基于自适应DBSCAN算法的开关柜绝缘状态评价方法

doi:10.19595/j.cnki.1000-6753.tces.L90024

摘要
图/表
参考文献
相关文章 (6)

全文: PDF (1112 KB) HTML
输出: BibTeX | EndNote (RIS)

摘要

为了更合理地评价开关柜绝缘状态,挖掘开关柜异常数据蕴含的价值,提出一种基于自适应DBSCAN的开关柜绝缘状态评价方法。首先计算绝缘状态检测数据暂态对地电压和超声波的偏差量,消除背景噪声;将绝缘状态偏差量与开关柜环境温度、环境湿度和运行年限构成开关柜绝缘状态的特征量,并建立开关柜的多维特征数据集。然后采用K平均最近邻法和数学期望法生成DBSCAN算法的扫描半径r和最少数目MinPts的候选参数,引入密度阈值自动寻找聚类簇数变化稳定的区间;利用开关柜检测数据集自身分布特性对DBSCAN算法中参数进行自适应最优选择,避免了人为主观设定导致的误差。最后构建基于加权集成的聚类有效性指标来判断聚类结果的有效性,以某开关柜现场检测数据为例,通过比较K-means和DBSCAN两种算法的结果,验证了该评价方法的优越性,为开关柜运行状态的评价提供一定的理论依据。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	胡金磊
	赖俊驹
	黎阳羊
	杨帆
	黄河

关键词 ：开关柜, 状态评价, 自适应寻优, DBSCAN聚类算法, 离群点, 有效性指标

Abstract：

In order to evaluate the insulation state of switchgear more reasonably and explore the value of abnormal data, an evaluation method based on adaptive DBSCAN (density based spatial clustering of applications with noise) is proposed. Firstly, the deviation of insulation state detection data transient to ground voltage and ultrasonic wave is calculated to eliminate the background noise; the deviation of insulation state, the ambient temperature, humidity and operation life of the switchgear constitute the characteristic quantity of insulation state of switchgear, and the multi-dimensional characteristic dataset of switchgear is established. Then, K-means nearest neighbor method and mathematical expectation method are used to generate scanning radius and minimum number candidate parameters of DBSCAN algorithm, and density threshold is introduced to automatically find the sTab.range of cluster number; parameters in DBSCAN algorithm are selected adaptively by using distribution characteristics of dataset to avoid the error caused by subjective setting. Finally, the cluster validity index based on weighted ensemble is constructed to judge the validity of clustering results. The field test data is used as an example by comparing the results of K-means and DBSCAN to verify the feasibility, which provides a theory for the evaluation of the operation state of the switchgear basis.

Key words： Switchgear state evaluation adaptive optimization DBSCAN algorithm outlier effectiveness index

收稿日期: 2020-05-11

PACS:

TM591

基金资助:

广东电网有限责任公司科技资助项目（031800KK52170056）

通讯作者: 杨帆女,1981年生,博士,副教授,研究方向为人工智能驱动的能源系统运行调度与电力设备状态评估等。E-mail: yangfan@shiep.edu.cn

作者简介: 胡金磊男,1981年生,博士,高级工程师,研究方向为电力系统状态监测、运行与维护工作等。E-mail: 165330119@qq.com

引用本文:

胡金磊, 赖俊驹, 黎阳羊, 杨帆, 黄河. 基于自适应DBSCAN算法的开关柜绝缘状态评价方法[J]. 电工技术学报, 2021, 36(zk1): 344-352. Hu Jinlei, Lai Junju, Li Yangyang, Yang Fan, Huang He. Evaluation Method of Switchgear Insulation State Based on Adaptive Density Based Spatial Clustering of Applications with Noise Algorithm. Transactions of China Electrotechnical Society, 2021, 36(zk1): 344-352.

链接本文:

https://dgjsxb.ces-transaction.com/CN/10.19595/j.cnki.1000-6753.tces.L90024 https://dgjsxb.ces-transaction.com/CN/Y2021/V36/Izk1/344

