光伏阵列故障类型的改进型RBF神经网络识别算法
|
摘要
光伏阵列是光伏系统中非常重要的组成部分。传统的BP神经网络诊断算法有着精度低、收敛速度慢等缺点,为了精确地诊断出光伏阵列内部的故障位置及其类型,通过分析阵列开路、短路、老化、阴影和电池板裂片5种故障,提出了一种改进型RBF神经网络的故障诊断识别算法。首先,建立RBF神经网络的光伏阵列故障诊断模型,确定基于遗传算法的故障模型隐层中心的确定方法,然后针对基于粒子群优化算法的网络模型进行自适应权重寻优的仿真实验。最后,将优化的算法与传统RBF神经网络算法进行对比。结果表明:该优化算法不仅可以有效地诊断光伏阵列的故障类型,还可以提高故障诊断的准确率。
Photovoltaic(PV) array is an important part of the PV system. The traditional BP neural network diagnosis algorithm has some disadvantages, such as low accuracy and slow convergence speed. To diagnose the location and types of fault in the PV array accurately, a fault diagnosis and identification algorithm based on the improved RBF neural network is put forward through analyzing five types of fault, i.e., open circuit, short circuit, aging, shadow, and panel fragmentation. Firstly, a PV array fault diagnosis model based on radial basis function(RBF) neural network is established. The method of determining the center of hidden layer of the fault model is formulated based on genetic algorithm, and then simulation experiments are conducted using the adaptive network weight optimization method based on particle swarm optimization(PSO) algorithm. Finally, the optimized algorithm and the traditional RBF neural network algorithm are com-pared. Results show that the proposed algorithm can not only diagnose the fault types of PV array effectively, but also improve the accuracy of fault diagnosis.
Photovoltaic(PV) array is an important part of the PV system. The traditional BP neural network diagnosis algorithm has some disadvantages, such as low accuracy and slow convergence speed. To diagnose the location and types of fault in the PV array accurately, a fault diagnosis and identification algorithm based on the improved RBF neural network is put forward through analyzing five types of fault, i.e., open circuit, short circuit, aging, shadow, and panel fragmentation. Firstly, a PV array fault diagnosis model based on radial basis function(RBF) neural network is established. The method of determining the center of hidden layer of the fault model is formulated based on genetic algorithm, and then simulation experiments are conducted using the adaptive network weight optimization method based on particle swarm optimization(PSO) algorithm. Finally, the optimized algorithm and the traditional RBF neural network algorithm are com-pared. Results show that the proposed algorithm can not only diagnose the fault types of PV array effectively, but also improve the accuracy of fault diagnosis.
引文
[1]胡义华,邓焰,何湘宁.光伏阵列故障诊断方法综述[J].电力电子技术,2013,47(3):21-23.Hu Yihua,Deng Yan,He Xiangning.A summary on PVarray fault diagnosis method[J].Powe Electronics,2013,47(3):21-23(in Chinese).
[2]李兵峰.光伏阵列故障检测方法的研究[D].天津:天津大学,2010.Li Bingfeng.Research on fault detection method of PV array[D].Tianjin:Tianjin University,2010(in Chinese).
[3]温正.精通MATLAB智能算法[M].北京:清华大学出版社,2015.
[4]于群,曹娜.电力系统建模与仿真[M].北京:机械工业出版社,2011.
[5]谢柱.基于特性参数的太阳能电池和光伏阵列建模研究[J].华东电力,2010,38(4):581-584.Xie Zhu.Study on modeling of solar cells and photovoltaic arrays based on characteristic parameters[J].East China Electric Power,2010,38(4):581-584(in Chinese).
[6]杨店飞,郭宇杰,沈桂鹏.基于BP神经网络的光伏组件故障类型诊断[J].陕西电力,2016,44(2):15-21.Yang Dianfei,Guo Yujie,Shen Guipeng.Fault types diagnosis of PV module based on BP neural network[J].Shanxi Electric Power,2016,44(2):15-21(in Chinese).
[7]乐治后.基于RBF神经网络的光伏电池故障诊断[J].上海电气技术,2015,8(3):28-32.Le Zhihou.Fault diagnosis of photovoltaic battery based on RBF neural network[J].Shanghai Electronic Technology,2015,8(3):28-32(in Chinese).
[8]兰琴丽,章乐多.BP神经网络在光伏发电系统故障诊断中的应用[J].通信电源技术,2011,28(4):38-40.Lan Qinli,Zhang Leduo.Application of BP neural network in fault diagnosis of solar photovoltaic system[J].Telecom Power Technology,2011,28(4):38-40(in Chinese).
