[1]王 伟,虢 韬,杨 恒.基于主成分分析和反向传播神经网络相结合的金属氧化物压敏电阻故障诊断分析[J].电瓷避雷器,2019,(06):20-25.[doi:10.16188/j.isa.1003-8337.2019.06.004]
 WANG Wei,GUO Tao,YANG Heng.Study on Metal Oxide Varister Fault Diagnosis Based on Principal Component Analysis and BP Neural Network[J].,2019,(06):20-25.[doi:10.16188/j.isa.1003-8337.2019.06.004]
点击复制

基于主成分分析和反向传播神经网络相结合的金属氧化物压敏电阻故障诊断分析()
分享到:

《电瓷避雷器》[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2019年06期
页码:
20-25
栏目:
避雷器
出版日期:
2019-12-10

文章信息/Info

Title:
Study on Metal Oxide Varister Fault Diagnosis Based on Principal Component Analysis and BP Neural Network
作者:
王 伟1 虢 韬2 杨 恒2
(1.贵州电网有限责任公司电网规划研究中心,贵阳 550002; 2.贵州电网有限责任公司输电运行检修分公司,贵阳 550002)
Author(s):
WANG Wei1 GUO Tao2 YANG Heng2
(1.Power Grid Planning Research Center, Guizhou Power Grid Co., Ltd., Guiyang 550002, China; 2.TransmissionOperation and Maintenance Branch, Guizhou Power Grid Co., Ltd., Guiyang 550002, China)
关键词:
主成分分析 反向传播神经网络 金属氧化物压敏电阻 故障诊断
Keywords:
principal component analysis BP neural network metal oxide varister fault diagnosis
DOI:
10.16188/j.isa.1003-8337.2019.06.004
摘要:
准确诊断金属氧化物压敏电阻故障对电力系统安全运行十分重要。为有效提高故障诊断率,本文提出基于主成分分析与反向传播神经网络相结合的故障诊断算法。对于MOV故障数据指示指标,利用主成分分析进行降维,降低原始指标间相关性,最后利用反向传播神经网络对所选主成分进行诊断。试验结果表明:相对于反向传播模型,PCA-反向传播模型诊断误判率下降了3%,模型运行时间降低了267 s。有效降低MOV误判率,简化了反向传播网络结构,提高网络收敛性和稳定性。
Abstract:
Accurate fault diagnosis of the metal oxide varister is very important for the safe operation of power system. In order to improve the MOV fault diagnosis rate, the PCA-BP algorithm is proposed. The principal component analysis is used to reduce the dimension of MOV diagnosis indexes and the correlation between the original indexes. The new indexes are input to the BP neural network to train, so the MOV fault diagnosis can be achieved. The results show that, compared with BP model, the diagnosis error rate of PCA-BP model decreased by 3%, and the running time of this model decreased by 267 s. It effectively reduces the MOV misjudgment rate, simplifies the BP network structure, and improves the convergence and stability of the network.

参考文献/References:

