Cargando…

Convolutional Neural Network-Based Transformer Fault Diagnosis Using Vibration Signals

Fast and accurate fault diagnosis is crucial to transformer safety and cost-effectiveness. Recently, vibration analysis for transformer fault diagnosis is attracting increasing attention due to its ease of implementation and low cost, while the complex operating environment and loads of transformers...

Descripción completa

Detalles Bibliográficos
Autores principales: Li, Chao, Chen, Jie, Yang, Cheng, Yang, Jingjian, Liu, Zhigang, Davari, Pooya
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10223529/
https://www.ncbi.nlm.nih.gov/pubmed/37430695
http://dx.doi.org/10.3390/s23104781
_version_ 1785049963925864448
author Li, Chao
Chen, Jie
Yang, Cheng
Yang, Jingjian
Liu, Zhigang
Davari, Pooya
author_facet Li, Chao
Chen, Jie
Yang, Cheng
Yang, Jingjian
Liu, Zhigang
Davari, Pooya
author_sort Li, Chao
collection PubMed
description Fast and accurate fault diagnosis is crucial to transformer safety and cost-effectiveness. Recently, vibration analysis for transformer fault diagnosis is attracting increasing attention due to its ease of implementation and low cost, while the complex operating environment and loads of transformers also pose challenges. This study proposed a novel deep-learning-enabled method for fault diagnosis of dry-type transformers using vibration signals. An experimental setup is designed to simulate different faults and collect the corresponding vibration signals. To find out the fault information hidden in the vibration signals, the continuous wavelet transform (CWT) is applied for feature extraction, which can convert vibration signals to red-green-blue (RGB) images with the time–frequency relationship. Then, an improved convolutional neural network (CNN) model is proposed to complete the image recognition task of transformer fault diagnosis. Finally, the proposed CNN model is trained and tested with the collected data, and its optimal structure and hyperparameters are determined. The results show that the proposed intelligent diagnosis method achieves an overall accuracy of 99.95%, which is superior to other compared machine learning methods.
format Online
Article
Text
id pubmed-10223529
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-102235292023-05-28 Convolutional Neural Network-Based Transformer Fault Diagnosis Using Vibration Signals Li, Chao Chen, Jie Yang, Cheng Yang, Jingjian Liu, Zhigang Davari, Pooya Sensors (Basel) Article Fast and accurate fault diagnosis is crucial to transformer safety and cost-effectiveness. Recently, vibration analysis for transformer fault diagnosis is attracting increasing attention due to its ease of implementation and low cost, while the complex operating environment and loads of transformers also pose challenges. This study proposed a novel deep-learning-enabled method for fault diagnosis of dry-type transformers using vibration signals. An experimental setup is designed to simulate different faults and collect the corresponding vibration signals. To find out the fault information hidden in the vibration signals, the continuous wavelet transform (CWT) is applied for feature extraction, which can convert vibration signals to red-green-blue (RGB) images with the time–frequency relationship. Then, an improved convolutional neural network (CNN) model is proposed to complete the image recognition task of transformer fault diagnosis. Finally, the proposed CNN model is trained and tested with the collected data, and its optimal structure and hyperparameters are determined. The results show that the proposed intelligent diagnosis method achieves an overall accuracy of 99.95%, which is superior to other compared machine learning methods. MDPI 2023-05-16 /pmc/articles/PMC10223529/ /pubmed/37430695 http://dx.doi.org/10.3390/s23104781 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Li, Chao
Chen, Jie
Yang, Cheng
Yang, Jingjian
Liu, Zhigang
Davari, Pooya
Convolutional Neural Network-Based Transformer Fault Diagnosis Using Vibration Signals
title Convolutional Neural Network-Based Transformer Fault Diagnosis Using Vibration Signals
title_full Convolutional Neural Network-Based Transformer Fault Diagnosis Using Vibration Signals
title_fullStr Convolutional Neural Network-Based Transformer Fault Diagnosis Using Vibration Signals
title_full_unstemmed Convolutional Neural Network-Based Transformer Fault Diagnosis Using Vibration Signals
title_short Convolutional Neural Network-Based Transformer Fault Diagnosis Using Vibration Signals
title_sort convolutional neural network-based transformer fault diagnosis using vibration signals
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10223529/
https://www.ncbi.nlm.nih.gov/pubmed/37430695
http://dx.doi.org/10.3390/s23104781
work_keys_str_mv AT lichao convolutionalneuralnetworkbasedtransformerfaultdiagnosisusingvibrationsignals
AT chenjie convolutionalneuralnetworkbasedtransformerfaultdiagnosisusingvibrationsignals
AT yangcheng convolutionalneuralnetworkbasedtransformerfaultdiagnosisusingvibrationsignals
AT yangjingjian convolutionalneuralnetworkbasedtransformerfaultdiagnosisusingvibrationsignals
AT liuzhigang convolutionalneuralnetworkbasedtransformerfaultdiagnosisusingvibrationsignals
AT davaripooya convolutionalneuralnetworkbasedtransformerfaultdiagnosisusingvibrationsignals