|
|
|
| Online fault detection method for photovoltaic array based on dynamic time warping |
| Cai Yuqiao1, Lin Peijie1, Lin Yaohai2, Zheng Qiao1, Cheng Shuying1 |
1. School of Physics and Information Engineering, and Institute of Micro-Nano Devices and Solar Cells, Fuzhou University, Fuzhou 350108;
2. College of Computer and Information Sciences, Fujian Agriculture and Forest University, Fuzhou 350002 |
|
|
|
|
Abstract As the core component of solar power station, online fault decetion of photovoltaic (PV) array is an effective method to improve the efficiency and safety of the entire system. Common online detection methods usually need to monitor multiple parameters without distinguishing the degree of the same type of fault. This paper proposes an online detection method for PV arrays, the only parameter to be monitored by this method is the current of the PV strings of the array, this model is concise and reliable. The real-time data stream of the PV array is transmitted and stored by RabbitMQ system. The pre-processed PV data is detected by the DTW detection algorithm, which can identify the fault degree of the fault. The experiment result shows the effectiveness of the proposed method in a 1.8kW grid-connected PV system.
|
|
Received: 06 February 2020
|
|
|
|
| Cite this article: |
|
Cai Yuqiao,Lin Peijie,Lin Yaohai等. Online fault detection method for photovoltaic array based on dynamic time warping[J]. Electrical Engineering, 2020, 21(7): 42-47.
|
|
|
|
| URL: |
|
http://dqjs.cesmedia.cn/EN/Y2020/V21/I7/42
|
[1] 尹淞, 郝继红. 我国太阳能光伏发电技术应用综述[J]. 电力技术, 2009(3): 1-4, 8.
[2] 王先发, 顾卫祥. 光伏系统直流侧故障电弧的检测与判别[J]. 电气技术, 2019, 20(5): 10-13.
[3] Chouder A, Silvestre S, Bilal T, et al.Monitoring, modelling and simulation of PV systems using LabVIEW[J]. Solar Energy, 2013, 91: 337-349.
[4] 王涛, 孙志鹏, 崔青, 等. 基于分类决策树算法的电力变压器故障诊断研究[J]. 电气技术, 2019, 20(11): 16-19.
[5] Chen Z, Han F, Wu L, et al.Random forest based intelligent fault diagnosis for PV arrays using array voltage and string currents[J]. Energy Convers & Manage 2018, 178: 250-264.
[6] 陈志宝, 丁杰, 周海, 等. 地基云图结合径向基函数人工神经网络的光伏功率超短期预测模型[J]. 中国电机工程学报, 2015(3): 561-567.
[7] 孙志鹏, 崔青, 张志磊, 等. 多分类支持向量机在电力变压器故障诊断中的应用[J]. 电气技术, 2019, 20(10): 25-28.
[8] Lin Peijie, Lin Yaohai, Chen Zhicong, et al.A density peak-based clustering approach for fault diagnosis of photovoltaic arrays[J]. International Journal of Photo- energy, 2017(204): 1-14.
[9] 杨大勇, 葛琪, 董永超, 等. 基于K均值聚类的光伏电站运行状态模式识别研究[J]. 电力系统保护与控制, 2016(14): 25-30.
[10] 马巍, 武欣嵘, 郑翔, 等. RabbitMQ在实时监控系统中的应用[J]. 军事通信技术, 2017, 38(1): 82-85.
[11] Zhao Y.Fault detection, classification and protection in solar photovoltaic arrays[M]. Northeastern University, ProQuest Dissertations Publishing, 2015.
[12] Ye Zhao, Roy B, Jerry M, et al.Graph-based semi- supervised learning for fault detection and classi- fication in solar photovoltaic arrays[J]. IEEE Transa- ctions on Power Electronics, 2015, 30(5): 2848-2858.
[13] 李文海, 程佳宇, 谢晨阳. 基于DTW相似判定的周期性时间序列预测方法[J]. 计算机科学, 2019(5): 157-162. |
|
|
|
2020, Vol. 21 
