Predication of Dissolved Gases Concentration in Transformer Oil Based on Ensemble Empirical Mode Decomposition and Extreme Learning Machine

ZHOU Feng; SUN Tingxi; QUAN Shaojing; LIU Min; WANG Hengchao; WANG Shutian

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

Predication of Dissolved Gases Concentration in Transformer Oil Based on Ensemble Empirical Mode Decomposition and Extreme Learning Machine

更新时间：2025-12-08

- Predication of Dissolved Gases Concentration in Transformer Oil Based on Ensemble Empirical Mode Decomposition and Extreme Learning Machine
- Vol. 46, Issue 10, Pages: 3658-3665(2020)
- 作者机构：
  
  1. 广东电网有限责任公司珠海供电局
  2. 2. 北京路遥科技有限公司
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published Online：31 October 2020，
  
  Published：2020
- 稿件说明：
移动端阅览
ZHOU Feng, SUN Tingxi, QUAN Shaojing, et al. Predication of Dissolved Gases Concentration in Transformer Oil Based on Ensemble Empirical Mode Decomposition and Extreme Learning Machine[J]. 2020, 46(10): 3658-3665.
DOI：

ZHOU Feng, SUN Tingxi, QUAN Shaojing, et al. Predication of Dissolved Gases Concentration in Transformer Oil Based on Ensemble Empirical Mode Decomposition and Extreme Learning Machine[J]. 2020, 46(10): 3658-3665. DOI：

摘要

为准确估计变压器油中溶解气体体积分数的发展趋势

提出一种基于集合经验模态分解和极限学习机的油中溶解气体体积分数预测模型。首先

对原始油中溶解气体体积分数序列进行集合经验模态分解获得若干个子序列;其次

采用极限学习机算法对各个子序列分别建立不同的预测模型

并利用改进的粒子群算法对极限学习机相关参数进行优化

以提高预测精度;最后

通过叠加各子序列的预测结果得到最终的气体体积分数预测结果。研究结果表明:基于集合经验模态分解的改进粒子群极限学习机算法模型均方根误差为0.13

平均相对误差为0.502%

最大相对误差为1.914%

对比其他模型的预测效果可知

改进后的粒子群算法能够获得更优的极限学习机网络输入权值和隐层阈值

从而提高预测精度。仿真结果证明所提方法能够更好地反映油中溶解气体体积分数的变化趋势。

Abstract

In order to accurately predict the trend of dissolved gas concentration

a prediction method of dissolved gases concentration in transformer oil based on ensemble empirical mode decomposition（EEMD） and extreme learning machine（ELM） was proposed in this paper. Firstly

the original data set of dissolved gases was analyzed by EEMD to obtain several sub-sequences. Then

different prediction models were

respectively

established for different components based on the extreme learning machine algorithm

moreover

an improved particle swarm optimization（IPSO） algorithm was introduced to optimize parameters of prediction model to improve accuracy of the prediction. Finally

prediction results of each component were superimposed and summed to obtain the overall prediction results. The results show that the root mean square error of the IPSO ELM mode based on EEMD is 0.13

the average relative error is 0.502%

and the maximum relative error is 1.914%. Compared with the prediction results of other models

the improved particle swarm optimization algorithm can obtain better extreme learning machine network input weights and hidden layer threshold

so as to improve the prediction accuracy. The validity of the method was verified by the calculation results of a case.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Discharge Characteristics of the Typical Defects in Oil-paper Insulation Under AC-DC Compound Voltage

Optimal Planning of Centralized Charging Stations Considering Benefits for Different Roles

Estimation Method for Thermal Parameters of Soil Around the Cable Based on Finite Element and Particle Swarm Optimization

Mechanical Fault Diagnosis Containing Unknown Fault of High Voltage Circuit Breaker Based on Tsallis Entropy and Hybrid Classifier

Feasibility Study on Transformer Winding Deformation Detection and Fault Identification Based on Distributed Optical Fiber Sensing

Related Author

WANG Hongbin

LI Feng

ZHANG Xiaohan

LI Chengrong

WEI Zhen

QI Bo

YIN Qing

ZHANG Xi

Related Institution

Electric Power Research Institute of Guangdong Grid Company

Beijing Key Laboratory of High Voltage & EMC, North China Electric Power University

State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University

State Grid Sichuan Electrical Power Research Institute

School of Electrical Engineering and Information, Sichuan University

AI问答

⁰