考虑覆冰厚度的输电线路覆冰增长预测
|
摘要
针对输电线路覆冰过程天气因素复杂、预测精度较差等问题,提出将覆冰厚度纳入特征向量,以覆冰厚度增长率为预测目标,并利用灰色综合关联分析法验证该方法的合理性;同时,将粒子群算法与最小二乘法支持向量机(LS-SVM)结合起来建立预测模型,得到覆冰厚度增长曲线。实例计算结果表明:预测方法改进后,训练集数据的拟合值与实际覆冰厚度的均方误差由0.23降至0.19,下降了17.4%;测试集数据的预测值与实际覆冰厚度的均方误差由5.10降至0.25,下降了95.1%,本预测方法的预测精度得到提高。
Aiming at the problems like complex weather condition of transmission line icing process and poor prediction accuracy,the ice covered thickness is proposed to be incorporated into feature vectors,and the ice covered thickness growth rate is proposed as an improved method for predicting,and the feasibility of which is verified by the method of grey correlation analysis.Meanwhile,particle swarm optimization algorithm is used to optimize least squares support vector machine(LS-SVM)to get the prediction of ice thickness growth curve.The results show that after model been improved,the mean square error between the fitting value of the training set data and the actual icing thickness is reduced from 0.23 to 0.19,with a decrease of 17.4%.The mean square error between the predicted value of the test set and the actual icing thickness is reduced from 5.10 to 0.25,with a decrease of 95.1%.By using this prediction method,the model prediction accuracy is improved.
Aiming at the problems like complex weather condition of transmission line icing process and poor prediction accuracy,the ice covered thickness is proposed to be incorporated into feature vectors,and the ice covered thickness growth rate is proposed as an improved method for predicting,and the feasibility of which is verified by the method of grey correlation analysis.Meanwhile,particle swarm optimization algorithm is used to optimize least squares support vector machine(LS-SVM)to get the prediction of ice thickness growth curve.The results show that after model been improved,the mean square error between the fitting value of the training set data and the actual icing thickness is reduced from 0.23 to 0.19,with a decrease of 17.4%.The mean square error between the predicted value of the test set and the actual icing thickness is reduced from 5.10 to 0.25,with a decrease of 95.1%.By using this prediction method,the model prediction accuracy is improved.
引文
[1]蒋兴良,易辉.输电线路覆冰及防护[M].北京:中国电力出版社,2002.JIANG Xingliang,YI Hui.Icing and protection of transmission line[M].Beijing,China:China Electric Power Press,2012.(in Chinese)
[2]胡毅.电网大面积冰灾分析及对策探讨[J].高电压技术,2008,34(2):215-219.HU Yi.Analysis and countermeasures discussion for large area icing accident on power grid[J].High Voltage Engineering,2008,34(2):215-219.(in Chinese)
[3]刘和云,周迪,付俊萍,等.导线雨淞覆冰预测简单模型的研究[J].中国电机工程学报,2001,21(4):45-48.LIU Heyun,ZHOU Di,FU Junping,et al.A simple model for predicting glaze loads on wires[J].Proceedings of the CSEE,2001,21(4):45-48.(in Chinese)
[4]阳林,郝艳捧,黎卫国,等.架空输电线路在线监测覆冰力学计算模型[J].中国电机工程学报,2010,30(19):100-105.YANG Lin,HAO Yanpeng,LI Weiguo,et al.A mechanical calculation model for on-line icing-monitoring system of overhead transmission lines[J].Proceedings of the CSEE,2010,30(19):100-105.(in Chinese)
[5]刘春城,刘佼.输电线路导线覆冰机理及雨凇覆冰模型[J].高电压技术,2011,37(1):241-248.LIU Chuncheng,LIU Jiao.Ice accretion mechanism and glaze loads model on wires of power transmission lines[J].High Voltage Engineering,2011,37(1):241-248.(in Chinese)
[6]KATHLEEN F J.A simple model for freezing rain iceloads[J].Atmospheric Research,1998,53(7):87-97
[7]黄晶,罗晓曙.神经网络在输电线覆冰增长因素中的应用[J].广西师范大学学报(自然科学版),2011,29(4):25-27.HUANG Jing,LUO Xiaoshu.Application of neural network in ice accretion over transmission line[J].Journal of Guangxi Normal University(Natural Science Edition),2011,29(4):25-27.(in Chinese)
[8]尹世锋,卢勇,王闸,等.基于CACA-WNN的恶劣气候条件下架空输电线路覆冰厚度的预测[J].电力科学与工程,2012,28(11):28-31.YIN Shifeng,LU Yong,WANG Zha,et al.Icing thickness forecasting of overhead transmission line under rough weather based on CACA-WNN[J].Electric Power Science and Engineering,2012,28(11):28-31.(in Chinese)
[9]谢运华.三峡地区导线覆冰与气象要素的关系[J].中国电力,2005,38(3):35-39.XIE Yunhua.The relation between meteorological elements and ice accretion in Three Gorges region[J].E-lectric Power,2005,38(3):35-39.(in Chinese)
[10]黄新波,孙钦东,张冠军,等.线路覆冰与局部气象因素的关系[J].高压电器,2008,44(4):289-294.HUANG Xinbo,SUN Qindong,ZHANG Guanjun,et al.Relation of transmission line icing and local meteorology[J].High Voltage Apparatus,2008,44(4):289-294.(in Chinese)
[11]IMAI I.Studies on ice accretion[J].Researches on Snow and Ice,1953,3(1):35-44.
