一种基于改进DBSCAN算法的光伏故障检测方法
|
摘要
工程中常常通过与邻近电站的单位发电量比较发现故障电站,电站的单位发电量主要与电站地理位置、光伏器件型号及特性等诸多要素有关,选择哪些电站进行比较以及比较的策略是一个需要深入探讨的问题。本文提出了一种改进的A-DBSCAN聚类算法的光伏发电站故障检测方法。通过对影响发电站单位发电量因素的分析,确定了该故障检测模型的输入变量。该方法不需其他外接设备的支持,同时还可以实现在线检测分析。通过比较相同发电环境中的发电系统的单位发电量来对故障检测,初步实验结果反映该方法的正确率为95. 45%,召回率为91. 3%。
In engineering projects,the faulty power station can be found by comparing the unit power generation with the neighbor power stations. The unit power generation of the power station is mainly related to the location of the power station,the type and characteristics of the photovoltaic device,and other factors. Choosing which power stations to compare and the strategy for comparison are issues that needs to be explored in depth. In the paper,an improved A-DBSCAN clustering algorithm for fault detection of photovoltaic power station is presented. The input variables of thefault detection model are determined by analyzing the factors affecting the unit power generation of the power station. This method does not need the support of other peripheral devices,but also enables online detection and analysis. By comparing the unit generating capacity of the power generation system in the same generation environment to detect the fault,the preliminary experimental results show that the correct rate of this method is 95. 45 % and the recall rate is 91. 3 %.
In engineering projects,the faulty power station can be found by comparing the unit power generation with the neighbor power stations. The unit power generation of the power station is mainly related to the location of the power station,the type and characteristics of the photovoltaic device,and other factors. Choosing which power stations to compare and the strategy for comparison are issues that needs to be explored in depth. In the paper,an improved A-DBSCAN clustering algorithm for fault detection of photovoltaic power station is presented. The input variables of thefault detection model are determined by analyzing the factors affecting the unit power generation of the power station. This method does not need the support of other peripheral devices,but also enables online detection and analysis. By comparing the unit generating capacity of the power generation system in the same generation environment to detect the fault,the preliminary experimental results show that the correct rate of this method is 95. 45 % and the recall rate is 91. 3 %.
引文
[1]王培珍,郑诗程.基于红外图像的太阳能光伏阵列故障分析[J].太阳能学报,2010,31(2):197-202.
[2] BEI N,FU Z Z,LI W et al. Automatic detection of defects in solar modules:Image processing in detecting[C]//International Conference on Wireless Communications NETWORKING and Mobile Computing. Changlu,China:IEEE Computer Society,2010:1-4.
[3]张晓娜,高德东,刘海雄,等.一种新型光伏阵列多传感器故障检测定位方法[J].可再生能源,2016,34(2):166-172.
[4]王欢,徐小力.一种新型光伏阵列在线故障检测方法研究[J].仪器仪表学报,2015,36(12):2765-2772.
[5] LIU Y L,LI B F,ZHONG D. Research on domestic PV module structure based on fault detection[C]//Proceedings of the8th World Congress on Intelligent Control and Automation. Jinan,China:IEEE Computer Society,2010:171-175.
[6] LIU Y L,LI B F,CHENG Z. Research on PV module structure based on fault detection[C]//Proceedings of Chinese Control and Decision Conference. Xuzhou,China:IEEE Computer Society,2010:3891-3895.
[7]程泽,李兵峰,刘力,等.一种新型结构的光伏阵列故障检测方法[J].电子测量与仪器学报,2010,24(2):131-136.
[8] OOZEKI T,YAMADA T,KATO K. On-site measurements of photovoltaic systems for detection of failure modules[C]//Proceedings of the 33rd IEEE Photovoltaic Specialists Conference. San Diego,USA:IEEE Computer Society,2008:1-6.
[9] TANG J N,ZHU Y Q,WANG W S. Fault diagnosis method and simulation analysis for photovoltaic array[C]//International Conference on Electrical and Control Engineering. Yichang,China:IEEE Computer Society,2011:1569-1573.
[10] XU X L,WANG H,ZUO Y B. Method for diagnosing photovoltaic array fault in solar photovoltaic system[C]//Asia-Pacific Power and Energy Engineering Conference. Wuhan,China:IEEE Computer Society,2011:1-5.
[11] CHINE W,MELLIT A,PAVAN A M et al. Fault diagnosis in photovoltaic arrays[C]//International Conference on Clean Electrical Power(ICCEP). Taormina,Italy:IEEE Computer Society,2015:67-72.
[12]丁坤,冯莉,王祥,等.小型光伏系统故障诊断方法研究[J].电网与清洁能源,2015,31(5):74-78.
[13] JIANG L L,DOUGLAS L. Maskell. Automatic fault detection and diagnosis for photovoltaic systems using combined artificial neural network and analytical based methods[C]//International Joint Conference on Neural Networks(IJCNN).Killarney,Ireland:IEEE Computer Society,2015:1-8.
[14]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.
[15]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):108-114.
[16] ZHAO Y,YANG L,LEHMAN B et al. Decision tree-based fault detection and classification in solar photovoltaic arrays[C]//Proceedings of the Twenty-Seventh Annual IEEE Applied Power Electronics Conference and Exposition(APEC).Orlando,USA:IEEE Computer Society,2012:93-99.
[17]徐瑞东,陈昊,胡义华,等.基于高斯过程的光伏阵列故障定位[J].电工技术学报,2013,28(6):249-256.
[18] CHOUAY Y,OUASSAID M. An intelligent method for fault diagnosis in photovoltaic systems[C]//2017 International Conference on Electrical and Information Technologies(ICEIT). Rabat,Morocco:IEEE Computer Society,2017:1-5.
