[1]贾茹宾,高金峰.基于ARIMA模型的变压器油中溶解气体含量时间序列预测方法[J].郑州大学学报(工学版),2020,41(02):67-72.[doi:10.13705/j.issn.1671-6833.2020.03.010]
　Jia Rubin,Gao Jinfeng.Time Series Prediction Method of Dissolved Gas Content in Transformer Oilased on ARIMA Model[J].Journal of Zhengzhou University (Engineering Science),2020,41(02):67-72.[doi:10.13705/j.issn.1671-6833.2020.03.010]
点击复制

基于ARIMA模型的变压器油中溶解气体含量时间序列预测方法()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
41
期数:
2020年02期
页码:
67-72
栏目:
出版日期:
2020-05-31

文章信息/Info

Title:
Time Series Prediction Method of Dissolved Gas Content in Transformer Oilased on ARIMA Model
作者:
贾茹宾; 高金峰
郑州大学电气工程学院
Author(s):
Jia Rubin; Gao Jinfeng
School of Electrical Engineering, Zhengzhou University
关键词:
变压器油; 气体含量; 时间序列; ARIMA模型; 预测
Keywords:
Transformer oil; gas content; sequentially; ARIMA model; predict
DOI:
10.13705/j.issn.1671-6833.2020.03.010
文献标志码:
A
摘要:
变压器油中溶解气体含量是衡量变压器运行状态的重要指标。运用差分自回归移动平均模型（ARIMA）对变压器油中气体含量进行预测，该方法通过python编程以气体含量值对应的时间为索 引输入预测模型，在建模中首先对时间序列平稳性进行单位根检验，采用差分处理的方法将原始不平 稳时间序列转换为平稳时间序列，而后利用自相关函数和偏自相关函数参数选择原则得出若干组模型，在对若干组模型进行优选的过程中分别使用赤池信息、贝叶斯信息、汉南⁃奎因3种准则得出一组最优模型，最后通过相关检验方法对优选模型进行残差检验，并利用满足残差要求的模型对气体含量预测。实验表明，提出的预测方法有较高的预测精度，可以为合理安排变压器的状态检修提供有价值的参考。
Abstract:
The dissolved gas content in transformer oil is an important index to measure the operation status of transformers. The differential autoregressive moving average model (ARIMA) is used to predict the gas content in transformer oil. This method uses the time corresponding to the gas content value as an index to input the prediction model through python programming. The original non-stationary time series is converted into a stationary time series by means of difference processing, and then several sets of models are obtained by using the autocorrelation function and partial autocorrelation function parameter selection principles, and are used in the process of optimizing several sets of models. A set of optimal models were obtained by Chichi information, Bayesian information, and Hannan-Quine criteria. Finally, the residuals of the optimal models were tested by correlation testing methods, and the gas content was predicted using the models that met the residual requirements. Experiments show that the proposed prediction method has high prediction accuracy, which can provide a valuable reference for rationally arranging the condition-based maintenance of transformers.

相似文献/References:

[1]陈志强,牛田野,李洪波,等.TiO2纳米粉体对变压器油工频击穿性能的影响[J].郑州大学学报(工学版),2012,33(04):125.[doi:10.3969/j.issn.1671-6833.2012.04.029]
　CHEN Zhiqiang,NIU Tianye,LI Hongbo,et al.Effect of TiO2 Nano-powder on the Industrial Frequency Power BreakdownProperties of Transformer Oil[J].Journal of Zhengzhou University (Engineering Science),2012,33(02):125.[doi:10.3969/j.issn.1671-6833.2012.04.029]

更新日期/Last Update: 2020-05-30