基于改进ED及CM-BPNN算法的保护测量回路误差状态评估方法

doi:10.11930/j.issn.1004-9649.202308052

中国电力 ›› 2023, Vol. 56 ›› Issue (11): 143-150.DOI: 10.11930/j.issn.1004-9649.202308052

基于改进ED及CM-BPNN算法的保护测量回路误差状态评估方法

易亚文¹^,²(), 赵静朴², 柳灿³, 蒋焮焮², 李方玖², 李振兴³

1. 武汉大学电气与自动化学院，湖北武汉　430072
2. 中国长江电力股份有限公司，湖北武汉　430010
3. 三峡大学电气与新能源学院，湖北宜昌　443002

收稿日期:2023-08-14 出版日期:2023-11-28 发布日期:2023-11-28
作者简介:易亚文（1979—），男，通信作者，高级工程师，从事水电站运行与维护研究，E-mail： 1729686912@qq.com
基金资助:
国家自然科学基金资助项目（大规模电力外送通道重合闸所致重大风险分析与规避控制策略研究，52077120）；长江电力股份有限公司科技项目（向家坝电站基于主动测评与多参信息差异的保护及测量装置状态评估与在线诊断，Z422202011）。

Error Status Evaluation Method for Protection Measurement Circuit Based on Improved ED and CM-BPNN Algorithms

Yawen YI¹^,²(), Jingpu ZHAO², Can LIU³, Xinxin JIANG², Fangjiu LI², Zhenxing LI³

1. School of Electrical Engineering and Automation, Wuhan University, Wuhan 430072, China
2. China Yangtze Power Co., Ltd., Wuhan 430010, China
3. College of Electrical Engineering and New Energy, China Three Gorges University, Yichang 443002, China

Received:2023-08-14 Online:2023-11-28 Published:2023-11-28
Supported by:
This work is supported by National Natural Science Foundation of China (Research on Major Risk Analysis and Control Strategy by Reclosing for Large-Scale Power Transmission Channel, No.52077120) and Science & Technology Project of China Yangtze Power Co., Ltd. (Xiangjiaba Power Station is Based on Active Evaluation and Multi-reference Information Difference Protection and Measurement Device Status Assessment and Online Diagnosis, No.Z422202011).

摘要/Abstract

摘要：

通过对保护测量回路误差状态进行准确评估，能掌握保护装置运行情况并及时发现保护装置存在的隐患。提出了一种基于改进欧氏距离（euclidean distance，ED）及云模型-BP神经网络（cloud model-back propagation neural metwork，CM-BPNN）算法的变电站保护测量回路误差状态评估方法。首先，对测量数据制定不同指标数据的归一化原则；其次，引入改进欧氏距离作为误差评估的启动判据，根据对保护动作性能的影响程度将误差状态进行等级划分并引入云模型计算二级指标的误差状态隶属度；最后，确定每一种误差状态对应的定位映射结果，完成BP神经网络模型的构建，再以此模型进行保护装置电流/电压未知误差状态的评估和定位。基于PSCAD软件搭建220 kV变电站模型，对所提方法的有效性进行验证。

关键词: 保护测量回路, 改进欧氏距离, 云模型, 神经网络

Abstract:

The accurate evaluation of the error status of the protection measurement circuit can help to understand the operation status of the protection devices, and to timely and effectively find the hidden dangers of the protection devices. This paper proposes an error status evaluation method for substation protection measurement circuit based on improved ED and CM-BPNN algorithms. Firstly, the normalization principle of different index data is formulated for the measurement data. Secondly, the improved Euclidean distance is introduced as the starting criterion for error evaluation. According to the degree of influence on the performance of the protection action, the error status is graded, and the cloud model is introduced to calculate the error status membership degree of the secondary index. Finally, the positioning mapping results corresponding to each error status are determined, and the BP neural network model is constructed, which is then used to evaluate and locate the unknown error status of the current/voltage of the protection devices. Based on PSCAD software, a 220kV substation model was constructed to verify the effectiveness of the proposed method.

Key words: protection measurement circuit, improved Euclidean distance, cloud model, neural network

易亚文, 赵静朴, 柳灿, 蒋焮焮, 李方玖, 李振兴. 基于改进ED及CM-BPNN算法的保护测量回路误差状态评估方法[J]. 中国电力, 2023, 56(11): 143-150.

