基于GA‑BP模型的大型接地网腐蚀速率预测方法
CSTR:
作者:
作者单位:

(1.五凌电力有限公司,湖南 长沙 410076;2.长沙理工大学电气与信息工程学院,湖南 长沙 410114)

通讯作者:

梁 峰(1995—),男,硕士研究生,主要从事电力设备状态评价和接地网状态评估与检测方面的研究;E?mail:792710378@qq.com

中图分类号:

TM862

基金项目:

国家自然科学基金(52177015);国家电投集团湖南五凌电力工程有限公司科技项目(320121SC0420220001)


Prediction method of corrosion rate of large‑scale grounding grid based on GA‑optimized BP neural network
Author:
Affiliation:

(1.Wuling Power Co., Ltd., Changsha 410076, China; 2.School of Electrical & Information Engineering, Changsha University of Science & Technology, Changsha 410114, China)

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [22]
  • | | | |
  • 文章评论
    摘要:

    接地网腐蚀速率是接地网腐蚀状态评估的一个重要方面。人工智能算法模型可以很好地预测接地网腐蚀速率,针对目前预测模型中特征输入量选取不够全面的问题,在对接地网进行电网络理论分析的基础上,确定接地网腐蚀采样点,提出以土壤理化性质和接地网电阻平均增长率为预测模型的特征输入量,采用遗传算法(genetic algorithm,GA)优化反向传播(back propagation,BP)神经网络,建立接地网腐蚀速率预测模型。将所提模型预测结果与未优化的BP神经网络模型和采用果蝇优化算法(fruit fly optimization algorithm,FOA)优化BP神经网络模型对比。在BP神经网络模型预测精度方面,GA算法相比于FOA算法,RMSE和MAPE值分别提高5.88%和1.5%,相比未经优化的BP神经网络模型,RMSE和MAPE值提高22.01%和4.96%。由此可见,提出的方法有更好的适用性。

    Abstract:

    The corrosion rate of grounding grid is an important aspect of corrosion state evaluation. The artificial intelligence algorithm model can predict the corrosion rate of the grounding grid well. In view of the problem that the selection of the characteristic input in the current prediction model is not comprehensive enough, based on the theoretical analysis of the grounding grid, the corrosion sampling point of the grounding grid is determined. The physical and chemical properties of the soil and the average growth rate of the grounding grid resistance are proposed as the characteristic input of the prediction model. The genetic algorithm (GA) is used to optimize the back propagation (BP) neural network, and the prediction model of the corrosion rate of the grounding grid is established. Compared with the unoptimized BP neural network model and the BP neural network model optimized by fruit fly optimization algorithm (FOA), the prediction performance of the proposed model is better and has better applicability.

