PSO Optimized ANN Diagnosis of Early Gear Pitting

Jialin Li; Yongzhi Qu; Liu Hong; David He

doi:10.1109/PHM-Chongqing.2018.00185

PSO Optimized ANN Diagnosis of Early Gear Pitting

Jialin Li, Yongzhi Qu, Liu Hong, David He

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

1 Scopus citations

Abstract

Gear pitting diagnosis has always been an important research topic and different diagnostic methods are used. This paper uses artificial neural network (ANN) to diagnose early gear pitting. There are several issues that are inevitable with the application of ANN for diagnosis of early gear pitting: feature extraction, neural network structure optimization, and training stability. This paper proposes a new feature extraction method that uses fast Fourier transform (FFT) to select a number of frequencies in the frequency spectrum and use the frequency amplitudes as the inputs of ANN. The particle swarm optimization (PSO) is used to optimize the initial value of the network to make the training more stable. Furthermore, the performance of the ANN diagnosis under different working conditions are also compared and analyzed in the paper. The proposed method has been validated through the data collected from the gear pitting test experiment. The validation results have shown that the faults diagnosis accuracy could reach 100%, which proves that the proposed method is reasonable.

Original language	English (US)
Title of host publication	Proceedings - 2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018
Editors	Ping Ding, Chuan Li, Shuai Yang, Ping Ding, Rene-Vinicio Sanchez
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1043-1048
Number of pages	6
ISBN (Electronic)	9781538653791
DOIs	https://doi.org/10.1109/PHM-Chongqing.2018.00185
State	Published - Jan 4 2019
Externally published	Yes
Event	2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018 - Chongqing, China Duration: Oct 26 2018 → Oct 28 2018

Publication series

Name	Proceedings - 2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018

Conference

Conference	2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018
Country/Territory	China
City	Chongqing
Period	10/26/18 → 10/28/18

Bibliographical note

Funding Information:
ACKNOWLEDGEMENT Sponsor: NSFC grant no. 51675089.

Publisher Copyright:
© 2018 IEEE.

Keywords

Artificial neural network
FFT
Gear pitting
PSO algorithm

Publisher link

10.1109/PHM-Chongqing.2018.00185

Find It

Find It at U of M Libraries

Cite this

Li, J., Qu, Y., Hong, L., & He, D. (2019). PSO Optimized ANN Diagnosis of Early Gear Pitting. In P. Ding, C. Li, S. Yang, P. Ding, & R.-V. Sanchez (Eds.), Proceedings - 2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018 (pp. 1043-1048). Article 8603493 (Proceedings - 2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PHM-Chongqing.2018.00185

PSO Optimized ANN Diagnosis of Early Gear Pitting. / Li, Jialin; Qu, Yongzhi; Hong, Liu et al.
Proceedings - 2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018. ed. / Ping Ding; Chuan Li; Shuai Yang; Ping Ding; Rene-Vinicio Sanchez. Institute of Electrical and Electronics Engineers Inc., 2019. p. 1043-1048 8603493 (Proceedings - 2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018).

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

Li, J, Qu, Y, Hong, L & He, D 2019, PSO Optimized ANN Diagnosis of Early Gear Pitting. in P Ding, C Li, S Yang, P Ding & R-V Sanchez (eds), Proceedings - 2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018., 8603493, Proceedings - 2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018, Institute of Electrical and Electronics Engineers Inc., pp. 1043-1048, 2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018, Chongqing, China, 10/26/18. https://doi.org/10.1109/PHM-Chongqing.2018.00185

Li J, Qu Y, Hong L, He D. PSO Optimized ANN Diagnosis of Early Gear Pitting. In Ding P, Li C, Yang S, Ding P, Sanchez RV, editors, Proceedings - 2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 1043-1048. 8603493. (Proceedings - 2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018). doi: 10.1109/PHM-Chongqing.2018.00185

Li, Jialin ; Qu, Yongzhi ; Hong, Liu et al. / PSO Optimized ANN Diagnosis of Early Gear Pitting. Proceedings - 2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018. editor / Ping Ding ; Chuan Li ; Shuai Yang ; Ping Ding ; Rene-Vinicio Sanchez. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 1043-1048 (Proceedings - 2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018).