Yawen YI, Jingpu ZHAO, Can LIU, Xinxin JIANG, Fangjiu LI, Zhenxing LI. Error Status Evaluation Method for Protection Measurement Circuit Based on Improved ED and CM-BPNN Algorithms[J]. Electric Power, 2023, 56(11): 143-150.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202308052

https://www.electricpower.com.cn/CN/Y2023/V56/I11/143

图/表 11

表 1 状态对应分值

Table 1 The scores corresponding to status

评估状态	误差值区间	归一化数值
正常（U₁）	[0, 5%]	[0.8, 1.0]
异常（U₂）	(5%, 15%]	[0.4, 0.8)
严重异常（U₃）	(15%, 25%]	[0.0, 0.4)

表 2 云模型特征值的确定

Table 2 Determination of the eigenvalues of the cloud model

状态等级区间	特征值
状态等级区间	$ E_{\rm{z}} $	$ E_{\rm{n}} $	$ H_{\rm{e}} $
U₁[0, 0.4]	c	$ \dfrac{{E_{\rm z2} - E_{\rm z1}}}{3} $	0.01
U₂(0.4, 0.8]	(a+b)/2	$ \dfrac{{E_{\rm z2} - E_{\rm z1}}}{3} $	0.01
U₃(0.8, 1.0]	a/2	$ \dfrac{{E_{\rm z3} - E_{\rm z2}}}{3} $	0.01

图 1 3种状态的云模型

Fig.1 Cloud models in three states

表 3 误差状态与定位数值关系

Table 3 The relationship between error status and positioning value

误差状态		定位数值Y_k
$ {l_{k3}} {\text{＞}} {l_{k2}} \; \&\; {l_{k3}} {\text{＞}} {l_{k1}} $		3
$ {l_{k2}} {\text{＞}} {l_{k3}} \; \&\; {l_{k2}} {\text{＞}} {l_{k1}} $		2
$ {l_{k1}} {\text{＞}} {l_{k3}} \; \& \; {l_{k1}} {\text{＞}} {l_{k2}} $		1

图 2 保护测量回路误差状态评估流程

Fig.2 Error status assessment process of protection measurement circuit

图 3 二级指标数据三相电压幅值波形

Fig.3 Three-phase voltage amplitude waveform of secondary index data

图 4 电压正序分量权重值比对结果

Fig.4 Comparison results of voltage positive sequence component weight values

图 5 序分量改进欧氏距离启动判据

Fig.5 Sequence component improved Euclidean distance initiation criterion

图 6 BP神经网络模型的每轮均方误差

Fig.6 Mean squared error for each round of the BP neural network model

图 7 BP神经网络模型的回归系数

Fig.7 The regression coefficients for BP neural network models

图 8 30组A相电压数据的实际状态与模型评估状态结果比对

Fig.8 Comparison of the actual status of 30 sets of A-phase voltage data and the model evaluation status results

