Investigation into LSTM Deep Learning for Induction Motor Fault Diagnosis

Xiaoyu Zhao; Ibrahim Alqatawneh; Mark Lane; Haiyang Li; Yongrui Qin; Fengshou Gu; Andrew D. Ball

doi:10.1007/978-3-030-99075-6_41

Investigation into LSTM Deep Learning for Induction Motor Fault Diagnosis

Xiaoyu Zhao, Ibrahim Alqatawneh, Mark Lane, Haiyang Li, Yongrui Qin, Fengshou Gu, Andrew D. Ball

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

2 Citations (Scopus)

Abstract

As motor faults could lead to unwanted loss in industry, it is important to find out the motor faults in time. Currently, with the popularity and mature application of deep learning, researchers in the field of electrical machine health assessment have begun to focus on deep learning methods. It is hoped that motor fault detection can be achieved with the help of deep learning methods. This paper presents to adopt deep learning methods represented by LSTM neural network for motor fault diagnosis and evaluates on our own experimental platform. Considering two typical motor faults with two different degrees of severity, the results show that the proposed LSTM approach has a high accuracy (98.81%) on motor fault classification. The results also confirm that: (1) adequate effort of preprocessing, including sample length selection in the time domain and frequency band selection in the frequency domain, can significantly improve accuracy and computational efficiency; (2) different faults can be separated through the information in frequency band of 100–1000 Hz, which has not been fully modelled analytically before.

Original language	English
Title of host publication	Proceedings of IncoME-VI and TEPEN 2021
Subtitle of host publication	Performance Engineering and Maintenance Engineering
Editors	Hao Zhang, Guojin Feng, Hongjun Wang, Fengshou Gu, Jyoti K. Sinha
Publisher	Springer, Cham
Pages	505-518
Number of pages	14
Volume	117
ISBN (Electronic)	9783030990756
ISBN (Print)	9783030990749
DOIs	https://doi.org/10.1007/978-3-030-99075-6_41
Publication status	Published - 18 Sep 2022
Event	6th International Conference on Maintenance Engineering, IncoME-VI and the Conference of the Efficiency and Performance Engineering Network, TEPEN 2021 - Hebei University of Technology, Tianjin, China Duration: 20 Oct 2021 → 23 Oct 2021 Conference number: 6 https://tepen.net/conference/tepen2021/

Publication series

Name	Mechanisms and Machine Science
Publisher	Springer
Volume	117
ISSN (Print)	2211-0984
ISSN (Electronic)	2211-0992

Conference

Conference	6th International Conference on Maintenance Engineering, IncoME-VI and the Conference of the Efficiency and Performance Engineering Network, TEPEN 2021
Abbreviated title	TEPEN-2021 and IncoME-VI
Country/Territory	China
City	Tianjin
Period	20/10/21 → 23/10/21
Internet address	https://tepen.net/conference/tepen2021/

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-030-99075-6_41Licence: Unspecified

Cite this

Zhao, X., Alqatawneh, I., Lane, M., Li, H., Qin, Y., Gu, F., & Ball, A. D. (2022). Investigation into LSTM Deep Learning for Induction Motor Fault Diagnosis. In H. Zhang, G. Feng, H. Wang, F. Gu, & J. K. Sinha (Eds.), Proceedings of IncoME-VI and TEPEN 2021 : Performance Engineering and Maintenance Engineering (Vol. 117, pp. 505-518). (Mechanisms and Machine Science; Vol. 117). Springer, Cham. https://doi.org/10.1007/978-3-030-99075-6_41

Zhao, Xiaoyu ; Alqatawneh, Ibrahim ; Lane, Mark et al. / Investigation into LSTM Deep Learning for Induction Motor Fault Diagnosis. Proceedings of IncoME-VI and TEPEN 2021 : Performance Engineering and Maintenance Engineering. editor / Hao Zhang ; Guojin Feng ; Hongjun Wang ; Fengshou Gu ; Jyoti K. Sinha. Vol. 117 Springer, Cham, 2022. pp. 505-518 (Mechanisms and Machine Science).

@inproceedings{cee284f2501749ac82665dd3b2544232,

title = "Investigation into LSTM Deep Learning for Induction Motor Fault Diagnosis",

abstract = "As motor faults could lead to unwanted loss in industry, it is important to find out the motor faults in time. Currently, with the popularity and mature application of deep learning, researchers in the field of electrical machine health assessment have begun to focus on deep learning methods. It is hoped that motor fault detection can be achieved with the help of deep learning methods. This paper presents to adopt deep learning methods represented by LSTM neural network for motor fault diagnosis and evaluates on our own experimental platform. Considering two typical motor faults with two different degrees of severity, the results show that the proposed LSTM approach has a high accuracy (98.81%) on motor fault classification. The results also confirm that: (1) adequate effort of preprocessing, including sample length selection in the time domain and frequency band selection in the frequency domain, can significantly improve accuracy and computational efficiency; (2) different faults can be separated through the information in frequency band of 100–1000 Hz, which has not been fully modelled analytically before.",

keywords = "Deep learning, LSTM, Motor fault diagnosis",

author = "Xiaoyu Zhao and Ibrahim Alqatawneh and Mark Lane and Haiyang Li and Yongrui Qin and Fengshou Gu and Ball, {Andrew D.}",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 6th International Conference on Maintenance Engineering, IncoME-VI and the Conference of the Efficiency and Performance Engineering Network, TEPEN 2021, TEPEN-2021 and IncoME-VI ; Conference date: 20-10-2021 Through 23-10-2021",

