基于改进BP神经网络的变电站检修运维成本预测
CSTR:
作者:
通讯作者:

熊一(1988-),男,博士,主要从事电网管理等研究;E-mail:675786099@qq.com

中图分类号:

TM-9

基金项目:

国网湖北省电力有限公司科技项目(52153820000A);国家自然科学基金(91746118);湖南省自然科学基金(2019JJ40302)


Overhaul operation and maintenance cost prediction of substation based on improved BP neural network
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [18]
  • |
  • 相似文献
  • |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    变电站的检修运维成本受众多复杂因素影响,且检修费用数据记录具有模糊性和波动性。为解决检修费用记录不明的问题,首先对变电站检修条目划分并采用水平和垂直方向的数据分析方法进行处理,再利用 BP神经网络预测检修运维成本。为提高 BP神经网络预测精度,采用 K-fold交叉验证对原始数据训练模型进行精准调整,应用遗传算法对 BP神经网路的初始值和阀值进行调整和改进,从而建立基于遗传算法的改进 BP神经网络检修运维成本预测方法。以某地市变电站为例进行变电检修运维成本预测,对比分析显示所提方法能有效提高模型预测精准度,从而为电网给变电站拨付检修费用提供参考价值。

    Abstract:

    Overhaul operation and maintenance costs of substations are affected by many complicated factors. Fuzzy and fluctuating data records of maintenance costs worsen the situation. In order to solve the unclearness of the overhaul cost record, this paper firstly divides the substation maintenance items and uses data analysis method of horizontal and vertical direction to process the items. Then BP neural network is used to predict the maintenance cost. In order to improve the accuracy of BP neural network prediction,Kfold crossvalidation is used to accurately adjust the original data training model. The genetic algorithm is used to adjust and improve the initial value and threshold of the BP neural network. Therefore an improved BP neural network maintenance and operation cost prediction method is established based on the genetic algorithm. Taking a substation in a certain city as an example to predict the operation and maintenance cost of substation maintenance, comparative analysis shows that the proposed method can effectively improve the accuracy of model prediction, thereby providing reference value for the power grid to allocate maintenance costs to substations.

