基于改进模糊时间序列的变压器油中气体预测方法
|
摘要
对变压器油中溶解气体含量进行预测有助于及早发现变压器内部的潜伏性故障,且对于更好地实现状态检修有着重要的指导意义.针对变压器油中气体组分数据丰富、正常运行状态下各组分含量变化趋势不明显的特点,提出基于模糊时间序列模型的变压器油中气体组分预测方法.考虑到油中气体组分的变化是相互作用和影响的,从论域划分角度对经典模糊时间序列模型进行改进,提出基于空间模糊C均值(fuzzy C-means,FCM)论域划分的多因素模糊时间序列模型.通过实例分析证明该方法能很好地拟合油中气体组分的变化趋势,且与经典模糊时间序列模型及一维FCM划分模糊时间序列模型的对比分析,验证了改进模型在预测效果上的优越性.
The prediction of dissolved gas content in transformer oil is helpful for early detection of latent faults in transformer,and it has important guiding significance for better condition based maintenance.In view of the abundant data of transformer dissolved gas analysis(DGA),and that the trend of the change of dissolved gas content in oil under normal running condition is not obvious,aprediction method based on fuzzy time series model is proposed.Considering that the change in dissolved gas content in oil is interaction and influenced,in this paper,the classical fuzzy time series model is improved from the view of domain division;and a multifactor fuzzy time series model is proposed based on spatial fuzzy C-means(FCM)domain partition.The case study shows that the method can well fit the changing trend of DGA data,and compared with the classic fuzzy time series model and the one-dimensional FCM fuzzy time series model,the superiority of the improved model in prediction is verified.
The prediction of dissolved gas content in transformer oil is helpful for early detection of latent faults in transformer,and it has important guiding significance for better condition based maintenance.In view of the abundant data of transformer dissolved gas analysis(DGA),and that the trend of the change of dissolved gas content in oil under normal running condition is not obvious,aprediction method based on fuzzy time series model is proposed.Considering that the change in dissolved gas content in oil is interaction and influenced,in this paper,the classical fuzzy time series model is improved from the view of domain division;and a multifactor fuzzy time series model is proposed based on spatial fuzzy C-means(FCM)domain partition.The case study shows that the method can well fit the changing trend of DGA data,and compared with the classic fuzzy time series model and the one-dimensional FCM fuzzy time series model,the superiority of the improved model in prediction is verified.
引文
[1]付宝英.基于粒子群优化的变压器故障诊断与预测研究[D].厦门:华侨大学,2012.FU Baoying.Transformer fault diagnosis and forecast research based on particle swarm optimization[D].Xiamen:Huaqiao University,2012.
[2]张艳.基于粒子群优化支持向量机的变压器故障诊断和预测[D].成都:西华大学,2011.Zhang Yan.Transformer fault diagnosis and prediction based on particle swarm optimize support vector machine[D].Chengdu:Xihua University,2011.
[3]Azizzadeh L,Zadeh L.Fuzzy sets,information and control[J].Information&Control,1965,8(3):338-353.
[4]李国勇.智能预测控制及其MATLAB实现[M].北京:电子工业出版社,2010.Li Guoyong.Intelligent Predictive Control and Its Realization of MATLAB[M].Beijing:Publishing House of Electronics Industry,2010.
[5]Song Q,Chissom B S.Forecasting enrollments with fuzzy time series—part I[J].Fuzzy Sets&Systems,1994,62(1):1-8.
[6]Chen S M.Forecasting enrollments based on fuzzy time series[J].Fuzzy Sets&Systems,1996,81(3):311-319.
[7]邱望仁.模糊时间序列模型及其在股指趋势分析中的应用研究[D].大连:大连理工大学,2012.Qiu Wangren.Research on fuzzy time series model and its application in trend analysis of stock exchange composite index[D].Dalian:Dalian University of Technology,2012.
[8]Song Q,Chissom B S.Fuzzy time series and its model[J].Fuzzy Sets&Systems,1993,54(3):269-277.
[9]Chen S M.Forecasting enrollments based on fuzzy time series[J].Fuzzy Sets&Systems,1996,81(3):311-319.
[10]Hwang J R,Chen S M,Lee C H.Handling forecasting problems using fuzzy time series[J].Fuzzy Sets&Systems,1998,100(1-3):217-228.
[11]Lee M H,Efendi R,Ismail Z.Modified weighted for enrollment forecasting based on fuzzy time series[J].Journal of Artificial Intelligence,2009,25(1):67-78.
