Application of DE-ELM in analog circuit fault diagnosis

Lihua Zhang; Qi Qin; Yue Shang; Shaowei Chen; Shuai Zhao

doi:10.1109/PHM.2016.7819874

Application of DE-ELM in analog circuit fault diagnosis

Lihua Zhang, Qi Qin, Yue Shang, Shaowei Chen, Shuai Zhao

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

12 Citations (Scopus)

Abstract

The extreme learning machine (ELM) possesses the advantageous features of the fast learning speed, great generalization performance and high precision. However, the randomness of the parameters will influence its generalization performance and precision greatly. This paper proposes a learning algorithm which is based on the differential evolution extreme learning machine (DE-ELM) for parameter optimization of ELM. It can optimize two parameters, input weights and threshold value, which are random-generated in the network. The experiment selects the elliptic filter circuit to build the fault model. We extract the information of the fault samples using the wavelet packet transformation, then compress the data with the method of principal component analysis. Finally, the DE is applied to optimize the parameters of ELM. The results verified that the proposed method significantly enhances the accuracy of the diagnosis.

Original language	English
Title of host publication	Proceedings of 2016 Prognostics and System Health Management Conference, PHM-Chengdu 2016
Editors	Qiang Miao, Zhaojun Li, Ming J. Zuo, Liudong Xing, Zhigang Tian
Publisher	IEEE Signal Processing Society
Publication date	16 Jan 2017
Article number	7819874
ISBN (Electronic)	9781509027781
DOIs	https://doi.org/10.1109/PHM.2016.7819874
Publication status	Published - 16 Jan 2017
Externally published	Yes
Event	7th IEEE Prognostics and System Health Management Conference, PHM-Chengdu 2016 - Chengdu, Sichuan, China Duration: 19 Oct 2016 → 21 Oct 2016

Conference

Conference	7th IEEE Prognostics and System Health Management Conference, PHM-Chengdu 2016
Country/Territory	China
City	Chengdu, Sichuan
Period	19/10/2016 → 21/10/2016

Series	Proceedings of 2016 Prognostics and System Health Management Conference, PHM-Chengdu 2016

Bibliographical note

Publisher Copyright:
© 2016 IEEE.

Keywords

Differential evolution
Extreme learning machine
Fault diagnosis
Parameter optimization

Access to Document

10.1109/PHM.2016.7819874

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

Zhang, Lihua ; Qin, Qi ; Shang, Yue et al. / Application of DE-ELM in analog circuit fault diagnosis. Proceedings of 2016 Prognostics and System Health Management Conference, PHM-Chengdu 2016. editor / Qiang Miao ; Zhaojun Li ; Ming J. Zuo ; Liudong Xing ; Zhigang Tian. IEEE Signal Processing Society, 2017. (Proceedings of 2016 Prognostics and System Health Management Conference, PHM-Chengdu 2016).

@inproceedings{bc6f0fc5e375446a988cec65e065b4df,

title = "Application of DE-ELM in analog circuit fault diagnosis",

abstract = "The extreme learning machine (ELM) possesses the advantageous features of the fast learning speed, great generalization performance and high precision. However, the randomness of the parameters will influence its generalization performance and precision greatly. This paper proposes a learning algorithm which is based on the differential evolution extreme learning machine (DE-ELM) for parameter optimization of ELM. It can optimize two parameters, input weights and threshold value, which are random-generated in the network. The experiment selects the elliptic filter circuit to build the fault model. We extract the information of the fault samples using the wavelet packet transformation, then compress the data with the method of principal component analysis. Finally, the DE is applied to optimize the parameters of ELM. The results verified that the proposed method significantly enhances the accuracy of the diagnosis.",

keywords = "Differential evolution, Extreme learning machine, Fault diagnosis, Parameter optimization",

author = "Lihua Zhang and Qi Qin and Yue Shang and Shaowei Chen and Shuai Zhao",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 7th IEEE Prognostics and System Health Management Conference, PHM-Chengdu 2016 ; Conference date: 19-10-2016 Through 21-10-2016",

year = "2017",

month = jan,

day = "16",

doi = "10.1109/PHM.2016.7819874",

language = "English",

series = "Proceedings of 2016 Prognostics and System Health Management Conference, PHM-Chengdu 2016",

editor = "Qiang Miao and Zhaojun Li and Zuo, {Ming J.} and Liudong Xing and Zhigang Tian",

booktitle = "Proceedings of 2016 Prognostics and System Health Management Conference, PHM-Chengdu 2016",

