A Method for Remaining Useful Life Prediction of Transformer Based on the CNN-LSTM Networks

Shi Xuntao; Hu Ran; Ou Mingyu; Yu Lei; Ke Qingpai; Wu Weiwei; Li Kairan

doi:10.1109/CIEEC54735.2022.9845984

A Method for Remaining Useful Life Prediction of Transformer Based on the CNN-LSTM Networks

Shi Xuntao
, Hu Ran
, Ou Mingyu
, Yu Lei
, Ke Qingpai
, Wu Weiwei
, Li Kairan

CSG
Shenzhen Power Supply Co.Ltd

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

5 Scopus citations

Abstract

The transformer is one of the core equipment of the power distribution network, and its reliability determines the safety of the distribution network. Therefore, it is significant to study the prediction of the remaining useful life (RUL) to prevent the catastrophic failures of the distribution network. In this paper, an advanced RUL prediction model based on the CNN (convolutional neural network) -LSTM (long short-term memory network) network is proposed. The proposed model can identify the fault characteristics of the transformer from the original data, and then accurately predict the RUL of the transformer. Compared with the traditional data-driven method, the proposed method does not rely on signal processing technology and the prior knowledge of diagnostic experts. The method in this paper has better performance during complex operating conditions. The experimental results validate the effectiveness of the proposed method.

Original language	English
Title of host publication	Proceedings of 2022 IEEE 5th International Electrical and Energy Conference, CIEEC 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	64-69
Number of pages	6
ISBN (Electronic)	9781665411042
DOIs	https://doi.org/10.1109/CIEEC54735.2022.9845984
State	Published - 2022
Externally published	Yes
Event	5th IEEE International Electrical and Energy Conference, CIEEC 2022 - Nanjing, China Duration: 27 May 2022 → 29 May 2022

Publication series

Name	Proceedings of 2022 IEEE 5th International Electrical and Energy Conference, CIEEC 2022

Conference

Conference	5th IEEE International Electrical and Energy Conference, CIEEC 2022
Country/Territory	China
City	Nanjing
Period	27/05/22 → 29/05/22

UN SDGs

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

SDG 7 Affordable and Clean Energy

Keywords

RUL
deep learning
distribution network
transformer

Access to Document

10.1109/CIEEC54735.2022.9845984

Cite this

Xuntao, S., Ran, H., Mingyu, O., Lei, Y., Qingpai, K., Weiwei, W., & Kairan, L. (2022). A Method for Remaining Useful Life Prediction of Transformer Based on the CNN-LSTM Networks. In Proceedings of 2022 IEEE 5th International Electrical and Energy Conference, CIEEC 2022 (pp. 64-69). (Proceedings of 2022 IEEE 5th International Electrical and Energy Conference, CIEEC 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CIEEC54735.2022.9845984

Xuntao, Shi ; Ran, Hu ; Mingyu, Ou et al. / A Method for Remaining Useful Life Prediction of Transformer Based on the CNN-LSTM Networks. Proceedings of 2022 IEEE 5th International Electrical and Energy Conference, CIEEC 2022. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 64-69 (Proceedings of 2022 IEEE 5th International Electrical and Energy Conference, CIEEC 2022).

@inproceedings{7d8e48c7ffa144caa5ff194a8c43ecbe,

title = "A Method for Remaining Useful Life Prediction of Transformer Based on the CNN-LSTM Networks",

abstract = "The transformer is one of the core equipment of the power distribution network, and its reliability determines the safety of the distribution network. Therefore, it is significant to study the prediction of the remaining useful life (RUL) to prevent the catastrophic failures of the distribution network. In this paper, an advanced RUL prediction model based on the CNN (convolutional neural network) -LSTM (long short-term memory network) network is proposed. The proposed model can identify the fault characteristics of the transformer from the original data, and then accurately predict the RUL of the transformer. Compared with the traditional data-driven method, the proposed method does not rely on signal processing technology and the prior knowledge of diagnostic experts. The method in this paper has better performance during complex operating conditions. The experimental results validate the effectiveness of the proposed method.",

keywords = "RUL, deep learning, distribution network, transformer",

author = "Shi Xuntao and Hu Ran and Ou Mingyu and Yu Lei and Ke Qingpai and Wu Weiwei and Li Kairan",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 5th IEEE International Electrical and Energy Conference, CIEEC 2022 ; Conference date: 27-05-2022 Through 29-05-2022",

year = "2022",

doi = "10.1109/CIEEC54735.2022.9845984",

language = "英语",

series = "Proceedings of 2022 IEEE 5th International Electrical and Energy Conference, CIEEC 2022",