[12]王军玲,王士同,包芳,等.基于空间距离的快速模糊C均值聚类算法[J].计算机工程与应用,2015,51(1):177-183.Wang Junling,Wang Shitong,Bao Fang,et al.Fast and robust fuzzy C-means clustering algorithm based onspace distance of nearest neighbors[J].Computer Engineering and Applications,2015,51(1):177-183.
[13]马云飞.多因素模糊时间序列预测模型的研究[D].大连:大连海事大学,2016.Ma Yunfei.The research of multi-factors fuzzy time series forcasting models[D].Dalian:Dalian Maritime University,2016.
[14]杨振勇.《变压器油中溶解气体分析和判断导则》判断变压器故障的探讨[J].变压器,2008,45(10):24-27.Yang Zhenyong.Discussionon diagnosis of transformer fault based on Guide to the analysis and the diagnosis of gasses dissolved in transformer oil[J].Transformer,2008,45(10):24-27.
[15]周东华.平滑算法和小波变换法相融合的气井生产数据处理[J].油气田地面工程,2011,30(4):33-35.Zhou Donghua.Smoothing algorithm and wavelet transform method for gas well production data processing[J].Oil-Gasfield Surface Engineering,2011,30(4):33-35.
[16]陈雪振.基于极限学习机的变压器故障预测方法研究[D].北京:华北电力大学,2015.Chen Xuezhen.Prediction method research of transformer fault based on extreme learning machine[D].Beijing:North China Electric Power University,2015.
[2]张艳.基于粒子群优化支持向量机的变压器故障诊断和预测[D].成都:西华大学,2011.Zhang Yan.Transformer fault diagnosis and prediction based on particle swarm optimize support vector machine[D].Chengdu:Xihua University,2011.
[3]Azizzadeh L,Zadeh L.Fuzzy sets,information and control[J].Information&Control,1965,8(3):338-353.
[4]李国勇.智能预测控制及其MATLAB实现[M].北京:电子工业出版社,2010.Li Guoyong.Intelligent Predictive Control and Its Realization of MATLAB[M].Beijing:Publishing House of Electronics Industry,2010.
[5]Song Q,Chissom B S.Forecasting enrollments with fuzzy time series—part I[J].Fuzzy Sets&Systems,1994,62(1):1-8.
[6]Chen S M.Forecasting enrollments based on fuzzy time series[J].Fuzzy Sets&Systems,1996,81(3):311-319.
[7]邱望仁.模糊时间序列模型及其在股指趋势分析中的应用研究[D].大连:大连理工大学,2012.Qiu Wangren.Research on fuzzy time series model and its application in trend analysis of stock exchange composite index[D].Dalian:Dalian University of Technology,2012.
[8]Song Q,Chissom B S.Fuzzy time series and its model[J].Fuzzy Sets&Systems,1993,54(3):269-277.
[9]Chen S M.Forecasting enrollments based on fuzzy time series[J].Fuzzy Sets&Systems,1996,81(3):311-319.
[10]Hwang J R,Chen S M,Lee C H.Handling forecasting problems using fuzzy time series[J].Fuzzy Sets&Systems,1998,100(1-3):217-228.
[11]Lee M H,Efendi R,Ismail Z.Modified weighted for enrollment forecasting based on fuzzy time series[J].Journal of Artificial Intelligence,2009,25(1):67-78.
[12]王军玲,王士同,包芳,等.基于空间距离的快速模糊C均值聚类算法[J].计算机工程与应用,2015,51(1):177-183.Wang Junling,Wang Shitong,Bao Fang,et al.Fast and robust fuzzy C-means clustering algorithm based onspace distance of nearest neighbors[J].Computer Engineering and Applications,2015,51(1):177-183.
[13]马云飞.多因素模糊时间序列预测模型的研究[D].大连:大连海事大学,2016.Ma Yunfei.The research of multi-factors fuzzy time series forcasting models[D].Dalian:Dalian Maritime University,2016.
[14]杨振勇.《变压器油中溶解气体分析和判断导则》判断变压器故障的探讨[J].变压器,2008,45(10):24-27.Yang Zhenyong.Discussionon diagnosis of transformer fault based on Guide to the analysis and the diagnosis of gasses dissolved in transformer oil[J].Transformer,2008,45(10):24-27.
[15]周东华.平滑算法和小波变换法相融合的气井生产数据处理[J].油气田地面工程,2011,30(4):33-35.Zhou Donghua.Smoothing algorithm and wavelet transform method for gas well production data processing[J].Oil-Gasfield Surface Engineering,2011,30(4):33-35.
[16]陈雪振.基于极限学习机的变压器故障预测方法研究[D].北京:华北电力大学,2015.Chen Xuezhen.Prediction method research of transformer fault based on extreme learning machine[D].Beijing:North China Electric Power University,2015.