Reconstruction independent component analysis-based methods for intelligent fault diagnosis

Yaguo Lei; Hongkai Shan; Feng Jia; Jing Lin

doi:10.1109/CSCWD.2016.7565996

Reconstruction independent component analysis-based methods for intelligent fault diagnosis

Yaguo Lei
, Hongkai Shan
, Feng Jia
, Jing Lin

School of Mechanical Engineering

Xi'an Jiaotong University

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

6 Scopus citations

Abstract

Based on machine learning techniques, this paper presents a novel intelligent fault diagnosis method, which is an integrated framework concerning reconstruction independent component analysis (RICA) and multiclass relevance vector machine (MRVM). In this method, the RICA is first used to automatically extract features from raw vibration signals. Then, the learned features are used as the input data of MRVM for the classification of different health conditions of machines. The proposed method is applied to the fault diagnosis of locomotive rolling bearings. According to the diagnosis results, it is verified that the proposed method is able to reliably classify different health conditions. By comparing with diagnosis method based on time-domain statistical analysis and wavelet transformation, the proposed method shows its superiority in automatic features extraction from raw signals.

Original language	English
Title of host publication	Proceedings of the 2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016
Editors	Xiaoping P. Liu, Jianming Yong, Jean-Paul Barthes, Weiming Shen, Chunsheng Yang, Junzhou Luo, Limin Chen
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	245-250
Number of pages	6
ISBN (Electronic)	9781509019151
DOIs	https://doi.org/10.1109/CSCWD.2016.7565996
State	Published - 13 Sep 2016
Event	20th IEEE International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016 - Nanchang, China Duration: 4 May 2016 → 6 May 2016

Publication series

Name	Proceedings of the 2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016

Conference

Conference	20th IEEE International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016
Country/Territory	China
City	Nanchang
Period	4/05/16 → 6/05/16

Keywords

automatic features extraction
intelligent fault diagnosis
multiclass relevance vector machine
reconstruction independent component analysis

Access to Document

10.1109/CSCWD.2016.7565996

Cite this

Lei, Y., Shan, H., Jia, F., & Lin, J. (2016). Reconstruction independent component analysis-based methods for intelligent fault diagnosis. In X. P. Liu, J. Yong, J.-P. Barthes, W. Shen, C. Yang, J. Luo, & L. Chen (Eds.), Proceedings of the 2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016 (pp. 245-250). Article 7565996 (Proceedings of the 2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CSCWD.2016.7565996

Lei, Yaguo ; Shan, Hongkai ; Jia, Feng et al. / Reconstruction independent component analysis-based methods for intelligent fault diagnosis. Proceedings of the 2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016. editor / Xiaoping P. Liu ; Jianming Yong ; Jean-Paul Barthes ; Weiming Shen ; Chunsheng Yang ; Junzhou Luo ; Limin Chen. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 245-250 (Proceedings of the 2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016).

@inproceedings{8b885a9acdd3476b8bb813497ee8a8bf,

title = "Reconstruction independent component analysis-based methods for intelligent fault diagnosis",

abstract = "Based on machine learning techniques, this paper presents a novel intelligent fault diagnosis method, which is an integrated framework concerning reconstruction independent component analysis (RICA) and multiclass relevance vector machine (MRVM). In this method, the RICA is first used to automatically extract features from raw vibration signals. Then, the learned features are used as the input data of MRVM for the classification of different health conditions of machines. The proposed method is applied to the fault diagnosis of locomotive rolling bearings. According to the diagnosis results, it is verified that the proposed method is able to reliably classify different health conditions. By comparing with diagnosis method based on time-domain statistical analysis and wavelet transformation, the proposed method shows its superiority in automatic features extraction from raw signals.",

keywords = "automatic features extraction, intelligent fault diagnosis, multiclass relevance vector machine, reconstruction independent component analysis",

author = "Yaguo Lei and Hongkai Shan and Feng Jia and Jing Lin",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 20th IEEE International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016 ; Conference date: 04-05-2016 Through 06-05-2016",

year = "2016",

month = sep,

day = "13",

doi = "10.1109/CSCWD.2016.7565996",

language = "英语",

series = "Proceedings of the 2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016",