[1] 董莉娜,胡可,王微波,等.小波消噪在10 kV金属氧化物避雷器在线检测中的应用[J].高电压技术,2014, 40(3):891-896. DONG Lina, HU Ke, WANG Weibo, et al. Application of wavelet de-noise in on-line detection of 10 kV metal oxide arresters[J]. High Voltage Engineering, 2014, 40(3): 891-896.
[2] 葛猛,韩学坤,陶安培.金属氧化物避雷器阀片老化缺陷的诊断及原因分析[J].高压电器,2009, 45(3):145-147. GE Meng, HAN Xuekun, TAO Anpei. Diagnosising and analysising the aged flaw of MOA valve piece[J]. High Voltage Apparatus, 2009, 45(3): 145-147.
[3] 丁国成,李伟,刘云鹏,等.外部环境因素对MOV在线监测影响的试验[J].高电压技术,2008, 34(6):1283-1287. DING Guocheng, LI Wei, LIU Yunpeng, et al. Experimental study of influence of environmental conditions on on-line monitoring data of metal oxide surge arrester[J]. High Voltage Engineering, 2008, 34(6): 1283-1287.
[4] GEORGE R L, EDSON G. Costa.MOSA monitoring technique based on analysis of total leakage current[J]. IEEE Transactions on Power Delivery, 2017, 28(2): 1057-1062.
[5] 曹洪亮,杨仲江,任婧,等.金属氧化物避雷器在线监测指标研究[J].中国电力,2015, 48(8):80-85. CAO Hongliang, YANG Zhongjiang, REN Jing, et al.Study on on-line monitoring index of MOA[J]. Electric Power, 2015, 48(8): 80-85.
[6] 张搏宇,李光范,陈立栋,等.避雷器及其比例单元的散热特性研究[J].电瓷避雷器,2010(4):46-50. ZHANG Boyu, LI Guangfan, CHEN Lidong, et al. Study on the thermal dispersion ability of MOA and MOA section[J]. Insulators and Surge Arresters, 2010(4): 46-50.
[7] 曹洪亮,谭涌波,李鹏飞,等.一种简便的阻性电流提取算法[J].电瓷避雷器,2015(5):115-118. CAO Hongliang, TAN Yongbo, LI Pengfei, et al. A simple algorithm to extract the resistive current[J]. Insulators and Surge Arresters, 2015(5): 115-118.
[8] 高峰,郭洁,徐欣,等.交流金属氧化物避雷器受潮与阻性电流的关系[J].高电压技术,2009, 35(11):2629-2633. GAO Feng, GUO Jie, XU Xin, et al. Relation between resistive current and MOA affected with damp[J]. High Voltage Engineering, 2009, 35(11): 2629-2633.
[9] 刘英华. 基于主成分分析与反向传播神经网络的网络流量预测[J]. 激光杂志, 2015, 36(6):151-153. LIU Yinghua. Network flow prediction based on principal component analysis and neural network[J]. Laser journal, 2015,36(6):151-153.
[10] 廖瑞金,杨丽君,孙才新,等.基于局部放电主成分因子向量的油纸绝缘老化状态统计分析[J].中国电机工程学报,2006, 26(14):114-119. LIAO Ruijin, YANG Lijun, SUN Caixin, et al. Aging condition assessment of oil-paper based on principal component and factor analysis of partial discharge[J]. Proceedings of the Chinese Society for Electrical Engineering, 2006, 26(14): 114-119.
[11] 许力,竺鹏东,顾宏杰,等.基于变尺度PCA的电力设备载流故障早期预警[J].电力自动化设备,2012, 32(5):147-151. XU Li, ZHU Pengdong, GU Hongjie, et al. Early warning of electric equipment current-carrying faults based on variable-scale principal component analysis[J]. Electric Power Automation Equipment, 2012, 32(5): 147-151.
[12] 姚仲敏, 潘飞, 沈玉会, 等. 基于GA-反向传播和POS-反向传播神经网络的光伏电站出力短期预测[J]. 电力系统保护与控制, 2015, 43(20): 83-89. YAO Zhongmin, PAN Fei, SHEN Yuhui, et al. Short-term prediction of photovoltaic power generation output based on GA and POSneural network[J]. Power System Protection and Control, 2015, 43(20): 83-89.
[13] 莫易敏, 姚亮, 王骏, 等. 基于主成分分析与反向传播神经网络的发动机故障诊断[J]. 武汉理工大学学报(交通科学与工程版), 2016, 40(1):85-88. MO Yimin, YAO Liang, WANG Jun, et al. Engine fault diagnosis based on principal component analysis and neural network[J]. Journal of Wuhan University of Technology(Transportation Science & Engineering), 2016, 40(1):85-88.
[14] 王峰,袁开明,舒乃秋.基于主成分和小波神经网络的绝缘子污秽放点发展阶段识别[J].绝缘材料,2015, 48(4):52-60. WANG Feng, YUAN Kaiming, SHU Naiqiu. Recognition of contamination discharge development stage of insulators based on principal component and wavelet neural network[J]. Insulation Material, 2015, 48(4): 52-60.
[15] 杨仲江,曹洪亮,李鹏飞,等.基于遗传算法的金属氧化物避雷器在线监测[J].高电压技术,2015, 41(9):3104-3109. YANG Zhongjiang, CAO Hongliang, LI Pengfei, et al. On-line monitoring of metal oxide arrester using genetic algorithm[J]. High Voltage Engineering, 2015, 41(9): 3104-3109.
[16] 孔繁钢,刘强,王冀星,等.基于改进BP神经网络算法的岸电电源智能输出控制的研究 [J]. 电网与清洁能源,2017,33(2):64-67. KONG Fangang, LIU Qiang, WANG Jixing, et al.Intelligent Output control of shore power supply based on improved bp neural network algorithm [J]. Power System and Clean Energy,2017,33(2):64-67.
[17] 徐志钮,赵丽娟,丁傲,等.一种新的SPD阻性电流提取算法[J].电力自动化设备,2010, 30(12):47-51. XU Zhiniu, ZHAO Lijuan, DING Ao, et al. Calculation of SPD resistive current[J]. Electric Power Automation Equipment, 2010, 30(12): 47-51.
[18] STOJANOVIC Z N, STOJKOVIC Z M. Evaluation of MOSA condition using leakage current method[J]. International Journal of Electrical Power & Energy Systems, 2013, 52: 87-95.

备注/Memo

备注/Memo:
收稿日期:2019-06-04 作者简介:王伟(1986—),男,本科,研究方向为输电线路设计、评审及运行维护。 基金项目:北斗卫星电力行业应用关键技术研究及数据应用产业化(编号:黔科合重大专项字【2018】3007)。
更新日期/Last Update: 2019-12-10