Multi-Branch Residual Multiscale CNN Based Power Transformer Fault Diagnosis on Vibration Signal

Binwen Zhang; Fei Jiao; Jie Tong; Yuanpeng Tan; Zhonghao Zhang; Shuang Lin

doi:10.17775/CSEEJPES.2022.00490

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

Multi-Branch Residual Multiscale CNN Based Power Transformer Fault Diagnosis on Vibration Signal

Regular Papers | 更新时间：2026-10-15

- Multi-Branch Residual Multiscale CNN Based Power Transformer Fault Diagnosis on Vibration Signal
- Multi-Branch Residual Multiscale CNN Based Power Transformer Fault Diagnosis on Vibration Signal
- 中国电机工程学会电力与能源系统学报(英文) 2025年11卷第4期页码：1905-1914
- 作者机构：
  
  1. China Electric Power Research Institute,Beijing,China
  2. State Grid Fujian Electric Power Research Institute,Fuzhou,China
- 作者简介：
- 基金信息：
- DOI：10.17775/CSEEJPES.2022.00490
  中图分类号：
- 纸质出版：2025-07-01
- 稿件说明：
移动端阅览
Binwen Zhang, Fei Jiao, Jie Tong, 等. Multi-Branch Residual Multiscale CNN Based Power Transformer Fault Diagnosis on Vibration Signal[J]. 中国电机工程学会电力与能源系统学报(英文), 2025,11(4):1905-1914.

Binwen Zhang, Fei Jiao, Jie Tong, et al. Multi-Branch Residual Multiscale CNN Based Power Transformer Fault Diagnosis on Vibration Signal[J]. CSEE Journal of Power and Energy Systems, 2025, 11(4): 1905-1914.
Binwen Zhang, Fei Jiao, Jie Tong, 等. Multi-Branch Residual Multiscale CNN Based Power Transformer Fault Diagnosis on Vibration Signal[J]. 中国电机工程学会电力与能源系统学报(英文), 2025,11(4):1905-1914. DOI： 10.17775/CSEEJPES.2022.00490.

Binwen Zhang, Fei Jiao, Jie Tong, et al. Multi-Branch Residual Multiscale CNN Based Power Transformer Fault Diagnosis on Vibration Signal[J]. CSEE Journal of Power and Energy Systems, 2025, 11(4): 1905-1914. DOI： 10.17775/CSEEJPES.2022.00490.

摘要

Abstract

Status of the transformer is highly associated with safe and stable operation of the whole power system. Since the vibration signal is generated along with operation of the transformer and can indicate change of equipment operation status in real-time

fault diagnosis based on the vibration signal is a feasible method to monitor status of the transformer. In this paper

an end-to-end multi-branch-attention-multiscale CNN (MAMCNN) framework is proposed based on a one-dimensional convolutional neural network

in which multi-branch inputs

multiscale residual learning

and attention mechanism-guided multi-branch fusion techniques are integrated to identify states of the 220 kV transformer. To address the problem of small samples for transformer fault diagnosis

the proposed method first tests on a public dataset of rolling element bearing vibration. Results show that MAMCNN still has good differentiation for fault features under strong noise and fluctuating operating conditions without denoising

and has high accuracy and stability for state identification. MAMCNN is then applied to 220 kV transformer fault diagnosis based on vibration signals

and results exhibit high accuracy

rapid and stable convergence in identifying four transformer states.

关键词

Keywords

references

21. Z. C. Cui, W. L. Chen, and Y. X. Chen. ( 2016, May 11 ). Multi-scale convolutional neural networks for time series classification . [Online ] . Available: http://arxiv.org/abs/1603.06995.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

Power Grid Fault Diagnosis Based on Deep Pyramid Convolutional Neural Network

Dynamic Differential Current-based Transformer Protection Using a Convolutional Neural Network

Fault diagnosis of power transformers using graph convolutional network

Multi-mapping fault diagnosis of high voltage circuit breaker based on mathematical morphology and wavelet entropy

Bubble Changing Features and Buckle of the Free Liquid Surface in Active Oiled Power Transformer Tank