Please wait a minute...
电网技术
 
      设为首页      加入收藏
 
 首页 | 电网技术 | 期刊浏览 | 投稿指南 | 期刊订阅 | 广告服务 | 联系我们 | Email Alert |RSS |留 言 板
电网技术  2018, Vol. 42 Issue (8): 2408-2415    DOI: 10.13335/j.1000-3673.pst.2017.0663
  国家重点研发计划 本期目录 | 过刊浏览 | 高级检索 |
基于生长-修剪优化RBF神经网络的电能质量扰动分类
王慧慧1, 2, 王萍1, 刘涛3, 张博文1
1.天津大学 电气自动化与信息工程学院,天津市 南开区 300072;
2.天津城建大学 控制与机械工程学院,天津市 西青区 300384;
3.天津工业大学 电气工程与自动化学院,天津市 西青区 300387
Power Quality Disturbance Classification Based on Growing and Pruning Optimal RBF Neural Network
WANG Huihui1, 2, WANG Ping1, LIU Tao3, ZHANG Bowen1
1. School of Electrical and Information Engineering, Tianjin University, Nankai District, Tianjin 300072, China;
2. School of Control and Mechanical Engineering, Tianjin Chengjian University, Xiqing District, Tianjin 300384, China;
3. School of Electrical Engineering and Automatic, Tianjin Polytechnic University, Xiqing District, Tianjin 300387, China
下载:  PDF(1333KB) 
输出:  BibTeX | EndNote (RIS)      
摘要 针对电能质量扰动分类算法中径向基函数(radial basis function,RBF)神经网络隐层神经元的中心点数量、中心点位置、宽度、输出权值的设置问题,提出一种基于网络生长-修剪算法(GAP)的RBF神经网络电能质量扰动分类算法。首先,建立电能质量扰动模型,采用GAP算法实现对RBF神经网络的结构参数优化,设计相应的电能质量扰动分类算法流程图;其次,利用广义S变换、特征值提取、GAP-RBF神经网络对8种电能质量扰动进行处理。通过仿真分析,验证GAP-RBF神经网络对隐层神经元的参数优化能力,并给出优化算法的参数设定范围;仿真和实验结果表明,与同类算法相比,所提算法在保证分类准确度的前提下减少了隐层神经元的数量,且实现了RBF神经网络的参数自优化和继承式学习。
服务
加入引用管理器
E-mail Alert
RSS
作者相关文章
王慧慧
王萍
刘涛
张博文
关键词:  S变换  GAP-RBF神经网络  特征值提取  电能质量  扰动分类    
Abstract: To set the centers, widths and output weights of neurons in hidden layer of radial basis function (RBF) neural network, a new algorithm for power quality disturbance classification using growing and pruning (GAP) RBF neural network is proposed. Firstly, the paper establishes a mathematical model of power quality disturbances, adopting GAP algorithm to optimize the parameters of RBF neural network and design flow chart of power quality disturbances classification algorithm. Secondly, generalized S-transform, feature extraction and GAP-RBF neural network are used to process eight types of power quality disturbances. With help of simulation analysis, ability of GAP-RBF neural network to optimize the hidden layer of neuron is verified, and the range of parameters for optimal algorithm are provided. Simulation and experiment results show that, compared with other similar algorithms, this algorithm can reduce the number of hidden neurons while ensuring accuracy of disturbance classification, and realize self-optimization of parameters and inherited learning of RBF neural network.
Key words:  S-transform    GAP-RBF neural network    feature extraction    power quality    disturbance classification
收稿日期:  2017-04-05                     发布日期:  2018-08-08      期的出版日期:  2018-08-05
ZTFLH:  TM711  
基金资助: 国家重点研发计划项目(2016YFB0900204); 天津市高等学校基本科研业务费资助项目(2016CJ14)
作者简介:  王慧慧(1986),女,讲师,博士研究生,通信作者,研究方向为电能质量,E-mail:huihuiwang@tju.edu.cn;王萍(1959),女,教授,博士生导师,研究方向为功率电子变换技术、电力控制技术、智能检测算法等,E-mail:pingw@tju.edu.cn;刘涛(1984),男,讲师,研究方向为新能源发电,电力电子与电机控制,E-mail:taoliu@tju.edu.cn;张博文(1992),男,硕士研究生,研究方向为电子与电力传动,E-mail:bwzhang@tju.edu.cn。
引用本文:    
王慧慧, 王萍, 刘涛, 张博文. 基于生长-修剪优化RBF神经网络的电能质量扰动分类[J]. 电网技术, 2018, 42(8): 2408-2415.
WANG Huihui, WANG Ping, LIU Tao, ZHANG Bowen. Power Quality Disturbance Classification Based on Growing and Pruning Optimal RBF Neural Network. POWER SYSTEM TECHNOLOGY, 2018, 42(8): 2408-2415.
链接本文:  
http://www.dwjs.com.cn/CN/10.13335/j.1000-3673.pst.2017.0663  或          http://www.dwjs.com.cn/CN/Y2018/V42/I8/2408
[1] 姚建刚,郭知非,陈锦攀.基于小波和BP神经网络的电能扰动分类新方法[J].电网技术,2012,36(5):139-144.
Yao Jiangang,Guo Zhifei,Chen Jinpan.A new approach to recognize power quality disturbances based on wavelet transform and BP neural network[J].Power System Technology,2012,36(5):139-144(in Chinese).
[2] 黄南天,徐殿国,刘晓胜.基于S变换与SVM的电能质量复合扰动识别[J].电工技术学报,2011,26(10):23-30.
Huang Nantian,Xu Dianguo,Liu Xiaosheng.Identification of power quality complex disturbances based on S-Transform and SVM[J].Transactions of China Electrotechnical Society,2011,26(10):23-30 (in Chinese).
[3] 张磊,黄纯,江亚群,等.应用HS改进原子分解的电能质量扰动辨识分析[J].电网技术,2015,39(1):194-201.
Zhang Lei,Huang Chun,Jiang Yaqun,et al.Identification analysis of power quality disturbances based on harmony search and atom decomposition[J].Power System Technology,2015,39(1):194-201(in Chinese).
[4] 黄南天,张卫辉,蔡国伟,等.采用改进多分辨率快速S变换的电能质量扰动识别[J].电网技术,2015,39(5):1412-1418.
Huang Nantian,Zhang Weihui,Cai Guowei,et al.Power quality disturbances classification with improved multiresolution fast s-transform[J].Power System Technology,2015,39(5):1412-1418(in Chinese).
[5] 刘志刚,张巧革,张杨.电能质量复合扰动分类的研究进展[J].电力系统保护与控制,2013,41(13):146-153.
Liu Zhigang,Zhang Qiaoge,Zhang Yang.Review of power quality mixed disturbances identification[J].Power System Protection and Control,2013,41(13):146-153(in Chinese).
[6] Valtierra-Rodriguez M,de Jesus Romero-Troncoso R,Osornio-Rios R A,et al.Detection and classification of single and combined power quality disturbances using neural networks[J].IEEE Transactions on Industrial Electronics,2014,61(5):2473-2482.
[7] 刘博. 基于模糊逻辑的电能质量暂态扰动分类研究[D].哈尔滨:哈尔滨工业大学,2016.
[8] Mohanty S R,Ray P K,Kishor N,etc.Classification of disturbances in hybrid DG system using modular PNN and SVM[J].International Journal of Electrical Power & Energy Systems,2013,44(1):764-777.
[9] 陈华丰,张葛祥.基于决策树和支持向量机的电能质量扰动识别[J].电网技术,2013,37(5):1272-1278.
Chen Huafeng,Zhang Gexiang.Power quality disturbance identification using decision tree and support vector machine[J].Power System Technology,2013,37(5):1272-1278(in Chinese).
[10] Kumar R,Singh B,Shahani D,et al.Recognition of power-quality disturbances using S-transform-based ANN classifier and rule-based decision tree[J].IEEE Transactions on Industry Applications,2015,51(2):1249-1258.
[11] 蔡昌春,程述成,邓志祥,等.基于模糊RBF神经网络的直流微电网并网等效建模[J].电网技术,2016,40(11):3446-3452.
Cai Changchun,Cheng Shucheng,Deng Zhixiang,et al.DC microgrid equivalent modeling based on fuzzy-RBF artificial neural network[J].Power System Technology,2016,40(11):3446-3452(in Chinese).
[12] Meng K,Dong Z Y,Wang D H,et al.A self-adaptive RBF neural network classifier for transformer fault analysis[J].IEEE Transactions on Power Systems,2010,25(3):1350-1360.
[13] Chiung-Chou Liao.Enhanced RBF network for recognizing noise- riding power quality events[J].IEEE Transactions on Instrumentation and Measurement,2010,59(6):1550-1561.
[14] Guang-Bin H,Saratchandran P,dararajan N.An efficient sequential learning algorithm for growing and pruning RBF(GAP-RBF) networks[J].IEEE Transactions on Systems Man and Cybernetics,Part B(Cybernetics),2004,34(6):2284-2292.
[15] Huihui Wang,Ping Wang,Tao Liu.Power quality disturbance classification using the S-transform and probabilistic neural network[J].Energies,2017,10(1):1-19.
[1] 杨晓梅, 罗月婉, 肖先勇, 郭朝云. 基于自适应阈值和奇异值分解的电能质量扰动检测新方法[J]. 电网技术, 2018, 42(7): 2286-2294.
[2] 肖斐, 艾芊. 考虑天气因素的区域配网扰动事件预估[J]. 电网技术, 2018, 42(4): 1132-1139.
[3] 林顺富, 汤继开, 汤波, 李东东, 符杨. 典型电能质量稳态指标预测模型研究[J]. 电网技术, 2018, 42(2): 614-620.
[4] 张怀天, 荆龙, 吴学智, 王小星, 王帅. 用于交直流配电网的模块化多电平换流器分序补偿控制策略[J]. 电网技术, 2018, 42(1): 254-261.