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

pages = "245--250",

editor = "Liu, \{Xiaoping P.\} and Jianming Yong and Jean-Paul Barthes and Weiming Shen and Chunsheng Yang and Junzhou Luo and Limin Chen",

booktitle = "Proceedings of the 2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016",

}

Lei, Y, Shan, H, Jia, F & Lin, J 2016, Reconstruction independent component analysis-based methods for intelligent fault diagnosis. in XP Liu, J Yong, J-P Barthes, W Shen, C Yang, J Luo & L Chen (eds), Proceedings of the 2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016., 7565996, Proceedings of the 2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016, Institute of Electrical and Electronics Engineers Inc., pp. 245-250, 20th IEEE International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016, Nanchang, China, 4/05/16. https://doi.org/10.1109/CSCWD.2016.7565996

Reconstruction independent component analysis-based methods for intelligent fault diagnosis. / Lei, Yaguo; Shan, Hongkai; Jia, Feng et al.
Proceedings of the 2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016. ed. / Xiaoping P. Liu; Jianming Yong; Jean-Paul Barthes; Weiming Shen; Chunsheng Yang; Junzhou Luo; Limin Chen. Institute of Electrical and Electronics Engineers Inc., 2016. p. 245-250 7565996 (Proceedings of the 2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016).

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

TY - GEN

T1 - Reconstruction independent component analysis-based methods for intelligent fault diagnosis

AU - Lei, Yaguo

AU - Shan, Hongkai

AU - Jia, Feng

AU - Lin, Jing

PY - 2016/9/13

Y1 - 2016/9/13

N2 - Based on machine learning techniques, this paper presents a novel intelligent fault diagnosis method, which is an integrated framework concerning reconstruction independent component analysis (RICA) and multiclass relevance vector machine (MRVM). In this method, the RICA is first used to automatically extract features from raw vibration signals. Then, the learned features are used as the input data of MRVM for the classification of different health conditions of machines. The proposed method is applied to the fault diagnosis of locomotive rolling bearings. According to the diagnosis results, it is verified that the proposed method is able to reliably classify different health conditions. By comparing with diagnosis method based on time-domain statistical analysis and wavelet transformation, the proposed method shows its superiority in automatic features extraction from raw signals.

AB - Based on machine learning techniques, this paper presents a novel intelligent fault diagnosis method, which is an integrated framework concerning reconstruction independent component analysis (RICA) and multiclass relevance vector machine (MRVM). In this method, the RICA is first used to automatically extract features from raw vibration signals. Then, the learned features are used as the input data of MRVM for the classification of different health conditions of machines. The proposed method is applied to the fault diagnosis of locomotive rolling bearings. According to the diagnosis results, it is verified that the proposed method is able to reliably classify different health conditions. By comparing with diagnosis method based on time-domain statistical analysis and wavelet transformation, the proposed method shows its superiority in automatic features extraction from raw signals.

KW - automatic features extraction

KW - intelligent fault diagnosis

KW - multiclass relevance vector machine

KW - reconstruction independent component analysis

UR - https://www.scopus.com/pages/publications/84991716562

U2 - 10.1109/CSCWD.2016.7565996

DO - 10.1109/CSCWD.2016.7565996

M3 - 会议稿件

AN - SCOPUS:84991716562

T3 - Proceedings of the 2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016

SP - 245

EP - 250

BT - Proceedings of the 2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016

A2 - Liu, Xiaoping P.

A2 - Yong, Jianming

A2 - Barthes, Jean-Paul

A2 - Shen, Weiming

A2 - Yang, Chunsheng

A2 - Luo, Junzhou

A2 - Chen, Limin

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 20th IEEE International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016

Y2 - 4 May 2016 through 6 May 2016

ER -

Lei Y, Shan H, Jia F, Lin J. Reconstruction independent component analysis-based methods for intelligent fault diagnosis. In Liu XP, Yong J, Barthes JP, Shen W, Yang C, Luo J, Chen L, editors, Proceedings of the 2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 245-250. 7565996. (Proceedings of the 2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2016). doi: 10.1109/CSCWD.2016.7565996

Reconstruction independent component analysis-based methods for intelligent fault diagnosis

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this