基于K-means聚类和随机森林的电缆风险评估及修复决策
CSTR:
作者:
作者单位:

1.南方电网广东广州供电局电力试验研究院,广州 510000;2.南京航空航天大学自动化学院,南京 211106

通讯作者:

杨帆,男,工程师,E-mail: yangfansyy@126.com。

中图分类号:

TM75

基金项目:

广州供电局配网类科技项目(GZHKJXM20200028)。


Cable Risk Assessment and Repair Decision Based on K-means Clustering and Random Forest
Author:
Affiliation:

1.Power Test and Research Institute of China Southern Power Grid Guangdong Guangzhou Power Supply Bureau, Guangzhou 510000, China;2.College of Automation Engineering, Nanjing University of Aeronautics & Astronautics, Nanjing 211106, China

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [18]
  • | | | |
  • 文章评论
    摘要:

    交联聚乙烯电缆是10 kV配电系统中的重要设备,其安全性至关重要。对电缆的修复决策做出科学判断,有助于提高配电系统的安全性并降低经济成本。鉴于此,本文提出了一种基于K-means聚类和随机森林(Random forest, RF)分类模型的电缆风险评估及修复决策方法。该方法首先根据电缆的绝缘状态,定义电缆的风险等级和风险程度;然后利用K-means聚类算法对多个老化指标进行聚类以实现风险等级区间的划分,从而建立多老化指标风险矩阵;基于多老化指标风险矩阵,利用综合权重法确定多维老化指标所对应的分类标签;最后基于RF算法建立并训练电缆的修复决策分类模型,输出电缆的修复决策结果。所提方法的平均正确率达到99.70%,实现了电缆快速且可靠的修复决策。

    Abstract:

    Crosslinked polyethylene cable is an important equipment in 10 kV distribution system, and its safety is very important. Making scientific judgments on cable repair decisions can help improve the safety and reduce the economic cost. In view of this, a cable risk assessment and repair decision method based on K-means clustering and random forest(RF) classification model is proposed. The method first defines the risk level and risk degree of the cable based on the insulation status of the cable. Then the K-means clustering algorithm is used to cluster the multi-aging index dataset and classify the risk level intervals to build a multi-aging index risk matrix. Based on the risk matrix of the multi-aging index, the classification labels corresponding to the multi-aging index are determined by using the comprehensive weight method. Finally, the classification model of the repair ways of the cables is established and trained based on the RF algorithm, and the selection results of the repair ways are output. The average accuracy of the proposed method reaches 99.70%, achieving rapid and reliable repair decisions for cables.