year = "2022",

month = sep,

day = "18",

doi = "10.1007/978-3-030-99075-6_41",

language = "English",

isbn = "9783030990749",

volume = "117",

series = "Mechanisms and Machine Science",

publisher = "Springer, Cham",

pages = "505--518",

editor = "Hao Zhang and Guojin Feng and Hongjun Wang and Fengshou Gu and Sinha, {Jyoti K.}",

booktitle = "Proceedings of IncoME-VI and TEPEN 2021",

address = "Switzerland",

url = "https://tepen.net/conference/tepen2021/",

}

Zhao, X, Alqatawneh, I, Lane, M, Li, H, Qin, Y, Gu, F & Ball, AD 2022, Investigation into LSTM Deep Learning for Induction Motor Fault Diagnosis. in H Zhang, G Feng, H Wang, F Gu & JK Sinha (eds), Proceedings of IncoME-VI and TEPEN 2021 : Performance Engineering and Maintenance Engineering. vol. 117, Mechanisms and Machine Science, vol. 117, Springer, Cham, pp. 505-518, 6th International Conference on Maintenance Engineering, IncoME-VI and the Conference of the Efficiency and Performance Engineering Network, TEPEN 2021, Tianjin, China, 20/10/21. https://doi.org/10.1007/978-3-030-99075-6_41

Investigation into LSTM Deep Learning for Induction Motor Fault Diagnosis. / Zhao, Xiaoyu; Alqatawneh, Ibrahim; Lane, Mark et al.

Proceedings of IncoME-VI and TEPEN 2021 : Performance Engineering and Maintenance Engineering. ed. / Hao Zhang; Guojin Feng; Hongjun Wang; Fengshou Gu; Jyoti K. Sinha. Vol. 117 Springer, Cham, 2022. p. 505-518 (Mechanisms and Machine Science; Vol. 117).

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

TY - GEN

T1 - Investigation into LSTM Deep Learning for Induction Motor Fault Diagnosis

AU - Zhao, Xiaoyu

AU - Alqatawneh, Ibrahim

AU - Lane, Mark

AU - Li, Haiyang

AU - Qin, Yongrui

AU - Gu, Fengshou

AU - Ball, Andrew D.

N1 - Conference code: 6

PY - 2022/9/18

Y1 - 2022/9/18

N2 - As motor faults could lead to unwanted loss in industry, it is important to find out the motor faults in time. Currently, with the popularity and mature application of deep learning, researchers in the field of electrical machine health assessment have begun to focus on deep learning methods. It is hoped that motor fault detection can be achieved with the help of deep learning methods. This paper presents to adopt deep learning methods represented by LSTM neural network for motor fault diagnosis and evaluates on our own experimental platform. Considering two typical motor faults with two different degrees of severity, the results show that the proposed LSTM approach has a high accuracy (98.81%) on motor fault classification. The results also confirm that: (1) adequate effort of preprocessing, including sample length selection in the time domain and frequency band selection in the frequency domain, can significantly improve accuracy and computational efficiency; (2) different faults can be separated through the information in frequency band of 100–1000 Hz, which has not been fully modelled analytically before.

AB - As motor faults could lead to unwanted loss in industry, it is important to find out the motor faults in time. Currently, with the popularity and mature application of deep learning, researchers in the field of electrical machine health assessment have begun to focus on deep learning methods. It is hoped that motor fault detection can be achieved with the help of deep learning methods. This paper presents to adopt deep learning methods represented by LSTM neural network for motor fault diagnosis and evaluates on our own experimental platform. Considering two typical motor faults with two different degrees of severity, the results show that the proposed LSTM approach has a high accuracy (98.81%) on motor fault classification. The results also confirm that: (1) adequate effort of preprocessing, including sample length selection in the time domain and frequency band selection in the frequency domain, can significantly improve accuracy and computational efficiency; (2) different faults can be separated through the information in frequency band of 100–1000 Hz, which has not been fully modelled analytically before.

KW - Deep learning

KW - LSTM

KW - Motor fault diagnosis

UR - http://www.scopus.com/inward/record.url?scp=85138826331&partnerID=8YFLogxK

UR - https://link.springer.com/book/10.1007/978-3-030-99075-6

U2 - 10.1007/978-3-030-99075-6_41

DO - 10.1007/978-3-030-99075-6_41

M3 - Conference contribution

AN - SCOPUS:85138826331

SN - 9783030990749

VL - 117

T3 - Mechanisms and Machine Science

SP - 505

EP - 518

BT - Proceedings of IncoME-VI and TEPEN 2021

A2 - Zhang, Hao

A2 - Feng, Guojin

A2 - Wang, Hongjun

A2 - Gu, Fengshou

A2 - Sinha, Jyoti K.

PB - Springer, Cham

T2 - 6th International Conference on Maintenance Engineering, IncoME-VI and the Conference of the Efficiency and Performance Engineering Network, TEPEN 2021

Y2 - 20 October 2021 through 23 October 2021

ER -

Zhao X, Alqatawneh I, Lane M, Li H, Qin Y, Gu F et al. Investigation into LSTM Deep Learning for Induction Motor Fault Diagnosis. In Zhang H, Feng G, Wang H, Gu F, Sinha JK, editors, Proceedings of IncoME-VI and TEPEN 2021 : Performance Engineering and Maintenance Engineering. Vol. 117. Springer, Cham. 2022. p. 505-518. (Mechanisms and Machine Science). Epub 2022 Sep 18. doi: 10.1007/978-3-030-99075-6_41

Investigation into LSTM Deep Learning for Induction Motor Fault Diagnosis

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this