Comparison Studies of Deep Belief Network and Typical Neural Network Applied to Analysis of Dissolved Gas in Oil

REN Shuangzan; XU Yaoyu; LI Yuan; WANG Yijing; ZHANG Guanjun

doi:10.13296/j.1001-1609.hva.2020.09.006

您当前的位置：

首页 >

文章列表页 >

Comparison Studies of Deep Belief Network and Typical Neural Network Applied to Analysis of Dissolved Gas in Oil

更新时间：2025-04-26

- Comparison Studies of Deep Belief Network and Typical Neural Network Applied to Analysis of Dissolved Gas in Oil
- High VoltageApparatus Vol. 56, Issue 9, Pages: 39-45(2020)
- 作者机构：
  
  1. 国网陕西省电力公司电力科学研究院
  2. 西安交通大学电力设备电气绝缘国家重点实验室
- 作者简介：
- 基金信息：
- DOI：10.13296/j.1001-1609.hva.2020.09.006
  CLC： TM411;TP183
- Published：2020
- 稿件说明：
移动端阅览
[1]任双赞,徐尧宇,李元,王怡静,张冠军.应用于油中溶解气体分析的深度信念网络与典型神经网络对比研究[J].高压电器,2020,56(09):39-45.

REN Shuangzan, XU Yaoyu, LI Yuan, et al. Comparison Studies of Deep Belief Network and Typical Neural Network Applied to Analysis of Dissolved Gas in Oil[J]. High voltageapparatus, 2020, 56(9): 39-45.
[1]任双赞,徐尧宇,李元,王怡静,张冠军.应用于油中溶解气体分析的深度信念网络与典型神经网络对比研究[J].高压电器,2020,56(09):39-45. DOI： 10.13296/j.1001-1609.hva.2020.09.006.

REN Shuangzan, XU Yaoyu, LI Yuan, et al. Comparison Studies of Deep Belief Network and Typical Neural Network Applied to Analysis of Dissolved Gas in Oil[J]. High voltageapparatus, 2020, 56(9): 39-45. DOI： 10.13296/j.1001-1609.hva.2020.09.006.

摘要

油中溶解气体分析是诊断油浸式变压器绝缘系统故障最有效的方法之一

对实现变压器故障精确诊断具有重要意义。文中基于深度信念网络（deep belief network

DBN）、BP神经网络（back propagation neural network

BPNN）和RBF神经网络（radial basis function neural network

RBFNN）构建了不同结构的变压器油中溶解气体分析模型

实现了基于油中溶解气体分析的变压器故障诊断。文中对比分析了不同建模方法、不同训练样本数和不同模型参数对变压器故障诊断精确度的影响。结果表明

文中构建的基于DBN的油中溶解气体分析模型在1 000组训练样本、5层DBN模型结构和第2层20个节点时

达到最高的识别精度84.87%。

Abstract

Dissolved gas analysis in transformer oil is one of the most effective methods to diagnose the fault of oil-immersed power transformer insulation system

which is of great significance to realize the accurate diagnosis of transformer fault.Based on the deep belief network（DBN） and the typical neural network model

BP neural network（BPNN）and RBF neural network（RBFNN）

this paper builds different structures of the DGA models to realize the transformer fault diagnosis.In addition

influences of different training data

modeling methods and parameters on the diagnosis accuracy of transformers is further analyzed.The proposed dissolved gas in oil model based on DBN achieves the highest recognition accuracy of 84.87% under 1 000-set training data

5-layer in DBN model structure and 20 nodes in 2 nd-layer.

关键词

Keywords

references

Views

136

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Power Transformer Fault Diagnosis via Neural Network Based on Particle Swarm Optimization with Neighborhood Operator

Application of Neural Network Based on Improved Particle Swarm Optimization in the Condition Monitoring of Transformer

Power Transformer Fault Diagnosis Based on Neural Networks with Improved Particle Swarm Optimization

Fault Diagnosis of Vacuum Circuit Breaker Based on Multi-sensor for Vibration Signals of Fusion

Dissolved Gas Analysis Based QPSO-BP Model for Transformer Fault Diagnosis

Related Author

JIA Rong

XU Qi-hui

LI Hui

LIU Wei

JIA Rong1

LI Hong-bin2

KANG Hui-xi2

HONG Gang1

Related Institution

College of Electrical Engineering,Xi’an University of Technology

西安理工大学电力工程系陕西西安710048

Department of Electrical Engineering,Xi′an University of Technology,Xi′an

Gansu Tou River Hydropower Development Ltd.

The Engineering College of Honghe University,Mengzi

⁰