[12]LENHARD R W.An indirect method for estimating the weight of glaze on wires[J].Bull Amer Meteor Soc,1955,36(3):1-5.
[13]苑吉河,蒋兴良,易辉,等.输电线路导线覆冰的国内外研究现状[J].高电压技术,2004,30(1):6-9.YUAN Jihe,JIANG Xingliang,YI Hui,et al.The present study on conductor icing of transmission lines[J].High Voltage Engineering,2004,30(1):6-9.(in Chinese)
[14]CHAINE P M,CASFONGUAY G.New approach to radial ice thickness concept applied to bundle-like conductors[R].Industrial Meteorology-study IV,Environment Canada,Toronto,1974,11.
[15]欧阳丽莎,黄新波.基于灰关联分析微气象因素和导线温度对输电线路导线覆冰的影响[J].高压电器,2011,47(3):31-36.OUYANG Lisha,HUANG Xinbo.Influences of meteorological conditions and conductor temperature on icing of transmission line based on grey relational analysis[J].High Voltage Apparatus,2011,47(3):31-36.(in Chinese)
[16]阳林,郝艳捧,黎卫国,等.输电线路覆冰与导线温度和微气象参数关联分析[J].高电压技术,2010,36(3):775-781.YANG Lin,HAO Yanpeng,LI Weiguo,et al.Relationships among transmission line icing,conductor temperature and local meteorology using grey relational analysis[J].High Voltage Engineering,2010,36(3):775-781.(in Chinese)
[17]邓聚龙.灰色理论基础[M].武汉:华中科技大学出版社,2002.DENG Julong.Grey theory foundation[M].Wuhan,China:Huazhong University of Science and Technology Press,2002.(in Chinese)
[18]孙才新,李俭,郑海平,等.基于灰色面积关联度分析的电力变压器绝缘故障诊断方法[J].电网技术,2002,26(7):24-29.SUN Caixin,LI Jian,ZHENG Haiping,et al.A new method of faulty insulation diagnosis in power transformer based on degree of area incidence analysis[J].Power System Technology,2002,26(7):24-29.(in Chinese)
[19]刘思峰,党耀国,方志耕.灰色系统理论及其应用[M].北京:科学出版社,2004.LIU Sifeng,DANG Yaoguo,FANG Zhigeng.Grey system theory and its application[M].Beijing:Science Press,2004.(in Chinese)
[20]杨朝霞,方健文,李佳蓉,等.粒子群优化算法在多参数拟合中的应用[J].浙江师范大学学报(自然科学版),2008,31(2):173-177.YANG Zhaoxia,FANG Jianwen,LI Jiarong,et al.Applicationg of particle swarm optimization to multiparameters fitting[J].Journal of Zhejiang Normal University(Natural Sciences),2008,31(2):173-177.(in Chinese)
[21]张选平,杜玉平,秦国强,等.一种动态改变惯性权的自适应粒子群算法[J].西安交通大学学报,2005,39(10):1039-1042.ZHANG Xuanping,DU Yuping,QIN Guoqiang,et al.Adaptive particle swarm algorithm with dynamically changing inertia weight[J].Journal of Xi’an Jiaotong University,2005,39(10):1039-1042.(in Chinese)
[22]周驰,高海兵,高亮,等.粒子群优化算法[J].计算机应用研究,2003,20(12):7-11.ZHOU Chi,GAO Haibing,GAO Liang,et al.Particle swarm optimization algorithm[J].Computer Application Research,2003,20(12):7-11.(in Chinese)
[23]张烈平,陈鸣,季文军.基于PSO优化LSSVR的三维WSN节点定位方法[J].中国科技论文,2014(1):24-27,44.ZHANG Lieping,CHEN Ming,JI Wenjun.Three-dimensional WSN node localization method based on LSS-VR optimized by PSO algorithm[J].China Sciencepaper 2014(1):24-27,44.(in Chinese)
[24]VAPNIK V.Nature of statistical learning theory[M].New York,USA:Springer Verlag,1999.
