首页 | 本学科首页   官方微博 | 高级检索  
     

应用弱化缓冲算子与最小二乘支持向量机的变压器油中溶解气体浓度预测
引用本文:卞建鹏,廖瑞金,杨丽君.应用弱化缓冲算子与最小二乘支持向量机的变压器油中溶解气体浓度预测[J].电网技术,2012,36(2):195-199.
作者姓名:卞建鹏  廖瑞金  杨丽君
作者单位:输配电装备及系统安全与新技术国家重点实验室(重庆大学),重庆市沙坪坝区,400044
基金项目:教育部科技创新工程重大项目培育资金项目
摘    要:变压器油中溶解气体浓度是评估油浸式变压器绝缘状态的重要依据。变压器油中溶解气体浓度的时间序列数据具有随机振荡性,往往不能准确把握溶解气体浓度的发展趋势,因此应用缓冲算子首先对原始数据进行弱化处理,减少其随机性。现有溶解气体浓度预测模型仅实现了点预测,为此采用最小二乘支持向量机与区间参数估计理论建立了溶解气体浓度的区间预测模型,确定未来溶解气体浓度在一定置信度下的变化区间。算例结果验证了该模型的有效性。

关 键 词:电力变压器  溶解气体  最小二乘支持向量机  弱化缓冲算子  区间预测

Concentration Prediction of Gases Dissolved in Transformer Oil Based on Weakening Buffer Operator and Least Square Support Vector Machine
BIAN Jianpeng,LIAO Ruijin,YANG Lijun.Concentration Prediction of Gases Dissolved in Transformer Oil Based on Weakening Buffer Operator and Least Square Support Vector Machine[J].Power System Technology,2012,36(2):195-199.
Authors:BIAN Jianpeng  LIAO Ruijin  YANG Lijun
Affiliation:(State Key Laboratory of Power Transmission Equipment & System Security and New Technology(Chongqing University),Shapingba District,Chongqing 400044,China)
Abstract:The concentration of gases dissolved in transformer oil is the important foundation to evaluate insulation state of oil-immersed transformer.Due to the random fluctuation of time-siries data of concentration of gases dissolved in transformer oil,the concentration of dissolved gases cannot often be mastered accurately,thus firstly the weakening buffer operator is applied to original data to weaken its randomness.In view of the fact that existing concentration prediction model of dissolved gases can implement point prediction only,therefore an interval prediction model for concentration of dissolved gases is built by least square support vector machine(LSSVM) and statistical interval estimation to determin the variation range of concentration of dissolved gases under a certain confidence level.Case calculation results verify the effectiveness of the proposed model.
Keywords:power transformer  dissolved gases  least square support vector machine (LSSVM)  weakening buffer operator  interval prediction
本文献已被 CNKI 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号