[19] HOSENUZZAMAN M,RAHIM N A,SELVARAJ J et al. Factors affecting the PV based power generation[C]//Proceedings of the 3rd IET International Conference on Clean Energy and Technology(CEAT). Kuching,Malaysia:IEEE Computer Society,2014:1-6.
[20]光伏太阳能网.浅析光伏电站发电量与光伏组件衰减的关系[EB/OL]. http://m. solarzoom. com/index. php/article/58583.
[21] SHARMA S,SHARMA A K,SONI D. Enhancing DBSCAN algorithm for data mining[C]//2017 International Conference on Energy,Communication,Data Analytics and Soft Computing(ICECDS). Chennai,India:IEEE Computer Society,2017:1634-1638.
[22] DHARNI C,BNASAL M. An improvement of DBSCAN Algorithm to analyze cluster for large datasets[C]//2013 IEEE International Conference in MOOC,Innovation and Technology in Education(MITE). Jaipur,India:IEEE Computer Society,2013:42-46.
[23]王实美.基于DBSCAN的自适应非均匀密度聚类算法研究[D].北京:北京交通大学,2017.
[2] BEI N,FU Z Z,LI W et al. Automatic detection of defects in solar modules:Image processing in detecting[C]//International Conference on Wireless Communications NETWORKING and Mobile Computing. Changlu,China:IEEE Computer Society,2010:1-4.
[3]张晓娜,高德东,刘海雄,等.一种新型光伏阵列多传感器故障检测定位方法[J].可再生能源,2016,34(2):166-172.
[4]王欢,徐小力.一种新型光伏阵列在线故障检测方法研究[J].仪器仪表学报,2015,36(12):2765-2772.
[5] LIU Y L,LI B F,ZHONG D. Research on domestic PV module structure based on fault detection[C]//Proceedings of the8th World Congress on Intelligent Control and Automation. Jinan,China:IEEE Computer Society,2010:171-175.
[6] LIU Y L,LI B F,CHENG Z. Research on PV module structure based on fault detection[C]//Proceedings of Chinese Control and Decision Conference. Xuzhou,China:IEEE Computer Society,2010:3891-3895.
[7]程泽,李兵峰,刘力,等.一种新型结构的光伏阵列故障检测方法[J].电子测量与仪器学报,2010,24(2):131-136.
[8] OOZEKI T,YAMADA T,KATO K. On-site measurements of photovoltaic systems for detection of failure modules[C]//Proceedings of the 33rd IEEE Photovoltaic Specialists Conference. San Diego,USA:IEEE Computer Society,2008:1-6.
[9] TANG J N,ZHU Y Q,WANG W S. Fault diagnosis method and simulation analysis for photovoltaic array[C]//International Conference on Electrical and Control Engineering. Yichang,China:IEEE Computer Society,2011:1569-1573.
[10] XU X L,WANG H,ZUO Y B. Method for diagnosing photovoltaic array fault in solar photovoltaic system[C]//Asia-Pacific Power and Energy Engineering Conference. Wuhan,China:IEEE Computer Society,2011:1-5.
[11] CHINE W,MELLIT A,PAVAN A M et al. Fault diagnosis in photovoltaic arrays[C]//International Conference on Clean Electrical Power(ICCEP). Taormina,Italy:IEEE Computer Society,2015:67-72.
[12]丁坤,冯莉,王祥,等.小型光伏系统故障诊断方法研究[J].电网与清洁能源,2015,31(5):74-78.
[13] JIANG L L,DOUGLAS L. Maskell. Automatic fault detection and diagnosis for photovoltaic systems using combined artificial neural network and analytical based methods[C]//International Joint Conference on Neural Networks(IJCNN).Killarney,Ireland:IEEE Computer Society,2015:1-8.
[14]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.
[15]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):108-114.
[16] ZHAO Y,YANG L,LEHMAN B et al. Decision tree-based fault detection and classification in solar photovoltaic arrays[C]//Proceedings of the Twenty-Seventh Annual IEEE Applied Power Electronics Conference and Exposition(APEC).Orlando,USA:IEEE Computer Society,2012:93-99.
[17]徐瑞东,陈昊,胡义华,等.基于高斯过程的光伏阵列故障定位[J].电工技术学报,2013,28(6):249-256.
[18] CHOUAY Y,OUASSAID M. An intelligent method for fault diagnosis in photovoltaic systems[C]//2017 International Conference on Electrical and Information Technologies(ICEIT). Rabat,Morocco:IEEE Computer Society,2017:1-5.
[19] HOSENUZZAMAN M,RAHIM N A,SELVARAJ J et al. Factors affecting the PV based power generation[C]//Proceedings of the 3rd IET International Conference on Clean Energy and Technology(CEAT). Kuching,Malaysia:IEEE Computer Society,2014:1-6.
[20]光伏太阳能网.浅析光伏电站发电量与光伏组件衰减的关系[EB/OL]. http://m. solarzoom. com/index. php/article/58583.
[21] SHARMA S,SHARMA A K,SONI D. Enhancing DBSCAN algorithm for data mining[C]//2017 International Conference on Energy,Communication,Data Analytics and Soft Computing(ICECDS). Chennai,India:IEEE Computer Society,2017:1634-1638.
[22] DHARNI C,BNASAL M. An improvement of DBSCAN Algorithm to analyze cluster for large datasets[C]//2013 IEEE International Conference in MOOC,Innovation and Technology in Education(MITE). Jaipur,India:IEEE Computer Society,2013:42-46.
[23]王实美.基于DBSCAN的自适应非均匀密度聚类算法研究[D].北京:北京交通大学,2017.