Prediction Model of Dissolved Gas in Transformer Oil Based on Variational Modal Decomposition and Recurrent Neural Network with Gated Recurrent Unit

XIE Le; QIU Wei; LI Zhenwei; LIU Yang; JIANG Qilong; LIU Dong

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

Prediction Model of Dissolved Gas in Transformer Oil Based on Variational Modal Decomposition and Recurrent Neural Network with Gated Recurrent Unit

更新时间：2025-12-08

- Prediction Model of Dissolved Gas in Transformer Oil Based on Variational Modal Decomposition and Recurrent Neural Network with Gated Recurrent Unit
- Vol. 48, Issue 2, Pages: 653-660(2022)
- 作者机构：
  
  1. 西南交通大学电气工程学院
  2. 广东电网有限责任公司珠海供电局
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published Online：28 February 2022，
  
  Published：2022
- 稿件说明：
移动端阅览
XIE Le, QIU Wei, LI Zhenwei, et al. Prediction Model of Dissolved Gas in Transformer Oil Based on Variational Modal Decomposition and Recurrent Neural Network with Gated Recurrent Unit[J]. 2022, 48(2): 653-660.
DOI：

XIE Le, QIU Wei, LI Zhenwei, et al. Prediction Model of Dissolved Gas in Transformer Oil Based on Variational Modal Decomposition and Recurrent Neural Network with Gated Recurrent Unit[J]. 2022, 48(2): 653-660. DOI：

摘要

油中溶解气体分析是变压器早期故障诊断的一种有效方法，对变压器油中溶解气体进行精准预测，可为变压器早期故障监测和预警提供理论依据。为此本研究提出了一种基于变分模态分解和门控循环单元神经网络的变压器油中溶解气体预测模型。首先对变压器原始油中溶解气体体积分数时间序列进行变分模态分解，将其分解为各子序列，消除其不平稳性的影响；然后分别建立门控循环单元神经网络预测模型对各子序列进行单步和多步预测；最后将预测得到的各子序列进行叠加重构从而得到对变压器油中溶解气体体积分数的单步和多步预测。算例分析表明，该模型单步预测的平均绝对误差和均方根误差分别为0.057 6和0.068 4，多步预测的平均绝对误差和均方根误差分别为0.167 9和0.204 1。相比于其他预测模型，该研究所提出模型在单步和多步预测能力上均有较大提升，为电力变压器监测预警提供了参考。

Abstract

Dissolved gas analysis in oil is an effective method for early fault diagnosis of the transformer. Accurate prediction of dissolved gas volume fraction in oil can provide a theoretical basis for early fault monitoring and early warning of the transformer. In this paper

a prediction method of dissolved gases in transformer oil based on variational mode decomposition（VMD） and recurrent neural network with gated recurrent unit（GRU-RNN） was proposed. Firstly

the original time series of dissolved gases volume fraction in oil of transformer were decomposed into sub-series by VMD to reduce the influence of instability. Then

the GRU-RNN prediction method was used to predict the sub-series in one step and multi-step

respectively. Finally

the predicted sub-series were superposed and reconstructed to obtain the one-step and multi-step prediction of dissolved gas volume fraction in transformer oil. The results show that the mean absolute error（MAE） and root mean square error（RMSE） of the method are 0.057 6 and 0.068 4

respectively

and the MAE and RMSE of the multi-step prediction are 0.167 9 and 0.204 1

respectively. Compared with other prediction methods

the proposed method in this paper has a great improvement in single-step and multi-step prediction ability

which provides a reference for the power transformer monitoring and early warning.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Transformer Fault Prediction Based on Time Series and Support Vector Machine

变压器健康状态实时预警方法及可解释性分析

Statistical Properties and Test Analysis of the Measured Lightning Invasion Waves in a Substation

Analysis of Transient Moisture Diffusion in Oil-paper Insulation Using Polarization and Depolarization Charge Difference Model

Electrical Properties of Oil-paper Affected by Water Conductivity During Paper-making Process

Related Author

HUANG Xinbo

JIANG Weitao

ZHU Yongcan

TIAN Yi

LIAO Caibo

JIANG Zihao

YANG Jinxin

SHAO Jian

Related Institution

School of Electronics and Information,Xi’an Polytechnic University

Department of Energy and Electrical Engineering, Nanchang University

Electric Power Research Institute of State Grid Jiangsu Electric Power Co., Ltd.

State Key Laboratory of Power Transmission Equipment & System Security and New Technology, Chongqing University

College of Electrical Engineering, Southwest Jiaotong University

AI问答

⁰