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

pages = "64--69",

booktitle = "Proceedings of 2022 IEEE 5th International Electrical and Energy Conference, CIEEC 2022",

address = "美国",

}

Xuntao, S, Ran, H, Mingyu, O, Lei, Y, Qingpai, K, Weiwei, W & Kairan, L 2022, A Method for Remaining Useful Life Prediction of Transformer Based on the CNN-LSTM Networks. in Proceedings of 2022 IEEE 5th International Electrical and Energy Conference, CIEEC 2022. Proceedings of 2022 IEEE 5th International Electrical and Energy Conference, CIEEC 2022, Institute of Electrical and Electronics Engineers Inc., pp. 64-69, 5th IEEE International Electrical and Energy Conference, CIEEC 2022, Nanjing, China, 27/05/22. https://doi.org/10.1109/CIEEC54735.2022.9845984

A Method for Remaining Useful Life Prediction of Transformer Based on the CNN-LSTM Networks. / Xuntao, Shi; Ran, Hu; Mingyu, Ou et al.
Proceedings of 2022 IEEE 5th International Electrical and Energy Conference, CIEEC 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 64-69 (Proceedings of 2022 IEEE 5th International Electrical and Energy Conference, CIEEC 2022).

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

TY - GEN

T1 - A Method for Remaining Useful Life Prediction of Transformer Based on the CNN-LSTM Networks

AU - Xuntao, Shi

AU - Ran, Hu

AU - Mingyu, Ou

AU - Lei, Yu

AU - Qingpai, Ke

AU - Weiwei, Wu

AU - Kairan, Li

PY - 2022

Y1 - 2022

N2 - The transformer is one of the core equipment of the power distribution network, and its reliability determines the safety of the distribution network. Therefore, it is significant to study the prediction of the remaining useful life (RUL) to prevent the catastrophic failures of the distribution network. In this paper, an advanced RUL prediction model based on the CNN (convolutional neural network) -LSTM (long short-term memory network) network is proposed. The proposed model can identify the fault characteristics of the transformer from the original data, and then accurately predict the RUL of the transformer. Compared with the traditional data-driven method, the proposed method does not rely on signal processing technology and the prior knowledge of diagnostic experts. The method in this paper has better performance during complex operating conditions. The experimental results validate the effectiveness of the proposed method.

AB - The transformer is one of the core equipment of the power distribution network, and its reliability determines the safety of the distribution network. Therefore, it is significant to study the prediction of the remaining useful life (RUL) to prevent the catastrophic failures of the distribution network. In this paper, an advanced RUL prediction model based on the CNN (convolutional neural network) -LSTM (long short-term memory network) network is proposed. The proposed model can identify the fault characteristics of the transformer from the original data, and then accurately predict the RUL of the transformer. Compared with the traditional data-driven method, the proposed method does not rely on signal processing technology and the prior knowledge of diagnostic experts. The method in this paper has better performance during complex operating conditions. The experimental results validate the effectiveness of the proposed method.

KW - RUL

KW - deep learning

KW - distribution network

KW - transformer

UR - https://www.scopus.com/pages/publications/85137353766

U2 - 10.1109/CIEEC54735.2022.9845984

DO - 10.1109/CIEEC54735.2022.9845984

M3 - 会议稿件

AN - SCOPUS:85137353766

T3 - Proceedings of 2022 IEEE 5th International Electrical and Energy Conference, CIEEC 2022

SP - 64

EP - 69

BT - Proceedings of 2022 IEEE 5th International Electrical and Energy Conference, CIEEC 2022

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 5th IEEE International Electrical and Energy Conference, CIEEC 2022

Y2 - 27 May 2022 through 29 May 2022

ER -

Xuntao S, Ran H, Mingyu O, Lei Y, Qingpai K, Weiwei W et al. A Method for Remaining Useful Life Prediction of Transformer Based on the CNN-LSTM Networks. In Proceedings of 2022 IEEE 5th International Electrical and Energy Conference, CIEEC 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 64-69. (Proceedings of 2022 IEEE 5th International Electrical and Energy Conference, CIEEC 2022). doi: 10.1109/CIEEC54735.2022.9845984

A Method for Remaining Useful Life Prediction of Transformer Based on the CNN-LSTM Networks

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this