参考文献 25

1	章剑光, 陈晓宇, 朱松涛, 等. 基于GIM模型的智能变电站二次回路三维可视化系统设计[J]. 电力系统保护与控制, 2022, 50 (19): 179- 186.
	ZHANG Jianguang, CHEN Xiaoyu, ZHU Songtao, et al. Design of a three-dimensional visualization system for the secondary circuit of an intelligent substation based on a GIM model[J]. Power System Protection and Control, 2022, 50 (19): 179- 186.
2	张宸滔, 郑永康, 卢继平, 等. 基于图神经网络的智能变电站二次回路故障定位研究[J]. 电力系统保护与控制, 2022, 50 (11): 81- 90.
	ZHANG Chentao, ZHENG Yongkang, LU Jiping, et al. Fault location of secondary circuits in a smart substation based on a graph neural network[J]. Power System Protection and Control, 2022, 50 (11): 81- 90.
3	吕航, 龚啸, 丁杰, 等. 基于二次回路建模的保护运维技术[J]. 电气技术, 2023, 24 (6): 64- 68.
	LÜ Hang, GONG Xiao, DING Jie, et al. Operation and maintenance technology of protection equipment based on modeling of secondary circuit[J]. Electrical Engineering, 2023, 24 (6): 64- 68.
4	李黄河, 苏晓, 柳明, 等. 继电保护的二次回路在线监测与故障分析[J]. 电子技术(上海), 2023, 52 (3): 390- 391.
	LI Huanghe, SU Xiao, LIU Ming, et al. Analysis of online monitoring and fault for secondary circuit in relay protection[J]. Electronic Technology, 2023, 52 (3): 390- 391.
5	王鸣誉, 李铁成, 任江波, 等. 利用Apriori算法实现变电站二次系统故障诊断[J]. 电力系统及其自动化学报, 2021, 33 (11): 145- 150.
	WANG Mingyu, LI Tiecheng, REN Jiangbo, et al. Realization of fault diagnosis of substation secondary system using apriori algorithm[J]. Proceedings of the CSU-EPSA, 2021, 33 (11): 145- 150.
6	南雷, 许航源, 李刚, 等. 电厂升压站继电保护二次回路智能检修维护方法研究[J]. 自动化技术与应用, 2021, 40 (4): 103- 105, 147. DOI
	NAN Lei, XU Hangyuan, LI Gang, et al. Research on intelligent maintenance method of relay protection secondary circuit in power plant booster station[J]. Techniques of Automation and Applications, 2021, 40 (4): 103- 105, 147. DOI
7	李玉峰, 吴晓宾, 孔海波, 等. 基于多参信息量的智能变电站继电保护二次回路故障在线诊断[J]. 自动化技术与应用, 2021, 40 (3): 172- 175.
	LI Yufeng, WU Xiaobin, KONG Haibo, et al. Online diagnosis of relay protection secondary circuit fault in intelligent substation based on multi-parameter information[J]. Techniques of Automation and Applications, 2021, 40 (3): 172- 175.
8	程瑛颖. 电能计量装置状态检验策略实践基础及其方法检验[C]//2013年中国电机工程学会年会论文集. 成都: 中国电机工程学会, 2013: 1354–1360.
9	黄俐萍, 王卉, 杜卫华. 电能计量装置运行评价方法研究[J]. 华东电力, 2014, 42 (11): 2322- 2326.
	HUANG Liping, WANG Hui, DU Weihua. Operation evaluation methods for energy metering devices[J]. East China Electric Power, 2014, 42 (11): 2322- 2326.
10	卢健豪. 电能计量装置状态监测技术的研究[D]. 广州: 广东工业大学, 2017.
	LU Jianhao. Research on condition monitoring technology of electric energy metering device[D]. Guangzhou: Guangdong University of Technology, 2017.
11	郭景涛. 面向智能电网AMI的网络计量关键技术与用户用电数据挖掘研究[D]. 天津: 天津大学, 2011.
	GUO Jingtao. Research on key technologies of network metering and data mining of user electricity consumption for smart grid AMI[D]. Tianjin: Tianjin University, 2011.
12	杨楠, 李宏圣, 袁景颜, 等. 计及灰色关联度分析的中长期负荷灰色预测方法[J]. 电力系统及其自动化学报, 2018, 30 (6): 108- 114. DOI
	YANG Nan, LI Hongsheng, YUAN Jingyan, et al. Medium-and long-term load forecasting method considering grey correlation degree analysis[J]. Proceedings of the CSU-EPSA, 2018, 30 (6): 108- 114. DOI
13	杨晓峰, 方逸航, 赵鹏臻, 等. 基于K-means和BPNN的风机状态识别[J]. 中国电力, 2023, 56 (6): 158- 166, 175.
	YANG Xiaofeng, FANG Yihang, ZHAO Pengzhen, et al. State recognition of wind turbines based on K-means and BPNN[J]. Electric Power, 2023, 56 (6): 158- 166, 175.
14	程瑛颖, 杜杰, 周全, 等. 基于随机矩阵理论和聚类算法的电能表运行状态评估方法[J]. 中国电力, 2020, 53 (11): 116- 125.
