Concentration Prediction Model of Dissolved Gases in Transformer Oil Based on NMF and Improved ELM

LIU Yanan; FAN Lixin; XU Gang; TANG Yiming; LIU Quan; DU Chen

doi:10.13296/j.1001-1609.hva.2016.01.027

您当前的位置：

首页 >

文章列表页 >

Concentration Prediction Model of Dissolved Gases in Transformer Oil Based on NMF and Improved ELM

更新时间：2025-04-26

- Concentration Prediction Model of Dissolved Gases in Transformer Oil Based on NMF and Improved ELM
- High VoltageApparatus Vol. 52, Issue 1, Pages: 162-169(2016)
- 作者机构：
  
  江苏方天电力技术有限公司
- 作者简介：
- 基金信息：
- DOI：10.13296/j.1001-1609.hva.2016.01.027
  CLC： TM41
- Published：2016
- 稿件说明：
移动端阅览
[1]刘亚南,范立新,徐钢,唐一铭,刘全,都晨.基于非负矩阵分解与改进极端学习机的变压器油中溶解气体浓度预测模型[J].高压电器,2016,52(01):162-169.

LIU Yanan, FAN Lixin, XU Gang, et al. Concentration Prediction Model of Dissolved Gases in Transformer Oil Based on NMF and Improved ELM[J]. High voltageapparatus, 2016, 52(1): 162-169.
[1]刘亚南,范立新,徐钢,唐一铭,刘全,都晨.基于非负矩阵分解与改进极端学习机的变压器油中溶解气体浓度预测模型[J].高压电器,2016,52(01):162-169. DOI： 10.13296/j.1001-1609.hva.2016.01.027.

LIU Yanan, FAN Lixin, XU Gang, et al. Concentration Prediction Model of Dissolved Gases in Transformer Oil Based on NMF and Improved ELM[J]. High voltageapparatus, 2016, 52(1): 162-169. DOI： 10.13296/j.1001-1609.hva.2016.01.027.

摘要

变压器油中溶解气体浓度是评估变压器绝缘状态的重要依据

对气体浓度进行有效预测

可以及时识别变压器潜伏性故障。文中提出一种基于非负矩阵分解（nonnegative matrix factorization

NMF）与改进极端学习机（extreme learning machine

ELM）组合的变压器中溶解气体浓度预测模型。该方法通过NMF算法对输入样本进行分解

同时引入Adaboost算法对极端学习机进行改进;将低维矩阵作为模型的训练样本输入

剔除冗余数据

提高预测精度。实例分析结果表明

文中提出的方法能有效地降低输入样本维数

提高预测精度

能较好地解决变压器油中溶解气体浓度预测问题。

Abstract

The concentration of dissolved gases in transformer oil is an important parameter to evaluate insulation state of oil-immersed transformer. Effective concentration prediction of the dissolved gases can help to identify latent faults of transformer in time. In this paper

a concentration prediction model of dissolved gases in transformer oil is proposed based on the nonnegative matrix factorization（NMF） and the improved extreme learning machine（ELM）. The input data is decomposed by using the NMF algorithm to reduce the dimension of input variables.Then Adaboost algorithm is introduced to improve the extreme learning machine

and the derived nonnegative lower-dimension mapping matrix is taken as the inputs of the model for training. Simulation illustrates the effectiveness and availability of the proposed method in reducing the dimension of the input variables

performing the concentration prediction of dissolved gases in transformer oil

and improving the prediction accuracy.

关键词

Keywords

references

Views

200

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Prediction Model for Dissolved Gas in Transformer Oil Based on Policy Gradient Optimization

Research on Hybrid Finite Element Method Based on Triangle Mesh and Its Application in Fluid-heat Coupled Calculation of Transformer

Vibration Sound Power Measurement Method of UHV Transformer Based on Location of Main Vibration Point

Research on Multi-source Information Fusion Fault Diagnosis of Transformer Based on KPCA-SVM

Vibration Characteristic Analysis of Transformer Under Harmonic Current with Different Contents

Related Author

TANG Jian

HOU Huijuan

WANG Shaojing

REN Maoxin

SHENG Gehao

JIANG Xiuchen

LI Hao

LIU Gang

Related Institution

Department of Electrical Engineering, Shanghai Jiao Tong University

State Grid Shanghai Electric Power Research Institute

Hebei Provincial Key Laboratory of Power Transmission Equipment Security Defense, North China Electric Power University

Institute of Electrical Engineering Chinese Academy of Sciences

School of Electronic, Electrical and Communication Engineering University of Chinese Academy of Sciences

⁰