基于人工蜂群算法优化支持向量机的接地网腐蚀速率预测模型
|
摘要
为了提高接地网腐蚀速率预测的精确度,在建立预测模型的过程中,首先对接地网进行了基于电网络理论的腐蚀诊断过程,并以经过诊断之后确定的腐蚀支路位置为采样点。考虑到仅以土壤理化性质反映接地网腐蚀速率的局限性,在接地网腐蚀诊断结果的基础上,提出接地网电阻平均增长速率作为预测模型的输入特征量之一。建立了基于人工蜂群优化支持向量机的接地网腐蚀速率预测模型,测试结果显示相对BP神经网络模型和广义回归神经网络模型,所提模型的预测结果精确度和稳定性更高,表明了对于解决接地网腐蚀速率预测问题,所提模型具有良好的适用性。
In order to improve the accuracy of corrosion rate prediction for grounding grid,firstly the corrosion diagnosis of grounding grid based on the theory of electric network is carried out,and the position of corrosion branches after diagnosis are taken as sampling points. Considering the limitation of reflecting the corrosion rate prediction of grounding grid only by soil physical and chemical properties,and based on the result of corrosion diagnosis,the ave-rage growth rate of resistance in grounding grid is proposed as one of the input characteristics of the prediction mo-del. Then the corrosion rate prediction model of grounding grid based on the support vector machine optimized by artificial bee colony algorithm is proposed. The test results show that compared with the BP neural network model and generalized regression neural network model,the proposed model has higher prediction precision and stability,and good applicability to solve the problem of corrosion rate prediction for grounding grid.
In order to improve the accuracy of corrosion rate prediction for grounding grid,firstly the corrosion diagnosis of grounding grid based on the theory of electric network is carried out,and the position of corrosion branches after diagnosis are taken as sampling points. Considering the limitation of reflecting the corrosion rate prediction of grounding grid only by soil physical and chemical properties,and based on the result of corrosion diagnosis,the ave-rage growth rate of resistance in grounding grid is proposed as one of the input characteristics of the prediction mo-del. Then the corrosion rate prediction model of grounding grid based on the support vector machine optimized by artificial bee colony algorithm is proposed. The test results show that compared with the BP neural network model and generalized regression neural network model,the proposed model has higher prediction precision and stability,and good applicability to solve the problem of corrosion rate prediction for grounding grid.
引文
[1] 周斌,彭敏放,黄清秀,等.基于节点撕裂和化学反应优化算法的接地网故障诊断[J].电力自动化设备,2017,37(1):163-168,175.ZHOU Bin,PENG Minfang,HUANG Qingxiu,et al.Fault diagnosis of grounding network based on the node tearing and chemical reaction optimization algorithm[J].Electric Power Automation Equipment,2017,37(1):163-168,175.
[2] 吕超,刘利强,胡凯旋,等.测试点偏移时的接地网腐蚀故障诊断方法[J].电力自动化设备,2016,36(1):155-161,168.Lü Chao,LI Liqiang,HU Kaixuan,et al.The corrosion fault diagnosis methods of grounding network with test point offset[J].Electric Power Automation Equipment,2016,36(1):155-161,168.
[3] 杨滔.接地网腐蚀状态检测及其寿命预测[D].长沙:湖南大学,2011.YANG Tao.Corrosion detection and life prediction of grounding network[D].Changsha:Hunan University,2011.
[4] 郭阳阳.基于神经网络的海南变电站土壤对Q235钢的腐蚀预测研究[D].北京:华北电力大学,2016.GUO Yangyang.Study on the corrosion prediction of Q235 steel in Hainan substation based on neural network[D].Beijing:North China Electric Power University,2016.
[5] 杜京义,韩娟,寇水潮,等.基于模糊可拓层次分析的接地网腐蚀速率预测[J].计算机应用与软件,2014,31(6):170-173,197.DU Jingyi,HAN Juan,KOU Shuichao,et al.Prediction of corrosion rate of grounding network based on fuzzy extension level analysis[J].Computer Application and Software,2014,31(6):170 -173,197.
[6] 杜京义,杜博玮,韩娟,等.一种预测接地网腐蚀速率的新方法[J].数学的实践与认识,2015,45(19):123-130.DU Jinyi,DU Bowei,HAN Juan,et al.A new method for predicting corrosion rate of grounding network[J].Mathematics in Practice and Theory,2015,45(19):123-130.
[7] 刘渝根,肖磊石,李谦,等.接地网故障诊断平台的功能与构建研究[J].高压电器,2011,47(9):78-83.LIU Yugen,XIAO Leishi,LI Qian,et al.Study on function and construction of fault diagnosis platform of grounding network[J].High Voltage Apparatus,2011,47(9):78-83.
[8] 刘渝根,王硕,田金虎,等.接地网腐蚀诊断优化测量方法[J].重庆大学学报,2008(11):1303-1306.LIU Yugen,WANG Shuo,TIAN Jinhu,et al.A method for optimizing the diagnosis and measurement of ground network corrosion[J].Journal of Chongqing University,2008(11):1303-1306.
[9] 闫爱军,陈沂,冯拉俊.几种接地网材料在土壤中的腐蚀特性研究[J].腐蚀科学与防护技术,2010,22(3):197-199.YAN Aijun,CHEN Yi,FENG Lajun.Study on corrosion characte-ristics of several grounding materials in soil[J].Corrosion Science and Protection Technology,2010,22(3):197-199.
[10] 王磊静,徐松,朱志平,等.红壤中变电站接地网金属材料的腐蚀行为分析[J].腐蚀科学与防护技术,2015,27(1):59-63.WANG Leijing,XU Song,ZHU Zhiping,et al.Analysis of corrosion behavior of metallic materials in substation in red soil[J].Corrosion Science and Protection Technology,2015,27(1):59-63.
[11] 朱志平,马骁,荆玲玲,等.变电站土壤腐蚀性评价及接地网金属腐蚀特性分析[J].电瓷避雷器,2009(4):18-22,26.ZHU Zhiping,MA Xiao,JING Lingling,et al.Evaluation of soil corrosion in substation and analysis of corrosion characteristics of ground wire[J].Insulators and Surge Arresters,2009(4):18-22,26.
[12] 王鑫.接地网腐蚀现场检测及化学镀镍防护技术[D].天津:天津大学,2012.WANG Xin.Site detection and electroless nickel plating protection technology[D].Tianjin:Tianjin University,2012.
[13] 张镱议,焦健,汪可,等.基于帝国殖民竞争算法优化支持向量机的电力变压器故障诊断模型[J].电力自动化设备,2018,38(1):99-104.ZHANG Yiyi,JIAO Jian,WANG Ke,et al.Power transformer fault diagnosis model based on the support vector machine optimized by imperial competition algorithm[J].Electric Power Automation Equipment,2011,38(1):99-104.
[14] 陈伟根,滕黎,刘军,等.基于遗传优化支持向量机的变压器绕组热点温度预测模型[J].电工技术学报,2014,29(1):44-51.CHEN Weigen,TENG Li,LIU Jun,et al.Transformer winding hot-spot temperature prediction model of support vector machine optimized by genetic algorithm[J].Transation of China Electrotechnical Society,2014,29(1):44-51.
[15] 赵辉,李牧东,翁兴伟.具有自适应全局最优引导快速搜索策略的人工蜂群算法[J].控制与决策,2014,29(11):2041-2047.ZHAO Hui,LI Mudong,WENG Xingwei.Artificial bee colony with adaptive global optimal guidance for fast search strategy[J].Control and Decision,2014,29(11):2041-2047.
[16] 陈伟根,奚红娟,苏小平,等.广义回归神经网络在变压器绕组热点温度预测中的应用[J].高电压技术,2012,38(1):16-21.CHEN Weigen,XI Hongjuan,SU Xiaoping,et al.Application of ge-neralized regression neural network in transformer winding hot temperature prediction[J].High Voltage Technology,2012,38(1):16-21.
[2] 吕超,刘利强,胡凯旋,等.测试点偏移时的接地网腐蚀故障诊断方法[J].电力自动化设备,2016,36(1):155-161,168.Lü Chao,LI Liqiang,HU Kaixuan,et al.The corrosion fault diagnosis methods of grounding network with test point offset[J].Electric Power Automation Equipment,2016,36(1):155-161,168.
[3] 杨滔.接地网腐蚀状态检测及其寿命预测[D].长沙:湖南大学,2011.YANG Tao.Corrosion detection and life prediction of grounding network[D].Changsha:Hunan University,2011.
[4] 郭阳阳.基于神经网络的海南变电站土壤对Q235钢的腐蚀预测研究[D].北京:华北电力大学,2016.GUO Yangyang.Study on the corrosion prediction of Q235 steel in Hainan substation based on neural network[D].Beijing:North China Electric Power University,2016.