	CHENG Yingying, DU Jie, ZHOU Quan, et al. Evaluation method for running state of electricity meters based on random matrix theory and clustering algorithm[J]. Electric Power, 2020, 53 (11): 116- 125.
15	王毓琦, 李红斌, 向鑫, 等. 电力互感器检定与评估方法综述[J]. 高压电器, 2020, 56 (4): 95- 101, 107.
	WANG Yuqi, LI Hongbin, XIANG Xin, et al. Summary of verification and evaluation methods of power transformer[J]. High Voltage Apparatus, 2020, 56 (4): 95- 101, 107.
16	于海波, 王春雨, 袁晓蕾, 等. 基于PCA-SVR的电能计量装置误差评估算法[J]. 电测与仪表, 2020, 57 (19): 140- 145.
	YU Haibo, WANG Chunyu, YUAN Xiaolei, et al. Error assessment algorithms for electric energy metering devices based on PCA-SVR[J]. Electrical Measurement & Instrumentation, 2020, 57 (19): 140- 145.
17	刘炜, 王朝亮, 肖涛, 等. AMI数据驱动的电动汽车充电设施计量运行误差状态评估方法[J]. 电力自动化设备, 2022, 42 (10): 70- 76.
	LIU Wei, WANG Chaoliang, XIAO Tao, et al. AMI data-driven state evaluation method for measurement operation error of electric vehicle charging facilities[J]. Electric Power Automation Equipment, 2022, 42 (10): 70- 76.
18	姚致清, 王朋飞, 陈光华, 等. 电力系统合并单元测试仪测量误差检测校准装置研制及性能分析[J]. 电力系统保护与控制, 2022, 50 (2): 119- 126.
	YAO Zhiqing, WANG Pengfei, CHEN Guanghua, et al. Development and performance analysis of a measurement error test and calibration device for a merging unit tester in a power system[J]. Power System Protection and Control, 2022, 50 (2): 119- 126.
19	高书垚, 安泰, 宋剑. 基于熵权-正态云模型的智能电能表状态评估研究[J]. 电测与仪表, 2022, 59 (1): 190- 194.
	GAO Shuyao, AN Tai, SONG Jian. Status evaluation of smart meter based on entropy weight-normal cloud model[J]. Electrical Measurement & Instrumentation, 2022, 59 (1): 190- 194.
20	南东亮, 王维庆, 张陵, 等. 基于关联规则挖掘与组合赋权-云模型的电网二次设备运行状态风险评估[J]. 电力系统保护与控制, 2021, 49 (10): 67- 76.
	NAN Dongliang, WANG Weiqing, ZHANG Ling, et al. Risk assessment of the operation state of power grid secondary equipment based on association rule mining and combination weighting-cloud model[J]. Power System Protection and Control, 2021, 49 (10): 67- 76.
21	顾佳浩, 淡淑恒. 考虑HI理论和在线监测误差的配电网可靠性评估[J]. 电力系统及其自动化学报, 2021, 33 (4): 127- 134. DOI
	GU Jiahao, DAN Shuheng. Reliability evaluation on distribution network considering HI theory and online monitoring error[J]. Proceedings of the CSU-EPSA, 2021, 33 (4): 127- 134. DOI
22	陈海涛, 杨军, 施迎春, 等. 基于云模型与马尔科夫链的继电保护装置寿命预测方法[J]. 电力系统保护与控制, 2019, 47 (16): 94- 100. DOI
	CHEN Haitao, YANG Jun, SHI Yingchun, et al. Life prediction method of relay protection device based on could model and Markov Chain[J]. Power System Protection and Control, 2019, 47 (16): 94- 100. DOI
23	刘文宇, 刘璐, 刘馨然, 等. 基于改进BP神经网络的低压配电台区智能电能表误差状态评估模型[J]. 电测与仪表, 2022, 59 (11): 176- 181.
	LIU Wenyu, LIU Lu, LIU Xinran, et al. An error estimation method of smart electricity meter in low voltage distribution area based on improved BP neural network[J]. Electrical Measurement & Instrumentation, 2022, 59 (11): 176- 181.
24	杨志淳, 靖晓平, 乐健, 等. 基于MI-PSO-BP算法的配电设备状态实时评估方法[J]. 电力自动化设备, 2019, 39 (12): 108- 113. DOI
	YANG Zhichun, JING Xiaoping, LE Jian, et al. Real-time condition assessment method based on MI-PSO-BP algorithm for distribution equipment[J]. Electric Power Automation Equipment, 2019, 39 (12): 108- 113. DOI
25	陈敬德, 高兆丽, 罗林根, 等. 基于BP神经网络的特高频局部放电定位误差校正[J]. 高电压技术, 2018, 44 (6): 2040- 2047.
	CHEN Jingde, GAO Zhaoli, LUO Lingen, et al. Positioning error correction of UHF partial discharge based on BP neural network[J]. High Voltage Engineering, 2018, 44 (6): 2040- 2047.