[25]SUYKENS J A K,VANDEWALLE J.Least squares support vector machine classifiers[J].Neural Processing Letters,1999,9(3):293-30.
[26]BROWNE M W.Cross-validation method[J].Journal of Mathematical Psychology,2000,44(1):108-132.
[27]尹子任,苏小林.基于粒子群算法优化支持向量机的输电线路覆冰预测[J].电力学报,2014(1):6-9,61.YING Ziren,SU Xiaolin.Icing thickness forecasting of transmission line based on particle swarm algorithm to optimize SVM[J].Journal of Electric Power,2014(1):6-9,61.(in Chinese)
[28]李佳杰.输电线路导线覆冰生长预测模型的理论研究[D].西安:西安工程大学,2013.LI Jiajie.Study on the model of forecasting icing growth on transmission lines[D].Xi’an,China:Xi’an Polytechnic University,2013.(in Chinese)
[29]蒋鸿林,张小苗,梁昌洪.基于有理函数逼近和MBPE结合恢复天线方向图[J].电波科学学报,2005,20(6):753-757.JIANG Honglin,ZHANG Xiaomiao,LIANG Changhong.Combination rational approach and MBPE technology to resume antenna radiation patterns[J].Chinese Journal of Radio Science,2005,20(6):753-757.(in Chinese)
[2]胡毅.电网大面积冰灾分析及对策探讨[J].高电压技术,2008,34(2):215-219.HU Yi.Analysis and countermeasures discussion for large area icing accident on power grid[J].High Voltage Engineering,2008,34(2):215-219.(in Chinese)
[3]刘和云,周迪,付俊萍,等.导线雨淞覆冰预测简单模型的研究[J].中国电机工程学报,2001,21(4):45-48.LIU Heyun,ZHOU Di,FU Junping,et al.A simple model for predicting glaze loads on wires[J].Proceedings of the CSEE,2001,21(4):45-48.(in Chinese)
[4]阳林,郝艳捧,黎卫国,等.架空输电线路在线监测覆冰力学计算模型[J].中国电机工程学报,2010,30(19):100-105.YANG Lin,HAO Yanpeng,LI Weiguo,et al.A mechanical calculation model for on-line icing-monitoring system of overhead transmission lines[J].Proceedings of the CSEE,2010,30(19):100-105.(in Chinese)
[5]刘春城,刘佼.输电线路导线覆冰机理及雨凇覆冰模型[J].高电压技术,2011,37(1):241-248.LIU Chuncheng,LIU Jiao.Ice accretion mechanism and glaze loads model on wires of power transmission lines[J].High Voltage Engineering,2011,37(1):241-248.(in Chinese)
[6]KATHLEEN F J.A simple model for freezing rain iceloads[J].Atmospheric Research,1998,53(7):87-97
[7]黄晶,罗晓曙.神经网络在输电线覆冰增长因素中的应用[J].广西师范大学学报(自然科学版),2011,29(4):25-27.HUANG Jing,LUO Xiaoshu.Application of neural network in ice accretion over transmission line[J].Journal of Guangxi Normal University(Natural Science Edition),2011,29(4):25-27.(in Chinese)
[8]尹世锋,卢勇,王闸,等.基于CACA-WNN的恶劣气候条件下架空输电线路覆冰厚度的预测[J].电力科学与工程,2012,28(11):28-31.YIN Shifeng,LU Yong,WANG Zha,et al.Icing thickness forecasting of overhead transmission line under rough weather based on CACA-WNN[J].Electric Power Science and Engineering,2012,28(11):28-31.(in Chinese)
[9]谢运华.三峡地区导线覆冰与气象要素的关系[J].中国电力,2005,38(3):35-39.XIE Yunhua.The relation between meteorological elements and ice accretion in Three Gorges region[J].E-lectric Power,2005,38(3):35-39.(in Chinese)
[10]黄新波,孙钦东,张冠军,等.线路覆冰与局部气象因素的关系[J].高压电器,2008,44(4):289-294.HUANG Xinbo,SUN Qindong,ZHANG Guanjun,et al.Relation of transmission line icing and local meteorology[J].High Voltage Apparatus,2008,44(4):289-294.(in Chinese)
[11]IMAI I.Studies on ice accretion[J].Researches on Snow and Ice,1953,3(1):35-44.
[12]LENHARD R W.An indirect method for estimating the weight of glaze on wires[J].Bull Amer Meteor Soc,1955,36(3):1-5.
[13]苑吉河,蒋兴良,易辉,等.输电线路导线覆冰的国内外研究现状[J].高电压技术,2004,30(1):6-9.YUAN Jihe,JIANG Xingliang,YI Hui,et al.The present study on conductor icing of transmission lines[J].High Voltage Engineering,2004,30(1):6-9.(in Chinese)
[14]CHAINE P M,CASFONGUAY G.New approach to radial ice thickness concept applied to bundle-like conductors[R].Industrial Meteorology-study IV,Environment Canada,Toronto,1974,11.
[15]欧阳丽莎,黄新波.基于灰关联分析微气象因素和导线温度对输电线路导线覆冰的影响[J].高压电器,2011,47(3):31-36.OUYANG Lisha,HUANG Xinbo.Influences of meteorological conditions and conductor temperature on icing of transmission line based on grey relational analysis[J].High Voltage Apparatus,2011,47(3):31-36.(in Chinese)
[16]阳林,郝艳捧,黎卫国,等.输电线路覆冰与导线温度和微气象参数关联分析[J].高电压技术,2010,36(3):775-781.YANG Lin,HAO Yanpeng,LI Weiguo,et al.Relationships among transmission line icing,conductor temperature and local meteorology using grey relational analysis[J].High Voltage Engineering,2010,36(3):775-781.(in Chinese)
[17]邓聚龙.灰色理论基础[M].武汉:华中科技大学出版社,2002.DENG Julong.Grey theory foundation[M].Wuhan,China:Huazhong University of Science and Technology Press,2002.(in Chinese)
[18]孙才新,李俭,郑海平,等.基于灰色面积关联度分析的电力变压器绝缘故障诊断方法[J].电网技术,2002,26(7):24-29.SUN Caixin,LI Jian,ZHENG Haiping,et al.A new method of faulty insulation diagnosis in power transformer based on degree of area incidence analysis[J].Power System Technology,2002,26(7):24-29.(in Chinese)
[19]刘思峰,党耀国,方志耕.灰色系统理论及其应用[M].北京:科学出版社,2004.LIU Sifeng,DANG Yaoguo,FANG Zhigeng.Grey system theory and its application[M].Beijing:Science Press,2004.(in Chinese)
[20]杨朝霞,方健文,李佳蓉,等.粒子群优化算法在多参数拟合中的应用[J].浙江师范大学学报(自然科学版),2008,31(2):173-177.YANG Zhaoxia,FANG Jianwen,LI Jiarong,et al.Applicationg of particle swarm optimization to multiparameters fitting[J].Journal of Zhejiang Normal University(Natural Sciences),2008,31(2):173-177.(in Chinese)
[21]张选平,杜玉平,秦国强,等.一种动态改变惯性权的自适应粒子群算法[J].西安交通大学学报,2005,39(10):1039-1042.ZHANG Xuanping,DU Yuping,QIN Guoqiang,et al.Adaptive particle swarm algorithm with dynamically changing inertia weight[J].Journal of Xi’an Jiaotong University,2005,39(10):1039-1042.(in Chinese)
[22]周驰,高海兵,高亮,等.粒子群优化算法[J].计算机应用研究,2003,20(12):7-11.ZHOU Chi,GAO Haibing,GAO Liang,et al.Particle swarm optimization algorithm[J].Computer Application Research,2003,20(12):7-11.(in Chinese)
[23]张烈平,陈鸣,季文军.基于PSO优化LSSVR的三维WSN节点定位方法[J].中国科技论文,2014(1):24-27,44.ZHANG Lieping,CHEN Ming,JI Wenjun.Three-dimensional WSN node localization method based on LSS-VR optimized by PSO algorithm[J].China Sciencepaper 2014(1):24-27,44.(in Chinese)
[24]VAPNIK V.Nature of statistical learning theory[M].New York,USA:Springer Verlag,1999.
[25]SUYKENS J A K,VANDEWALLE J.Least squares support vector machine classifiers[J].Neural Processing Letters,1999,9(3):293-30.
[26]BROWNE M W.Cross-validation method[J].Journal of Mathematical Psychology,2000,44(1):108-132.
[27]尹子任,苏小林.基于粒子群算法优化支持向量机的输电线路覆冰预测[J].电力学报,2014(1):6-9,61.YING Ziren,SU Xiaolin.Icing thickness forecasting of transmission line based on particle swarm algorithm to optimize SVM[J].Journal of Electric Power,2014(1):6-9,61.(in Chinese)
[28]李佳杰.输电线路导线覆冰生长预测模型的理论研究[D].西安:西安工程大学,2013.LI Jiajie.Study on the model of forecasting icing growth on transmission lines[D].Xi’an,China:Xi’an Polytechnic University,2013.(in Chinese)
[29]蒋鸿林,张小苗,梁昌洪.基于有理函数逼近和MBPE结合恢复天线方向图[J].电波科学学报,2005,20(6):753-757.JIANG Honglin,ZHANG Xiaomiao,LIANG Changhong.Combination rational approach and MBPE technology to resume antenna radiation patterns[J].Chinese Journal of Radio Science,2005,20(6):753-757.(in Chinese)