    参考文献
    [1] 闫孝姮,林晓雪,吕秋皓,等.基于Homotopy-Tikhonov算法的接地网电阻抗成像方法[J].电工技术学报,2022,37(9):2284-2294. YAN Xiaoheng,LIN Xiaoxue,Lü Qiuhao,et al.Grounding grid electrical impedance tomography based on Homotopy-Tikhonov algorithm[J].Transactions of China Electrotechnical Society,2022,37(9):2284-2294.
    [2] 王乐天,刘振,宋萌清,等.基于矩量法的新建接地网对原接地网的影响[J].电网与清洁能源,2023,39(9):32-39+46. WANG Letian,LIU Zhen,SONG Mengqing,et al.Impact of newly built grounding grid on the original grounding grid based on the method of moments[J].Power System and Clean Energy,2023,39(9):32-39+46.
    [3] 李光茂,杜钢,王勇,等.湿热环境下电场作用对碳钢腐蚀行为的影响[J].高压电器,2022,58(6):144-149+156. LI Guangmao,DU Gang,WANG Yong,et al.Effect of electric field on corrosion behavior of carbon steel in humid and hot environment[J].High Voltage Apparatus,2022,58(6):144-149+156.
    [4] 贾文虎,徐群杰.海上风电设施防腐蚀技术研究进展[J].发电技术,2023,44(5):703-711. JIA Wenhu,XU Qunjie.Research progress of anti-corrosion technology for offshore wind power facilities[J].Power Generation Technology,2023,44(5):703-711.
    [5] 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 corrosion prediction of Q235 steel from soil in Hainan substation based on artificial neural network[D].Beijing:North China Electric Power University,2016.
    [6] 程宏伟,高莲,于虹,等.基于改进果蝇算法优化BP神经网络的接地网腐蚀速率预测模型[J].电测与仪表,2022,59(11):71-78. CHENG Hongwei,GAO Lian,YU Hong,et al.Corrosion rate prediction model of grounding grid based on BP neural network optimized by updated fruit fly optimization algorithm[J].Electrical Measurement & Instrumentation,2022,59(11):71-78.
    [7] 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.Predicting grounding grid corrosion rate based on fuzzy extensible analytic hierarchy process[J].Computer Applications and Software,2014,31(6):170-173+197.
    [8] 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 Jingyi,DU Bowei,HAN Juan,et al.A novel analyzing method to predict grounding grid corrosion rate[J].Mathematics in Practice and Theory,2015,45(19):123-130.
    [9] DECKER J B,ROLLINS K M,ELLSWORTH J C.Corrosion rate evaluation and prediction for piles based on long-term field performance[J].Journal of Geotechnical and Geoenvironmental Engineering,2008,134(3):341-351.
    [10] SEICA M V,PACKER J A,GRABINSKY M W,et al.Evaluation of the properties of Toronto iron water mains and surrounding soil[J].Canadian Journal of Civil Engineering,2002,29(2):222-237.
    [11] CHENDORAIN M D,STEWART L D,PACKER B.Corrosion of unexploded ordnance in soil-field results[J].Environmental Science & Technology,2005,39(8):2442-2447.
    [12] 王海涛,陈明,文中,等.基于KPCA-ISHO-LSSVM的接地网腐蚀速率预测[J].智慧电力,2022,50(2):62-68. WANG Haitao,CHEN Ming,WEN Zhong,et al.Corrosion rate prediction of grounding grid based on KPCA-ISHO-LSSVM[J].Smart Power,2022,50(2):62-68.
    [13] 刘渝根,陈超.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[J].电力自动化设备,2019,39(5):182-186+200. LIU Yugen,CHEN Chao.Corrosion rate prediction model of grounding grid based on support vector machine optimized by artificial bee colony algorithm[J].Electric Power Automation Equipment,2019,39(5):182-186+200.
    [14] 李文彬,王勇,冯砚厅,等.基于改进CL-ML方法的接地网不开挖腐蚀速率预测模型[J].电力科学与工程,2021,37(4):49-54. LI Wenbin,WANG Yong,FENG Yanting,et al.The non-excavation corrosion rate prediction model of grounding grid based on improved CL-ML method[J].Electric Power Science and Engineering,2021,37(4):49-54.
    [15] 陈敬友,陈超,吴迪,等.接地网腐蚀性评价方法与腐蚀速率预测[J].腐蚀与防护,2021,42(3):64-67+78. CHEN Jingyou,CHEN Chao,WU Di,et al.Corrosion evaluation method and corrosion rate prediction of grounding grid[J].Corrosion & Protection,2021,42(3):64-67+78.
    [16] 张树亮,刘东亮,徐洪福,等.基于磁场分布特性的接地网腐蚀断点检测方法研究[J].电瓷避雷器,2021(1):51-55+62. ZHANG Shuliang,LIU Dongliang,XU Hongfu,et al.Detection method of corrosion breakpoint of grounding grid based on distribution characteristics of magnetic field[J].Insulators and Surge Arresters,2021(1):51-55+62.
    [17] 粟渊恺,刘盛祥,范力权,等.高土壤电阻率地区500 kV变电站过电压防护复合接地研究[J].电力科学与技术学报,2017,32(3):75-80.SU Yuankai,LIU Shengxiang,FAN Liquan,et al.Study on the over-voltage protection compound grounding in 500 kV substation with high soil resistivity[J].Journal of Electric Power Science and Technology,2017,32(3):75-80.
    [18] 谭媛,张文海,王杨.基于多源信息融合的配网故障外部原因识别[J].电力建设,2023,44(3):77-84. TAN Yuan,ZHANG Wenhai,WANG Yang.Distribution system external fault causes identification based on multi-source information fusion[J].Electric Power Construction,2023,44(3):77-84.
    [19] 于艾清,丁丽青,王育飞,等.基于故障邻接状态的配电网多故障抢修与优化策略[J].中国电力,2023,56(3):64-76. YU Aiqing,DING Liqing,WANG Yufei,et al.Multi-fault repair and optimization strategy of distribution network based on fault adjacency state[J].Electric Power,2023,56(3):64-76.
    [20] 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.Grounding grid fault diagnosis based on node tearing and chemical reaction optimization algorithm[J].Electric Power Automation Equipment,2017,37(1):163-168+175.
    [21] 彭茜,王爱娟,李峻阳,等.基于高效遗传算法的电网需求侧调度优化研究及其收敛性分析[J].电力系统保护与控制,2022,50(6):33-42. PENG Qian,WANG Aijuan,LI Junyang,et al.Optimization of the demand side dispatching of a power grid based on an efficient genetic algorithm and its convergence analysis[J].Power System Protection and Control,2022,50(6):33-42.
    [22] 李博通,孙铭阳,陈晓龙,等.无相位量测的多环中压配电网线路参数辨识方法[J].电力系统自动化,2023,47(24):22-30. LI Botong,SUN Mingyang,CHEN Xiaolong,et al.Line parameter identification method for multi-ring medium-voltage distribution network based on phaseless measurement[J].Automation of Electric Power Systems,2023,47(24):22-30.
    相似文献
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

彭威龙,曾松梧,张宝庆,等.基于GA‑BP模型的大型接地网腐蚀速率预测方法[J].电力科学与技术学报,2024,(3):264-270.
PENG Weilong, ZENG Songwu, ZHANG Baoqing, et al. Prediction method of corrosion rate of large‑scale grounding grid based on GA‑optimized BP neural network[J]. Journal of Electric Power Science and Technology,2024,(3):264-270.

复制
分享
文章指标
  • 点击次数:157
  • 下载次数: 256
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 在线发布日期: 2024-07-25
文章二维码