[9]张文瑾,葛强,黄澄扬,等.基于BP神经网络的光伏阵列智能故障诊断[J].扬州大学学报:自然科学版,2015,18(1):32-35.Zhang Wenjin,Ge Qiang,Huang Chengyang,et al.The photovolatic array intelligent fault diagnosis based on the BP neural network[J].Journal of Yangzhou University:Natural Science Edition,2015,18(1):32-35(in Chinese).
[10]王元章,吴春华,周笛青,等.基于BP神经网络的光伏阵列故障诊断研究[J].电力系统保护与控制,2013,41(16):110-114.Wang Yuanzhang,Wu Chunhua,Zhou Diqing,et al.A survey of fault diagnosis for PV array based BP neural network[J].Power System Protection and Control,2013,41(16):110-114(in Chinese).
[11]刘景艳,王福忠,杨占山.基于RBF神经网络和自适应遗传算法的变压器故障诊断[J].武汉大学学报:工学版,2016,49(1):88-93.Liu Jingyan,Wang Fuzhong,Yang Zhanshan.Transformer fault diagnosis based on RBF neural network and adaptive genetic algorithm[J].Engineering Journal of Wuhan University:Natural Science Edition,2016,49(1):88-93(in Chinese).
[12]刘景艳,李玉东,杨晓邦.遗传神经网络在齿轮故障诊断中的应用[J].郑州大学学报:工学版,2012,33(3):36-39.Liu Jingyan,Li Yudong,Yang Xiaobang.Application of genetic neural network to gear fault diagnosis[J].Journal of Zhengzhou University:Engineering Science,2012,33(3):36-39(in Chinese).
[13]左磊,侯立刚,张旺,等.基于粒子群-支持向量机的模拟电路故障诊断[J].系统工程与电子技术,2010,32(7):1553-1556.Zuo Lei,Hou Ligang,Zhang Wang,et al.Analog circuit fault diagnosis based on particle swarm optimization support vector machine[J].Systems Engineering and Electronics,2010,32(7):1553-1556(in Chinese).
[14]沈桂鹏,杨店飞,郭宇杰.基于自适应权重粒子群优化BP神经网络的光伏阵列故障诊断与定位[J].陕西电力,2016,44(8):23-27.Shen Guipeng,Yang Dianfei,Guo Yujie.Fault diagnosis and location of photovoltaic array based on BP neural network trained by adaptive inertia weight particle swarm optimization algorithm[J].Shanxi Electric Power,2016,44(8):23-27(in Chinese).
[15]孟祥萍,潘莹,耿卫星,等.混沌免疫遗传算法在电力系统故障诊断中应用[J].电力自动化设备,2007,27(5):81-83,100.Meng Xiangping,Pan Ying,Geng Weixing,et al.Chaotic immune genetic algorithm in power system fault diagnosis[J].Electric Power Automation Equipment,2017,27(5):81-83,100(in Chinese).
[16]祁涛,张彦斌,温晋华.基于遗传粒子群算法的模拟电路故障诊断方法研究[J].计算机测量与控制,2015,23(12):3940-3943.Qi Tao,Zhang Yanbin,Wen Jinhua.Analog circuit fault diagnosis based on genetic particle swarm optimization algorithm(GAPSO)[J].Computer Measurement and Control,2015,23(12):3940-3943(in Chinese).
[17]袁圃,毛剑琳,向凤红,等.改进的基于遗传优化BP神经网络的电网故障诊断[J].电力系统及其自动化学报,2017,29(1):118-122.Yuan Ying,Mao Jianlin,Xiang Fenghong,et al.Grid fault diagnosis based on improved genetic optimization BP neural network[J].Proceedings of the CSU-EPSA,2017,29(1):118-122(in Chinese).
[2]李兵峰.光伏阵列故障检测方法的研究[D].天津:天津大学,2010.Li Bingfeng.Research on fault detection method of PV array[D].Tianjin:Tianjin University,2010(in Chinese).
[3]温正.精通MATLAB智能算法[M].北京:清华大学出版社,2015.
[4]于群,曹娜.电力系统建模与仿真[M].北京:机械工业出版社,2011.
[5]谢柱.基于特性参数的太阳能电池和光伏阵列建模研究[J].华东电力,2010,38(4):581-584.Xie Zhu.Study on modeling of solar cells and photovoltaic arrays based on characteristic parameters[J].East China Electric Power,2010,38(4):581-584(in Chinese).
