摘要
电力变压器故障预测可实现对变压器故障的早期预警,对保证电力系统的正常运行具有重要意义。该文提出了一种基于时间序列和支持向量机(SVM)的变压器故障预测模型。该模型以时间序列分析中的自回归积分滑动平均模型(ARIMA)为基础,采用遗传算法(GA)对ARIMA模型参数p和q进行定阶,并利用定阶后的时间序列模型对变压器油中溶解气体进行预测,然后利用基于网格搜索算法(GS)优化后的SVM模型对预测出的油中溶解气体进行诊断。运行结果表明,该模型的预测准确率可达89.66%,而利用GM–SVM、ARIMA–SVM和GA–ARIMA–ANN得到的预测准确率分别为58.62%、79.31%、75.86%。因此,所提出模型有更高的预测准确率。
The fault prediction of power transformer can realize the early warning of transformer fault,which is vital to ensure the normal operation of the electric power system.A transformer fault prediction model based on time series and support vector machine(SVM)is presented in this paper.The model is based on the autoregressive integral moving average(ARIMA)model in time series analysis,and the parameters p and q of ARIMA model are determined by genetic algorithm(GA).The dissolved gas in transformer oil is predicted by the time series model after parameter determination.Then the SVM model optimized by grid search algorithm(GS)is used to predict the dissolved gas in oil.The running results show that the accuracy of transformer fault prediction model can reaches 89.66%,while the prediction accuracy of GM-SVM,ARIMA-SVM and GA-ARIMA-ANN is 58.62%,79.31%and 75.86%,respectively.So the method proposed in this paper has the higher prediction accuracy.
作者
黄新波
蒋卫涛
朱永灿
田毅
HUANG Xinbo;JIANG Weitao;ZHU Yongcan;TIAN Yi(School of Electronics and Information,Xi’an Polytechnic University,Xi'an 710048,China)
出处
《高电压技术》
EI
CAS
CSCD
北大核心
2020年第7期2530-2538,共9页
High Voltage Engineering
基金
陕西省重点项目-工业领域(2018ZDXM-GY-040)
西安市科技计划项目(201805030YD8CG14(4))。
作者简介
通信作者:黄新波,1975-,男,博士(后),教授,博导,主要从事智能电网输变电设备在线监测理论与关键技术、无线网络传感器等研究,E-mail:huangxb1975@163.com;蒋卫涛,1996-,男,硕士生,从事电力系统在线监测理论与智能化技术研究,E-mail:792742345@qq.com;朱永灿,1986-,男,博士,硕导,主要从事输电线路覆冰及智能电网在线监测技术研究,E-mail:286844943@qq.com;田毅,1984-,男,博士,讲师,主要从事输变电设备故障诊断、高压绝缘和等离子体放电研究,E-mail:yyittian@126.com。