[5] 杜京义,韩娟,寇水潮,等.基于模糊可拓层次分析的接地网腐蚀速率预测[J].计算机应用与软件,2014,31(6):170-173,197.DU Jingyi,HAN Juan,KOU Shuichao,et al.Prediction of corrosion rate of grounding network based on fuzzy extension level analysis[J].Computer Application and Software,2014,31(6):170 -173,197.
[6] 杜京义,杜博玮,韩娟,等.一种预测接地网腐蚀速率的新方法[J].数学的实践与认识,2015,45(19):123-130.DU Jinyi,DU Bowei,HAN Juan,et al.A new method for predicting corrosion rate of grounding network[J].Mathematics in Practice and Theory,2015,45(19):123-130.
[7] 刘渝根,肖磊石,李谦,等.接地网故障诊断平台的功能与构建研究[J].高压电器,2011,47(9):78-83.LIU Yugen,XIAO Leishi,LI Qian,et al.Study on function and construction of fault diagnosis platform of grounding network[J].High Voltage Apparatus,2011,47(9):78-83.
[8] 刘渝根,王硕,田金虎,等.接地网腐蚀诊断优化测量方法[J].重庆大学学报,2008(11):1303-1306.LIU Yugen,WANG Shuo,TIAN Jinhu,et al.A method for optimizing the diagnosis and measurement of ground network corrosion[J].Journal of Chongqing University,2008(11):1303-1306.
[9] 闫爱军,陈沂,冯拉俊.几种接地网材料在土壤中的腐蚀特性研究[J].腐蚀科学与防护技术,2010,22(3):197-199.YAN Aijun,CHEN Yi,FENG Lajun.Study on corrosion characte-ristics of several grounding materials in soil[J].Corrosion Science and Protection Technology,2010,22(3):197-199.
[10] 王磊静,徐松,朱志平,等.红壤中变电站接地网金属材料的腐蚀行为分析[J].腐蚀科学与防护技术,2015,27(1):59-63.WANG Leijing,XU Song,ZHU Zhiping,et al.Analysis of corrosion behavior of metallic materials in substation in red soil[J].Corrosion Science and Protection Technology,2015,27(1):59-63.
[11] 朱志平,马骁,荆玲玲,等.变电站土壤腐蚀性评价及接地网金属腐蚀特性分析[J].电瓷避雷器,2009(4):18-22,26.ZHU Zhiping,MA Xiao,JING Lingling,et al.Evaluation of soil corrosion in substation and analysis of corrosion characteristics of ground wire[J].Insulators and Surge Arresters,2009(4):18-22,26.
[12] 王鑫.接地网腐蚀现场检测及化学镀镍防护技术[D].天津:天津大学,2012.WANG Xin.Site detection and electroless nickel plating protection technology[D].Tianjin:Tianjin University,2012.
[13] 张镱议,焦健,汪可,等.基于帝国殖民竞争算法优化支持向量机的电力变压器故障诊断模型[J].电力自动化设备,2018,38(1):99-104.ZHANG Yiyi,JIAO Jian,WANG Ke,et al.Power transformer fault diagnosis model based on the support vector machine optimized by imperial competition algorithm[J].Electric Power Automation Equipment,2011,38(1):99-104.
[14] 陈伟根,滕黎,刘军,等.基于遗传优化支持向量机的变压器绕组热点温度预测模型[J].电工技术学报,2014,29(1):44-51.CHEN Weigen,TENG Li,LIU Jun,et al.Transformer winding hot-spot temperature prediction model of support vector machine optimized by genetic algorithm[J].Transation of China Electrotechnical Society,2014,29(1):44-51.
[15] 赵辉,李牧东,翁兴伟.具有自适应全局最优引导快速搜索策略的人工蜂群算法[J].控制与决策,2014,29(11):2041-2047.ZHAO Hui,LI Mudong,WENG Xingwei.Artificial bee colony with adaptive global optimal guidance for fast search strategy[J].Control and Decision,2014,29(11):2041-2047.
[16] 陈伟根,奚红娟,苏小平,等.广义回归神经网络在变压器绕组热点温度预测中的应用[J].高电压技术,2012,38(1):16-21.CHEN Weigen,XI Hongjuan,SU Xiaoping,et al.Application of ge-neralized regression neural network in transformer winding hot temperature prediction[J].High Voltage Technology,2012,38(1):16-21.