[6]杨店飞,郭宇杰,沈桂鹏.基于BP神经网络的光伏组件故障类型诊断[J].陕西电力,2016,44(2):15-21.Yang Dianfei,Guo Yujie,Shen Guipeng.Fault types diagnosis of PV module based on BP neural network[J].Shanxi Electric Power,2016,44(2):15-21(in Chinese).
[7]乐治后.基于RBF神经网络的光伏电池故障诊断[J].上海电气技术,2015,8(3):28-32.Le Zhihou.Fault diagnosis of photovoltaic battery based on RBF neural network[J].Shanghai Electronic Technology,2015,8(3):28-32(in Chinese).
[8]兰琴丽,章乐多.BP神经网络在光伏发电系统故障诊断中的应用[J].通信电源技术,2011,28(4):38-40.Lan Qinli,Zhang Leduo.Application of BP neural network in fault diagnosis of solar photovoltaic system[J].Telecom Power Technology,2011,28(4):38-40(in Chinese).
[9]张文瑾,葛强,黄澄扬,等.基于BP神经网络的光伏阵列智能故障诊断[J].扬州大学学报:自然科学版,2015,18(1):32-35.Zhang Wenjin,Ge Qiang,Huang Chengyang,et al.The photovolatic array intelligent fault diagnosis based on the BP neural network[J].Journal of Yangzhou University:Natural Science Edition,2015,18(1):32-35(in Chinese).
[10]王元章,吴春华,周笛青,等.基于BP神经网络的光伏阵列故障诊断研究[J].电力系统保护与控制,2013,41(16):110-114.Wang Yuanzhang,Wu Chunhua,Zhou Diqing,et al.A survey of fault diagnosis for PV array based BP neural network[J].Power System Protection and Control,2013,41(16):110-114(in Chinese).
[11]刘景艳,王福忠,杨占山.基于RBF神经网络和自适应遗传算法的变压器故障诊断[J].武汉大学学报:工学版,2016,49(1):88-93.Liu Jingyan,Wang Fuzhong,Yang Zhanshan.Transformer fault diagnosis based on RBF neural network and adaptive genetic algorithm[J].Engineering Journal of Wuhan University:Natural Science Edition,2016,49(1):88-93(in Chinese).
[12]刘景艳,李玉东,杨晓邦.遗传神经网络在齿轮故障诊断中的应用[J].郑州大学学报:工学版,2012,33(3):36-39.Liu Jingyan,Li Yudong,Yang Xiaobang.Application of genetic neural network to gear fault diagnosis[J].Journal of Zhengzhou University:Engineering Science,2012,33(3):36-39(in Chinese).
[13]左磊,侯立刚,张旺,等.基于粒子群-支持向量机的模拟电路故障诊断[J].系统工程与电子技术,2010,32(7):1553-1556.Zuo Lei,Hou Ligang,Zhang Wang,et al.Analog circuit fault diagnosis based on particle swarm optimization support vector machine[J].Systems Engineering and Electronics,2010,32(7):1553-1556(in Chinese).
[14]沈桂鹏,杨店飞,郭宇杰.基于自适应权重粒子群优化BP神经网络的光伏阵列故障诊断与定位[J].陕西电力,2016,44(8):23-27.Shen Guipeng,Yang Dianfei,Guo Yujie.Fault diagnosis and location of photovoltaic array based on BP neural network trained by adaptive inertia weight particle swarm optimization algorithm[J].Shanxi Electric Power,2016,44(8):23-27(in Chinese).
[15]孟祥萍,潘莹,耿卫星,等.混沌免疫遗传算法在电力系统故障诊断中应用[J].电力自动化设备,2007,27(5):81-83,100.Meng Xiangping,Pan Ying,Geng Weixing,et al.Chaotic immune genetic algorithm in power system fault diagnosis[J].Electric Power Automation Equipment,2017,27(5):81-83,100(in Chinese).
[16]祁涛,张彦斌,温晋华.基于遗传粒子群算法的模拟电路故障诊断方法研究[J].计算机测量与控制,2015,23(12):3940-3943.Qi Tao,Zhang Yanbin,Wen Jinhua.Analog circuit fault diagnosis based on genetic particle swarm optimization algorithm(GAPSO)[J].Computer Measurement and Control,2015,23(12):3940-3943(in Chinese).
[17]袁圃,毛剑琳,向凤红,等.改进的基于遗传优化BP神经网络的电网故障诊断[J].电力系统及其自动化学报,2017,29(1):118-122.Yuan Ying,Mao Jianlin,Xiang Fenghong,et al.Grid fault diagnosis based on improved genetic optimization BP neural network[J].Proceedings of the CSU-EPSA,2017,29(1):118-122(in Chinese).
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |