-fault states of rolling bearings, the diagnostic accuracy rates of the three groups of classifiers are respectively 25%, 93.75% and 100%, which proves that Random Forest has better diagnosis effect and robustness for rolling bearings with small samples.

Original language	English
Title of host publication	Proceedings - 2019 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2019
Editors	Chuan Li, Shaohui Zhang, Jianyu Long, Diego Cabrera, Ping Ding
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	305-310
Number of pages	6
ISBN (Electronic)	9781728101996
DOIs	https://doi.org/10.1109/SDPC.2019.00062
Publication status	Published - Aug 2019
Event	2019 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2019 - Beijing, China Duration: 15 Aug 2019 → 17 Aug 2019

Publication series

Name	Proceedings - 2019 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2019

Conference

Conference	2019 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2019
Country/Territory	China
City	Beijing
Period	15/08/19 → 17/08/19

Keywords

Fault Diagnosis; Random Forest
Rolling Bearing
SVM
Wavelet Packet Decomposition

Access to Document

10.1109/SDPC.2019.00062

Cite this

Yan, H., Mu, H., Yi, X., Yang, Y., & Chen, G. (2019). Fault diagnosis of rolling bearing with small samples based on wavelet packet theory and random forest. In C. Li, S. Zhang, J. Long, D. Cabrera, & P. Ding (Eds.), Proceedings - 2019 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2019 (pp. 305-310). Article 9169013 (Proceedings - 2019 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SDPC.2019.00062

Yan, Hongmei ; Mu, Huina ; Yi, Xiaojian et al. / Fault diagnosis of rolling bearing with small samples based on wavelet packet theory and random forest. Proceedings - 2019 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2019. editor / Chuan Li ; Shaohui Zhang ; Jianyu Long ; Diego Cabrera ; Ping Ding. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 305-310 (Proceedings - 2019 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2019).

@inproceedings{df2ed2bef43b4aef98398b33f03677e5,

title = "Fault diagnosis of rolling bearing with small samples based on wavelet packet theory and random forest",

abstract = "In order to solve the problem of non-stationary vibration signals of rolling bearings and large sample size, a small sample fault diagnosis method based on wavelet packet theory and Random Forest algorithm was proposed in this paper. Firstly, the signal was preprocessed, then three-layer wavelet packet decomposition was carried out, and the decomposition coefficients are extracted as feature vectors, which were used to train BP Neural Network, Support Vector Machine (SVM) and Random Forest model. Through the diagnosis of multi-fault states of rolling bearings, the diagnostic accuracy rates of the three groups of classifiers are respectively 25%, 93.75% and 100%, which proves that Random Forest has better diagnosis effect and robustness for rolling bearings with small samples.",

keywords = "Fault Diagnosis; Random Forest, Rolling Bearing, SVM, Wavelet Packet Decomposition",

author = "Hongmei Yan and Huina Mu and Xiaojian Yi and Yuanyuan Yang and Guangliang Chen",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2019 ; Conference date: 15-08-2019 Through 17-08-2019",

year = "2019",

month = aug,

doi = "10.1109/SDPC.2019.00062",

language = "English",

series = "Proceedings - 2019 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "305--310",

editor = "Chuan Li and Shaohui Zhang and Jianyu Long and Diego Cabrera and Ping Ding",

booktitle = "Proceedings - 2019 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2019",

address = "United States",

}

Yan, H, Mu, H , Yi, X, Yang, Y & Chen, G 2019, Fault diagnosis of rolling bearing with small samples based on wavelet packet theory and random forest. in C Li, S Zhang, J Long, D Cabrera & P Ding (eds), Proceedings - 2019 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2019., 9169013, Proceedings - 2019 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2019, Institute of Electrical and Electronics Engineers Inc., pp. 305-310, 2019 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2019, Beijing, China, 15/08/19. https://doi.org/10.1109/SDPC.2019.00062

Fault diagnosis of rolling bearing with small samples based on wavelet packet theory and random forest. / Yan, Hongmei; Mu, Huina ; Yi, Xiaojian et al.
Proceedings - 2019 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2019. ed. / Chuan Li; Shaohui Zhang; Jianyu Long; Diego Cabrera; Ping Ding. Institute of Electrical and Electronics Engineers Inc., 2019. p. 305-310 9169013 (Proceedings - 2019 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2019).

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

TY - GEN

T1 - Fault diagnosis of rolling bearing with small samples based on wavelet packet theory and random forest

AU - Yan, Hongmei

AU - Mu, Huina

AU - Yi, Xiaojian

AU - Yang, Yuanyuan

AU - Chen, Guangliang

PY - 2019/8

Y1 - 2019/8

N2 - In order to solve the problem of non-stationary vibration signals of rolling bearings and large sample size, a small sample fault diagnosis method based on wavelet packet theory and Random Forest algorithm was proposed in this paper. Firstly, the signal was preprocessed, then three-layer wavelet packet decomposition was carried out, and the decomposition coefficients are extracted as feature vectors, which were used to train BP Neural Network, Support Vector Machine (SVM) and Random Forest model. Through the diagnosis of multi-fault states of rolling bearings, the diagnostic accuracy rates of the three groups of classifiers are respectively 25%, 93.75% and 100%, which proves that Random Forest has better diagnosis effect and robustness for rolling bearings with small samples.

AB - In order to solve the problem of non-stationary vibration signals of rolling bearings and large sample size, a small sample fault diagnosis method based on wavelet packet theory and Random Forest algorithm was proposed in this paper. Firstly, the signal was preprocessed, then three-layer wavelet packet decomposition was carried out, and the decomposition coefficients are extracted as feature vectors, which were used to train BP Neural Network, Support Vector Machine (SVM) and Random Forest model. Through the diagnosis of multi-fault states of rolling bearings, the diagnostic accuracy rates of the three groups of classifiers are respectively 25%, 93.75% and 100%, which proves that Random Forest has better diagnosis effect and robustness for rolling bearings with small samples.

KW - Fault Diagnosis; Random Forest

KW - Rolling Bearing

KW - SVM

KW - Wavelet Packet Decomposition

UR - http://www.scopus.com/inward/record.url?scp=85091522709&partnerID=8YFLogxK

U2 - 10.1109/SDPC.2019.00062

DO - 10.1109/SDPC.2019.00062

M3 - Conference contribution

AN - SCOPUS:85091522709

T3 - Proceedings - 2019 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2019

SP - 305

EP - 310

BT - Proceedings - 2019 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2019

A2 - Li, Chuan

A2 - Zhang, Shaohui

A2 - Long, Jianyu

A2 - Cabrera, Diego

A2 - Ding, Ping

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2019

Y2 - 15 August 2019 through 17 August 2019

ER -

Yan H, Mu H , Yi X, Yang Y, Chen G. Fault diagnosis of rolling bearing with small samples based on wavelet packet theory and random forest. In Li C, Zhang S, Long J, Cabrera D, Ding P, editors, Proceedings - 2019 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 305-310. 9169013. (Proceedings - 2019 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2019). doi: 10.1109/SDPC.2019.00062

Fault diagnosis of rolling bearing with small samples based on wavelet packet theory and random forest

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this