publisher = "IEEE Signal Processing Society",

address = "United States",

}

Zhang, L, Qin, Q, Shang, Y, Chen, S & Zhao, S 2017, Application of DE-ELM in analog circuit fault diagnosis. in Q Miao, Z Li, MJ Zuo, L Xing & Z Tian (eds), Proceedings of 2016 Prognostics and System Health Management Conference, PHM-Chengdu 2016., 7819874, IEEE Signal Processing Society, Proceedings of 2016 Prognostics and System Health Management Conference, PHM-Chengdu 2016, 7th IEEE Prognostics and System Health Management Conference, PHM-Chengdu 2016, Chengdu, Sichuan, China, 19/10/2016. https://doi.org/10.1109/PHM.2016.7819874

Application of DE-ELM in analog circuit fault diagnosis. / Zhang, Lihua; Qin, Qi; Shang, Yue et al.
Proceedings of 2016 Prognostics and System Health Management Conference, PHM-Chengdu 2016. ed. / Qiang Miao; Zhaojun Li; Ming J. Zuo; Liudong Xing; Zhigang Tian. IEEE Signal Processing Society, 2017. 7819874 (Proceedings of 2016 Prognostics and System Health Management Conference, PHM-Chengdu 2016).

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - Application of DE-ELM in analog circuit fault diagnosis

AU - Zhang, Lihua

AU - Qin, Qi

AU - Shang, Yue

AU - Chen, Shaowei

AU - Zhao, Shuai

PY - 2017/1/16

Y1 - 2017/1/16

N2 - The extreme learning machine (ELM) possesses the advantageous features of the fast learning speed, great generalization performance and high precision. However, the randomness of the parameters will influence its generalization performance and precision greatly. This paper proposes a learning algorithm which is based on the differential evolution extreme learning machine (DE-ELM) for parameter optimization of ELM. It can optimize two parameters, input weights and threshold value, which are random-generated in the network. The experiment selects the elliptic filter circuit to build the fault model. We extract the information of the fault samples using the wavelet packet transformation, then compress the data with the method of principal component analysis. Finally, the DE is applied to optimize the parameters of ELM. The results verified that the proposed method significantly enhances the accuracy of the diagnosis.

AB - The extreme learning machine (ELM) possesses the advantageous features of the fast learning speed, great generalization performance and high precision. However, the randomness of the parameters will influence its generalization performance and precision greatly. This paper proposes a learning algorithm which is based on the differential evolution extreme learning machine (DE-ELM) for parameter optimization of ELM. It can optimize two parameters, input weights and threshold value, which are random-generated in the network. The experiment selects the elliptic filter circuit to build the fault model. We extract the information of the fault samples using the wavelet packet transformation, then compress the data with the method of principal component analysis. Finally, the DE is applied to optimize the parameters of ELM. The results verified that the proposed method significantly enhances the accuracy of the diagnosis.

KW - Differential evolution

KW - Extreme learning machine

KW - Fault diagnosis

KW - Parameter optimization

UR - http://www.scopus.com/inward/record.url?scp=85015652666&partnerID=8YFLogxK

U2 - 10.1109/PHM.2016.7819874

DO - 10.1109/PHM.2016.7819874

M3 - Article in proceeding

AN - SCOPUS:85015652666

T3 - Proceedings of 2016 Prognostics and System Health Management Conference, PHM-Chengdu 2016

BT - Proceedings of 2016 Prognostics and System Health Management Conference, PHM-Chengdu 2016

A2 - Miao, Qiang

A2 - Li, Zhaojun

A2 - Zuo, Ming J.

A2 - Xing, Liudong

A2 - Tian, Zhigang

PB - IEEE Signal Processing Society

T2 - 7th IEEE Prognostics and System Health Management Conference, PHM-Chengdu 2016

Y2 - 19 October 2016 through 21 October 2016

ER -

Zhang L, Qin Q, Shang Y, Chen S, Zhao S. Application of DE-ELM in analog circuit fault diagnosis. In Miao Q, Li Z, Zuo MJ, Xing L, Tian Z, editors, Proceedings of 2016 Prognostics and System Health Management Conference, PHM-Chengdu 2016. IEEE Signal Processing Society. 2017. 7819874. (Proceedings of 2016 Prognostics and System Health Management Conference, PHM-Chengdu 2016). doi: 10.1109/PHM.2016.7819874

Application of DE-ELM in analog circuit fault diagnosis

Abstract

Conference

Bibliographical note

Keywords

Access to Document

AUB Link

Other files and links

Fingerprint

Cite this