@inproceedings{3b0b51f290f8426c8ef8ca89d6f00ca9,

title = "PSO Optimized ANN Diagnosis of Early Gear Pitting",

abstract = "Gear pitting diagnosis has always been an important research topic and different diagnostic methods are used. This paper uses artificial neural network (ANN) to diagnose early gear pitting. There are several issues that are inevitable with the application of ANN for diagnosis of early gear pitting: feature extraction, neural network structure optimization, and training stability. This paper proposes a new feature extraction method that uses fast Fourier transform (FFT) to select a number of frequencies in the frequency spectrum and use the frequency amplitudes as the inputs of ANN. The particle swarm optimization (PSO) is used to optimize the initial value of the network to make the training more stable. Furthermore, the performance of the ANN diagnosis under different working conditions are also compared and analyzed in the paper. The proposed method has been validated through the data collected from the gear pitting test experiment. The validation results have shown that the faults diagnosis accuracy could reach 100\%, which proves that the proposed method is reasonable.",

keywords = "Artificial neural network, FFT, Gear pitting, PSO algorithm",

author = "Jialin Li and Yongzhi Qu and Liu Hong and David He",

note = "Funding Information: ACKNOWLEDGEMENT Sponsor: NSFC grant no. 51675089. Publisher Copyright: {\textcopyright} 2018 IEEE.; 2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018 ; Conference date: 26-10-2018 Through 28-10-2018",

year = "2019",

month = jan,

day = "4",

doi = "10.1109/PHM-Chongqing.2018.00185",

language = "English (US)",

series = "Proceedings - 2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018",

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

pages = "1043--1048",

editor = "Ping Ding and Chuan Li and Shuai Yang and Ping Ding and Rene-Vinicio Sanchez",

booktitle = "Proceedings - 2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018",

}

TY - GEN

T1 - PSO Optimized ANN Diagnosis of Early Gear Pitting

AU - Li, Jialin

AU - Qu, Yongzhi

AU - Hong, Liu

AU - He, David

PY - 2019/1/4

Y1 - 2019/1/4

N2 - Gear pitting diagnosis has always been an important research topic and different diagnostic methods are used. This paper uses artificial neural network (ANN) to diagnose early gear pitting. There are several issues that are inevitable with the application of ANN for diagnosis of early gear pitting: feature extraction, neural network structure optimization, and training stability. This paper proposes a new feature extraction method that uses fast Fourier transform (FFT) to select a number of frequencies in the frequency spectrum and use the frequency amplitudes as the inputs of ANN. The particle swarm optimization (PSO) is used to optimize the initial value of the network to make the training more stable. Furthermore, the performance of the ANN diagnosis under different working conditions are also compared and analyzed in the paper. The proposed method has been validated through the data collected from the gear pitting test experiment. The validation results have shown that the faults diagnosis accuracy could reach 100%, which proves that the proposed method is reasonable.

AB - Gear pitting diagnosis has always been an important research topic and different diagnostic methods are used. This paper uses artificial neural network (ANN) to diagnose early gear pitting. There are several issues that are inevitable with the application of ANN for diagnosis of early gear pitting: feature extraction, neural network structure optimization, and training stability. This paper proposes a new feature extraction method that uses fast Fourier transform (FFT) to select a number of frequencies in the frequency spectrum and use the frequency amplitudes as the inputs of ANN. The particle swarm optimization (PSO) is used to optimize the initial value of the network to make the training more stable. Furthermore, the performance of the ANN diagnosis under different working conditions are also compared and analyzed in the paper. The proposed method has been validated through the data collected from the gear pitting test experiment. The validation results have shown that the faults diagnosis accuracy could reach 100%, which proves that the proposed method is reasonable.

KW - Artificial neural network

KW - FFT

KW - Gear pitting

KW - PSO algorithm

UR - https://www.scopus.com/pages/publications/85061794652

UR - https://www.scopus.com/inward/citedby.url?scp=85061794652&partnerID=8YFLogxK

U2 - 10.1109/PHM-Chongqing.2018.00185

DO - 10.1109/PHM-Chongqing.2018.00185

M3 - Conference contribution

AN - SCOPUS:85061794652

T3 - Proceedings - 2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018

SP - 1043

EP - 1048

BT - Proceedings - 2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018

A2 - Ding, Ping

A2 - Li, Chuan

A2 - Yang, Shuai

A2 - Ding, Ping

A2 - Sanchez, Rene-Vinicio

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2018 Prognostics and System Health Management Conference, PHM-Chongqing 2018

Y2 - 26 October 2018 through 28 October 2018

ER -

PSO Optimized ANN Diagnosis of Early Gear Pitting

Abstract

Publication series

Conference

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this