[5] 林顺富, 李扬, 汤波, 符杨, 李东东. 基于改进FastICA及偏最小二乘法的系统谐波阻抗估计[J]. 电网技术, 2018, 42(1): 308-314.
[6] 焦晋荣, 贾清泉, 王宁, 林飞飞, 郑旭然. 柔性直流配电网纹波形成机理与叠加特性[J]. 电网技术, 2017, 41(6): 1726-1733.
[7] 李小鹏, 滕予非, 刘耀, 汤涌, 甄威. 基于测量波阻抗的高压直流输电线路纵联保护[J]. 电网技术, 2017, 41(2): 617-623.
[8] 殷桂梁, 陈思佳, 吴杰, 张知微, 张雪. 含不平衡负荷的微电网中并网逆变器的滑模控制策略[J]. 电网技术, 2016, 40(9): 2698-2705.
[9] 赵晨雪, 陶顺, 肖湘宁. 基于电能质量检测系统电压暂降信息的故障定位估计方法[J]. 电网技术, 2016, 40(2): 642-648.
[10] 金森钧, 高雄, 陈俊鑫, 彭勇刚, 韦巍, 雷金勇, 田兵. 基于电能质量的分布式电源上网电价机制[J]. 电网技术, 2016, 40(12): 3790-3795.
[11] 苏剑, 马钊, 尚宇炜, 刘东. 2016中国国际供电会议圆桌论坛技术报道[J]. 电网技术, 2016, 40(11): 3368-3374.
[12] 黄建明, 瞿合祚, 李晓明. 基于短时傅里叶变换及其谱峭度的电能质量混合扰动分类[J]. 电网技术, 2016, 40(10): 3184-3191.
[13] 孙毅, 许鹏, 武昕, 陆俊. 面向用电侧电能质量监测的时空压缩感知方法[J]. 电网技术, 2015, 39(8): 2351-2357.
[14] 邹福筱,帅智康,涂春鸣,沈征,姜飞. 故障限流与电能质量复合控制系统及其运行机理[J]. 电网技术, 2015, 39(5): 1351-1357.
[15] 段耀强,荆平,陈国富,安宁钰. 统一电能质量调节器串联侧滤波器设计与有源阻尼控制策略[J]. 电网技术, 2015, 39(5): 1405-1411.
[1] MENG Yangyang LU Jiping SUN Huali PAN Xue GAO Daochun LIAO Yong. Short-Term Wind Power Forecasting Based on Similar Days and Artificial Neural Network[J]. Power System Technology, 2010, 34(12): 163 -167 .
[2] . Wave Reflection Energized by Multi-Pulse Width Modulation Sources in Distributed Power System [J]. Power System Technology, 2006, 30(1): 19 -22 .
[3] ZHONG Wu-zhi SONG Xin-li TANG Yong BU Guang-quan WU Guo-yang LIU Tao. Small Signal Stability Analysis for UHV AC/DC Power Grids[J]. Power System Technology, 2010, 34(3): 1 -4 .
[4] ZHANG Jianhua SU Ling CHEN Yong SU Jing WNAG Li. Energy Management of Microgrid and Its Control Strategy[J]. Power System Technology, 2011, 35(7): 24 -28 .
[5] YAO Jun|LIAO Yong|QU Xing-hong|LIU Ren .

Optimal Wind-Energy Tracking Control of Direct-Driven Permanent Magnet
Synchronous Generators for Wind Turbines

[J]. Power System Technology, 2008, 32(10): 11 -15 .
[6] YANG Fei, LIU Shixin, WANG Haixia, FANG Yin, LI Weidong, ZHENG Wei. A Decomposition Method to Calculate Available Transfer Capability of Large Interconnected Power Grid YANG Fei1, LIU Shixin1, WANG Haixia1, FANG Yin2, LI Weidong1, ZHENG Wei3[J]. Power System Technology, 2014, 38(1): 138 -145 .
[7] ZHUANG Wei, MU Longhua. Fault Line Selection of Coalmine Distribution Network Considering Decaying DC Component of Zero-Sequence Current Under Single-Phase Earth Fault[J]. Power System Technology, 2014, 38(4): 1087 -1094 .
[8] WANG Lei, DU Xiaoqiang, SONG Yongduan. Neuron Adaptive PID Control Algorithm With Application to Flywheel Energy Storage System Unit[J]. Power System Technology, 2014, 38(1): 74 -79 .
[9] WEI Wei, WANG En, LIU Zhe. Real-Time Probabilistic Model Based Risk Assessment of Dispatching Operations Process[J]. Power System Technology, 2013, 37(12): 3509 -3514 .
[10] SUN Xiaofeng, YANG Yalin, ZHAO Wei, SHEN Hong, TAN Guangjun. An Adaptive Droop Control Method for Inverters in Microgrid[J]. Power System Technology, 2014, 38(9): 2386 -2391 .
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
京ICP备05032083号-3
版权所有:《电网技术》编辑部 电话:010-82812532
技术支持:北京玛格泰克科技发展有限公司