    参考文献
    [1] 时珊珊,崔正达,陈颖,等. 电气化交通和城市电网协同韧性提升方法综述[J].电工电能新技术,2022,41(3): 43-54.SHI Shanshan, CUI Zhengda, CHEN Ying, et al. Summary of methods for improving the collaborative resilience of electrified transportation and urban power grid[J]. Advanced Technology of Electrical Engineering and Energy, 2022,41(3): 43-54.
    [2] ZHANG Xi, LIU Youbo, DUAN Jiajun,et al. DDPG-based multi-agent framework for SVC tuning in urban power grid with renewable energy resources[J]. IEEE Transactions on Power Systems, 2021, 36(6): 5465-5475.
    [3] 冯庆燎,陈申宇,张攀. 基于配网管廊的电力、通信两张网运营环境改善初探[C]//2017年度中国电力企业管理创新实践优秀论文大赛论文集(上册). 北京: 中国电力企业管理, 2018: 306-311.FENG Qingliao, CHEN Shenyu, ZHANG Pan. Preliminary exploration of improving the operation environment of power and communication dual networks based on distribution network corridors[C]//Proceedings of the 2017 Annual China Electric Power Enterprise Management Innovation Practice Excellent Paper Competition(Volume I). Beijing: China Electric Power Enterprise Management, 2018: 306-311.
    [4] 张文涛. 电缆及电缆沟实时综合防控系统初探[J]. 企业技术开发, 2015, 34(29): 15-16.ZHANG Wentao. Preliminary study on real-time comprehensive prevention and control system of cable and cable trench[J]. Technology Development of Enterprise, 2015, 34(29): 15-16.
    [5] 黄新波,吴明松,朱永灿,等. 基于模糊数学的电缆线路风险评估模型研究[J].高压电器, 2021,57(9):19-25.HUANG Xinbo, WU Mingsong, ZHU Yongcan, et al. Research on the risk assessment model of cable lines based on fuzzy mathematics[J]. High Voltage Apparatus, 2021, 57(9): 19-25.
    [6] 廖雁群,袁婧,徐小冰,等. 基于风险评估的高压电缆巡检周期优化模型[J].高电压技术,2021,47(1):305-314.LIAO Yanqun, YUAN Jing, XU Xiaobing, et al. Optimization model for high-voltage cable inspection cycle based on risk assessment[J]. High Voltage Engineering, 2021, 47(1): 305-314.
    [7] 吴明松,黄新波,朱永灿,等. 基于层次分析法的电缆线路风险评估[J].西安工程大学学报, 2019, 33(6): 637-642.WU Mingsong, HUANG Xinbo, ZHU Yongcan, et al. Risk assessment of cable lines based on analytic hierarchy process[J]. Journal of Xi’an Polytechnic University, 2019, 33(6): 637-642.
    [8] 李慧,徐海亮,王浩,等. 基于改进鲸鱼算法优化支持向量机的故障诊断的研究与应用[J]. 科学技术与工程, 2022, 22(13): 5284-5290.LI Hui, XU Hailiang, WANG Hao,et al. Research and application of fault diagnosis based on support vector machine optimized by improved whale algorithm[J]. Science and Technology and Engineering, 2022, 22(13): 5284-5290.
    [9] 恽钰蛟,贾鹏,伍兴达,等. 基于慢特征分析和随机森林的风叶结冰故障监测[J]. 工业控制计算机, 2022, 35(6): 103-105.YUN Yujiao,JIA Peng,WU Xingda,et al. Wind blade icing fault monitoring based on slow feature analysis and random forest[J]. Industrial Control Computer, 2022, 35(6): 103-105.
    [10] 王丽,陈基漓,谢晓兰,等. 基于混沌天牛群算法优化的神经网络分类模型[J]. 科学技术与工程, 2022, 22(12): 4854-4863.WANG Li,CHEN Jili,XIE Xiaolan,et al. Neural network classification model based on chaotic beetle swarm optimization[J]. Science and Technology and Engineering, 2022, 22(12): 4854-4863.
    [11] HE W, HE Y G, LI B, et al. A naive-bayes-based fault diagnosis approach for analog circuit by using image-oriented feature extraction and selection technique[J]. IEEE Access, 2020, 8: 5065-5079.
    [12] NAIMI A, DENG J, SHIMJITH S, et al. Fault detection and isolation of a pressurized water reactor based on neural network and K-nearest neighbor[J]. IEEE Access, 2022, 10: 17113-17121.
    [13] 宋鹏先,王浩鸣,房晟辰,等. 基于综合健康指数的热缩材料寿命评估模型[J]. 绝缘材料, 2020, 53(11): 45-49.SONG Pengxian, WANG Haoming, FANG Shengchen, et al. A life assessment model for heat shrinkable materials based on comprehensive health index[J]. Insulation Materials, 2020, 53(11): 45-49.
    [14] 许小勇,钟太勇. 三次样条插值函数的构造与Matlab实现[J]. 兵工自动化, 2006, 25(11): 76-78.XU Xiaoyong, ZHONG Taiyong. Construction and Matlab implementation of cubic spline interpolation function[J]. Army Automation, 2006, 25(11): 76-78.
    [15] 刘亮,许灵,刘斯文. 基于K-Means聚类的高校困难学生贫困等级划分研究:以蚌埠学院为例[J]. 白城师范学院学报, 2017, 31(8): 32-35, 58.LIU Liang, XU Ling, LIU Siwen. Poverty grading of poor college students based on K-means clustering: A case study of bengbu college[J]. Journal of Baicheng Normal University, 2017, 31(8): 32-35, 58.
    [16] Breiman. Random forests[J]. Machine Learning. 2001, 45(1): 5-32.
    [17] 邓雪,李家铭,曾浩健,等. 层次分析法权重计算方法分析及其应用研究[J]. 数学的实践与认识, 2012, 42(7): 93-100.DENG Xue, LI Jiaming, ZENG Haojian, et al. Analytic hierarchy process weight calculation method analysis and its application research[J]. Mathematics in Practice and Understanding, 2012, 42(7): 93-100.
    [18] 席禹,于力,蒋文辉,等. 基于修正层次分析法的多阶段PMU最优配置[J]. 广东电力, 2022, 35(9): 87-93.XI Yu, YU Li, JIANG Wenhui, et al. Multi-stage PMU optimal configuration based on modified analytic hierarchy process[J]. Guangdong Electric Power, 2022, 35(9): 87-93.
    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

杨帆,王红斌,方健,何嘉兴,黄柏,王莉.基于K-means聚类和随机森林的电缆风险评估及修复决策[J].南京航空航天大学学报,2024,56(5):892-899

复制
分享
文章指标
  • 点击次数:244
  • 下载次数: 223
  • HTML阅读次数: 158
  • 引用次数: 0
历史
  • 收稿日期:2023-04-27
  • 最后修改日期:2024-01-08
  • 在线发布日期: 2024-11-08
文章二维码
您是第6577294位访问者
网站版权 © 南京航空航天大学学报
技术支持:北京勤云科技发展有限公司
请使用 Firefox、Chrome、IE10、IE11、360极速模式、搜狗极速模式、QQ极速模式等浏览器,其他浏览器不建议使用!