[1]	吴小忠, 肖立华, 童超, 夏向阳, 袁翎, 甘星, 江志文, 黄湘源. 基于传递熵与JS-BP神经网络的锂离子电池容量预测模型[J]. 中国电力, 2025, 58(2): 186-192, 215.
[2]	黄宁泊, 高建伟, 许传博, 徐选华, 赵舒通, 缑迅杰, 姜晓静. 基于经验挖掘与混合语言的海上风电制氢加氢港口选址研究[J]. 中国电力, 2024, 57(9): 113-123.
[3]	王宇飞, 杜桐, 边伟国, 张钊, 刘慧婷, 杨丽君. 基于DTW K-medoids与VMD-多分支神经网络的多用户短期负荷预测[J]. 中国电力, 2024, 57(6): 121-130.
[4]	吴军英, 路欣, 刘宏, 张彬, 柴守亮, 刘蕴春, 王佳楠. 基于Spearman-GCN-GRU模型的超短期多区域电力负荷预测[J]. 中国电力, 2024, 57(6): 131-140.
[5]	邵必林, 纪丹阳. 基于VMD-SE的电力负荷分量的多特征短期预测[J]. 中国电力, 2024, 57(4): 162-170.
[6]	陈巳阳, 韩利, 方济中, 丁五行, 成诚, 李文, 张源, 钱勇. 基于不确定参数的变电站碳储量预估方法[J]. 中国电力, 2024, 57(4): 200-210.
[7]	娄奇鹤, 李荣盛, 谭捷, 袁铁江. 基于卷积神经网络的暂稳极限功率计算[J]. 中国电力, 2024, 57(4): 211-219.
[8]	马汝括, 董杰, 王雅湉, 伊国鑫, 丁祥浩, 马乐. 基于神经网络的高寒地区CF₄和SF₆/CF₄检测[J]. 中国电力, 2024, 57(3): 103-112.
[9]	阎洁, 杨佳琳, 王航宇, 卢姣阳, 刘永前, 张磊. 基于风况预测误差自适应的海上风电场尾流偏转控制方法[J]. 中国电力, 2024, 57(3): 190-196.
[10]	李卓, 王胤喆, 叶林, 罗雅迪, 宋旭日, 张振宇. 从感知-预测-优化综述图神经网络在电力系统中的应用[J]. 中国电力, 2024, 57(12): 2-16.
[11]	陈庆斌, 杨耿煌, 耿丽清, 苏娟, 孙京生. 基于相似日选取和数据重构的短期光伏功率组合预测方法[J]. 中国电力, 2024, 57(12): 71-81.
[12]	张金良, 胡泽萍. 计及多重不确定性的生物质电厂库存优化模型[J]. 中国电力, 2024, 57(12): 157-168.
[13]	陈来恩, 曾小勇, 曾子豪, 成采辰, 孙耀科. 基于物理信息与深度神经网络的锂离子电池温度预测[J]. 中国电力, 2024, 57(11): 18-25.
[14]	薛松萍, 高德荃, 赵子岩, 林彧茜, 广泽晶, 张大卫. 基于业务差异化传输需求下的电力通信网路由算法[J]. 中国电力, 2024, 57(11): 183-190.
[15]	周颖, 白雪峰, 王阳, 邱敏, 孙冲, 武亚杰, 李彬. 面向虚拟电厂运营的温度敏感负荷分析与演变趋势研判[J]. 中国电力, 2024, 57(1): 9-17.

基于改进ED及CM-BPNN算法的保护测量回路误差状态评估方法

Error Status Evaluation Method for Protection Measurement Circuit Based on Improved ED and CM-BPNN Algorithms

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 25

相关文章 15

编辑推荐

Metrics

模态框（Modal）标题

基于改进ED及CM-BPNN算法的保护测量回路误差状态评估方法

Error Status Evaluation Method for Protection Measurement Circuit Based on Improved ED and CM-BPNN Algorithms

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 25

相关文章 15

编辑推荐

Metrics