    参考文献
    [1] 顾洁,杜渐,秦杰,等.基于全寿命周期成本的变电站设备检修模糊规划模型[J].电力系统自动化,2014,38(1):44-50.GU Jie,DU Jian,QIN Jie,et al.A fuzzy programming model based on life cycle cost for equipment maintenance in substations[J].Automation of Electric Power Systems,2014,38(1):44-50.
    [2] 何旭,姜宪国,张沛超,等.考虑检修策略的智能变电站保护系统可用性分析[J].电网技术,2015,39(4):1121-1128.HE Xu,JIANG Xianguo,ZHANG Peichao,et al.Availability analysis of smart substation protection system considering maintenance strategies[J].Power System Technology,2015,39(4):1121-1128.
    [3] 郭丽娟,陶松梅,张炜,等.兼顾供电可靠性和LCC的变电站主设备检修策略优化方法[J].电力系统自动化,2016,40(15):99-105.GUO Lijuan,TAO Songmei,ZHANG Wei,et al.Maintenance strategy optimization for main equipment in substations considering both power supply reliability and life cycle cost[J].Automation of Electric Power Systems,2016,40(15):99-105.
    [4] 刘苏,姚建刚,韦亦龙,等.基于Monte Carlo的主变压器全寿命周期成本研究[J].电源技术,2017,41(2):312-315.LIU Su,YAO Jiangang,WEI Yilong,et al.Life cycle cost study of main transformer based on Monte Carlo[J].Chinese Journal of Power Sources,2017,41(2):312-315.
    [5] 蔡嘉,江修波.基于贝叶斯算法的220 kV变压器故障检修成本模型分析[J].电力科学与技术学报,2013,28(4):15-18.CAI Jia,JIANG Xiubo.Bayesian econometrics method based maintenance cost model for 220 kV transformers[J].Journal of Electric Power Science and Technology,2013,28(4):15-18.
    [6] 黄俊宁,于群.基于多源数据融合与设备相似性的高压开关柜评价模型[J/OL].高压电器:17[20210427].http://kns.cnki.net/kcms/detail/61.1127.TM.20210426.1645.002.html.Huang Junning,YU Qun.High voltage switch cabinet evaluation model based on multisource data fusion and equipment similarity[J/OL].High Voltage Apparatus,17[20210427].http://kns.cnki.net/kcms/detail/61.1127.TM.20210426.1645.002.html.
    [7] 钱海,贾松江,杨飞,等.基于移动互联的继电保护设备智能运维技术研究[J].智慧电力,2019,47(11):60-66.QIAN Hai,JIA Songjiang,YANG Fei,et al.Intelligent operation and maintenance technology for relay protection equipment based on mobile internet[J].Smart Power,2019,47(11):60-66.
    [8] 韩俊,谢珍建,黄河,等.基于停电损失计算与成本分析的配电网单元制供电网格可靠性规划[J].智慧电力,2020,48(1):63-68+117.HAN Jun,XIE Zhenjian,HUANG He,et al.Unit mesh reliability planning for distribution network based on outage cost calculation and cost analysis[J].Smart Power,2020,48(1):63-68+117.
    [9] 付成然,何永秀.基于解释结构模型的变电设备实物资产效益影响因素分析[J].山东电力技术,2019,46(5):35-40.FU Chengran,HE Yongxiu.Analysis on influencing factors of physical assets benefit of substation equipment based on interpretative structural model[J].Shandong Electric Power,2019,46(5):35-40.
    [10] 李正明,梁彩霞,王满商.基于PSODBN神经网络的光伏短期发电出力预测[J].电力系统保护与控制,2020,48(8):149-154.LI Zhengming,LIANG Caixia,WANG Manshang.Shortterm power generation output prediction based on a PSODBN neural network[J] Power System Protection and Control,2020,48(8):149-154.
    [11] 王宏刚,田洪迅,李浩松,等.考虑小样本统计的BP神经网络配电系统可靠性预测方法[J].电力科学与技术学报,2019,34(2):40-46.WANG Honggang,TIAN Hongxun,LI Haosong,et al.Reliability prediction method of power system based on a BP neural network considering small samples[J].Journal of Electric Power Science and Technology,2019,34(2):40-46.
    [12] 何廷一,田鑫萃,李胜男,等.基于蜂群算法改进的BP神经网络风电功率预测[J].电力科学与技术学报,2018,33(4):22-28.HE Tingyi,TIAN Xincui,LI Shengnan,et al.Improved BP neural network based on Artificial Bee Colony algorithm for wind power prediction[J].Journal of Electric Power Science and Technology,2018,33(4):22-28.
    [13] 汉京善,吕海平,李丹煜,等.基于GABP神经网络算法的输电线路舞动预警方法[J].电网与清洁能源,2021,37(4):17+14.HAN Jingshan,LV Haiping,LI Danyu,et al.Prediction of transmission line galloping using improved BP neural network based on genetic algorithm[J].Power System and Clean Energy,2021,37(4):17+14.
    [14] 黄玲玲,寻健,王浩.海上风机综合检修优化策略[J].电测与仪表,2020,57(22):112-119.HUANG Lingling,XUN Jian,WANG Hao.Optimization strategy for comprehensive maintenance of offshore wind turbines[J].Electrical Measurement & Instrumentation,2020,57(22):112-119.
    [15] 张武军,程远林,周捷,等.基于特性分析的改进BP神经网络短期电力预测方法[J].湖南电力,2020,40(3):17-22.ZHANG Wujun,CHENG Yuanlin,ZHOU Jie,et al.Short term power forecasting method of improved BP neural network based on characteristic analysis[J].Hunan Electric Power,2020,40(3):17-22.
    [16] 何凯,王剑晓,王佳伟,等.基于全成本电价的电网规划方案评估与优选[J].中国电力,2020,53(3):66-75.HE Kai,WANG Jianxiao,WANG Jiawei,et al.Evaluation and optimization of power network planning scheme based on totalcost price[J].Electric Power,2020,53(3):66-75.
    [17] 刘巍,李锰,李秋燕,等.基于改进遗传算法的电网投资组合预测方法[J].电力系统保护与控制,2020,48(8):78-85.LIU Wei,LI Meng,LI Qiuyan,et al.Power grid portfolio forecasting method based on an improved genetic algorithm[J].Power System Protection and Control,2020,48(8):78-85.
    [18] 吕何,孔政敏,张成刚.基于混合优化随机森林回归的短期电力负荷预测[J].武汉大学学报(工学版),2020,53(8):704-711.LV He,KONG Zhengmin,ZHANG Chenggang.Short term load forecasting based on hybrid optimized random forest regression[J].Engineering Journal of Wuhan University,2020,53(8):704-711.
    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

熊一,詹智红,柯方超,等.基于改进BP神经网络的变电站检修运维成本预测[J].电力科学与技术学报,2021,36(4):44-52.
Xiong Yi, Zhan Zhihong, Ke Fangchao, et al. Overhaul operation and maintenance cost prediction of substation based on improved BP neural network[J]. Journal of Electric Power Science and Technology,2021,36(4):44-52.

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 在线发布日期: 2021-08-28
文章二维码