[1] 蒲天骄, 乔骥, 韩笑, 等. 人工智能技术在电力设备运维检修中的研究及应用[J]. 高电压技术, 2020, 46(2): 369-383.
Pu Tianjiao, Qiao Ji, Han Xiao, et al.Research and application of artificial intelligence in operation and maintenance for power equipment[J]. High Voltage Engineering, 2020, 46(2): 369-383.
[2] 张燕, 方瑞明. 基于油中溶解气体动态网络标志物模型的变压器缺陷预警与辨识[J]. 电工技术学报, 2020, 35(9): 2032-2041.
Zhang Yan, Fang Ruiming.Fault detection and identi-fication of transformer based on dynamical network marker model of dissolved gas in oil[J]. Transactions of China Electrotechnical Society, 2020, 35(9): 2032-2041.
[3] 谢静, 束洪春, 王科. 基于模糊分层理论的高压开关柜状态评价算法[J]. 高电压技术, 2014, 40(10): 3192-3196.
Xie Jing, Shu Hongchun, Wang Ke.State evaluation based on AHP fuzzy theory of high voltage switch- gears[J]. High Voltage Engineering, 2014, 40(10): 3192-3196.
[4] 贾亚楠, 刘东明, 随慧斌. 基于正态云模型和D-S证据理论的开关柜运行状态综合评估[J]. 高压电器, 2017, 53(9): 247-252.
Jia Yanan, Liu Dongming, Sui Huibin.Comprehen- sive evaluation for switchgear based on the normal cloud model and D-S evidence theory[J]. High Voltage Apparatus, 2017, 53(9): 247-252.
[5] 陈曦, 唐斌, 余飞. 基于变权重理论和融合实时信息配电开关柜的状态评价[J]. 电子测量与仪器学报, 2018, 32(8): 193-200.
Chen Xi, Tang Bin, Yu Fei.State evaluation of distribution switchboard based on variable weight theory and fusion of real time information[J]. Journal of Electronic Measurement and Instrumentation, 2018, 32(8): 193-200.
[6] 谢静, 束洪春, 王科, 等. 基于FCM算法的高压开关柜局部放电状态评价方法研究[J]. 高压电器, 2015, 51(10): 82-90, 96.
Xie Jing, Shu Hongchun, Wang Ke, et al.Study on state evaluation of partial discharge in high voltage switchgear based on fuzzy clustering algorithm[J]. High Voltage Apparatus, 2015, 51(10): 82-90, 96.
[7] 滕予非, 吴杰, 张真源, 等. 基于离群点检测的高压并联电抗器本体电流互感器测量异常故障在线诊断[J]. 电工技术学报, 2019, 34(11): 2405-2414.
Teng Yufei, Wu Jie, Zhang Zhenyuan, et al.Online identification of measurement abnormality fault based on outlier detection for current transformer in high voltage shunt reactor[J]. Transactions of China Electrotechnical Society, 2019, 34(11): 2405-2414.
[8] 亢超群. 基于多源信息融合的配电开关柜状态评价方法研究[D]. 北京: 华北电力大学, 2016.
[9] 赵仕策, 赵洪山, 寿佩瑶. 智能电力设备关键技术及运维探讨[J]. 电力系统自动化, 2020, 44(20): 1-11.
Zhao Shice, Zhao Hongshan, Shou Peiyao.Dis- cussion on key technology and operation & maintenance of intelligent power equipment[J]. Auto- mation of Electric Power Systems, 2020, 44(20): 1-11.
[10] 邹阳, 何倩玲, 蔡金锭. 基于组合赋权-双基点法的变压器油纸绝缘状态综合评估[J]. 电工技术学报, 2019, 34(20): 4400-4408.
Zou Yang, He Qianling, Cai Jinding.Comprehensive evaluation of transformer oil-paper state based on combined weight-double base point method[J]. Transactions of China Electrotechnical Society, 2019, 34(20): 4400-4408.
[11] 罗伟明, 吴帆, 黄业广, 等. 基于局部密度聚类算法的变压器故障状态评估[J]. 广东电力, 2018, 31(8): 81-90.
Luo Weiming, Wu Fan, Huang Yeguang, et al.Transformer fault state evaluation method based on multilocal density clustering algorithm[J]. Guangdong Electric Power, 2018, 31(8): 81-90.
[12] 张为金. 基于机器学习的电力异常数据检测[D]. 成都: 电子科技大学, 2018.
[13] 李春燕, 蔡文悦, 赵溶生, 等. 基于优化SAX和带权负荷特性指标的AP聚类用户用电行为分析[J]. 电工技术学报, 2019, 34(增刊1): 368-377.
Li Chunyan, Cai Wenyue, Zhao Rongsheng, et al.Customer behavior analysis based on affinity propagation algorithm with optimized SAX and weighted load characteristic indices[J]. Transactions of China Electrotechnical Society, 2019, 34(S1): 368-377.
[14] 徐搏超. 基于参数关联性的电站参数异常点清洗方法[J]. 电力系统自动化, 2020, 44(20): 142-149.
Xu Bochao.Parameter correlation based parameter abnormal point cleaning method for power station[J]. Automation of Electric Power systems, 2020, 44(20): 142-149.
[15] 毋雪雁, 王水花, 张煜东. K最近邻算法理论与应用综述[J]. 计算机工程与应用, 2017, 53(21): 1-7.
Wu Xueyan, Wang Shuihua, Zhang Yudong.Survey on theory and application of K-nearest-neighbors algorithm[J]. Computer Engineering and Applications, 2017, 53(21): 1-7.
[16] 周国亮, 宋亚奇, 王桂兰, 等. 状态监测大数据存储及聚类划分研究[J]. 电工技术学报, 2013, 28(增刊2): 337-344.
Zhou Guoliang, Song Yaqi, Wang Guilan, et al.Research of condition monitoring big data storage and clustering[J]. Transactions of China Electro- technical Society, 2013, 28(S2): 337-344.
[17] 董骁翀, 孙英云, 蒲天骄, 等. 一种基于Wasserstein距离及有效性指标的最优场景约简方法[J]. 中国电机工程学报, 2019, 39(16): 4650-4658, 4968.
Dong Xiaochong, Sun Yingyun, Pu Tianjiao, et al.An optimal scenario reduction method based on Wasserstein distance and validity index[J]. Pro- ceedings of the CSEE, 2019, 39(16): 4650-4658, 4968.
[18] Liang Shaoyi, Han Deqiang, Yang Yi.Cluster validity index for irregular clustering results[J]. Applied Soft Computing, 2020, 95: 106583.
[19] 马克勤, 杨延娇, 秦红武, 等. 结合最大最小距离和加权密度的K-means聚类算法[J]. 计算机工程与应用, 2020, 56(16): 50-54.
Ma Keqin, Yang Yanjiao, Qin Hongwu, et al.K-means clustering algorithm combining max-min distance and weighted density[J]. Computer Engin- eering and Applications, 2020, 56(16): 50-54.
[20] 田力, 向敏. 基于密度聚类技术的电力系统用电量异常分析算法[J]. 电力系统自动化, 2017, 41(5): 64-70.
Tian Li, Xiang Min.Abnormal power consumption analysis based on density-based spatial clustering of applications with noise in power systems[J]. Auto- mation of Electric Power Systems, 2017, 41(5): 64-70.