基于t-SNE流形学习与快速聚类算法的光伏逆变器故障预测技术

doi:10.11930/j.issn.1004-9649.201902032

中国电力 ›› 2020, Vol. 53 ›› Issue (6): 41-47.DOI: 10.11930/j.issn.1004-9649.201902032

• 人工智能在电力系统的应用 • 上一篇下一篇

基于t-SNE流形学习与快速聚类算法的光伏逆变器故障预测技术

张筱辰^1,2, 朱金大^1,2, 杨冬梅^1,2, 陈永华^1,2, 杜炜^1,2

1. 南瑞集团（国网电力科学研究院）有限公司，江苏南京 211106;
2. 国电南瑞科技股份有限公司，江苏南京 211106

收稿日期:2019-02-11 修回日期:2019-12-10 发布日期:2020-06-05
作者简介:张筱辰(1988-),男,通信作者,博士,出站博士后,从事信息物理系统、综合能源系统研究,E-mail:zhangxch2008@126.com;朱金大(1964-),男,高级工程师(教授级),从事智能配用电及其自动化、能源互联网研究,E-mail:zhujinda@sgepri.sgcc.com.cn;杨冬梅(1983-),女,高级工程师,从事综合能源、能源互联网研究,E-mail:yangdongmei@sgepri.sgcc.com.cn
基金资助:
国家重点研发计划资助项目(2018YFB0905000)

Photovoltaic Inverter Fault Prediction Technology Based on t-SNE Manifold Learning and Fast Clustering Algorithm

ZHANG Xiaochen^1,2, ZHU Jinda^1,2, YANG Dongmei^1,2, CHEN Yonghua^1,2, DU Wei^1,2

1. NARI Group Corporation(State Grid Electric Power Research Institute), Nanjing 211106, China;
2. NARI Technology Co., Ltd., Nanjing 211106, China

Received:2019-02-11 Revised:2019-12-10 Published:2020-06-05
Supported by:
This work is supported by National Key R&D Program of China (No.2018YFB0905000)

摘要/Abstract

摘要： 光伏逆变器作为太阳能光伏发电系统的关键设备，其健康状态直接影响电力系统的安全与稳定。提出了一种基于t-SNE流形学习与快速聚类算法的光伏逆变器故障预测技术，将光伏逆变器集群的历史监测信号作为原始特征库，采用t-SNE降维算法提取光伏逆变器集群的主特征矩阵，基于快速聚类算法搜寻每一采样时刻的聚类中心光伏逆变器，分别计算每台逆变器在各个采样时刻的偏心距离，得到归一化的累积偏心距离矩阵，通过合理设定预警阈值，从而实现光伏逆变器故障的准确预测。最后基于设计开发的分布式光伏发电监控系统，利用采集的光伏逆变器集群的历史运行数据对算法进行了测试。结果表明，提出的光伏逆变器故障预测技术能够提前准确地预测光伏逆变器故障，有助于保障设备健康平稳运行。

关键词: 故障预测, 流形学习, 聚类算法, 逆变器, 光伏

Abstract: As the key component of solar photovoltaic power generation system, photovoltaic inverter directly affects the safety and stable operation of power systems. Therefore, a photovoltaic inverter fault prediction technology is proposed based on t-SNE manifold learning and fast clustering algorithm. Firstly, the historical monitoring data of the PV inverter cluster are used to construct the original feature database. Secondly, the t-SNE dimensionality reduction algorithm is applied to extract the main feature matrix of the PV inverter cluster. Thirdly, the cluster center PV inverter at each sampling time is searched by the fast clustering algorithm, and the eccentricity distance of each inverter at the sampling time is calculated respectively. Then, the normalized accumulative eccentricity distance matrix is obtained. By setting a rational warning threshold, the accurate fault prediction is thus realized for photovoltaic inverters. Finally, the algorithm is tested with the collected PV inverter cluster data acquired by the distributed photovoltaic generation monitoring system. The results show that the proposed fault prediction technology can accurately predict the photovoltaic inverter faults in advance, which is helpful to ensure the healthy and stable operation of the equipment.

Key words: fault prediction, manifold learning, clustering algorithm, inverter, photovoltaic

张筱辰, 朱金大, 杨冬梅, 陈永华, 杜炜. 基于t-SNE流形学习与快速聚类算法的光伏逆变器故障预测技术[J]. 中国电力, 2020, 53(6): 41-47.

ZHANG Xiaochen, ZHU Jinda, YANG Dongmei, CHEN Yonghua, DU Wei. Photovoltaic Inverter Fault Prediction Technology Based on t-SNE Manifold Learning and Fast Clustering Algorithm[J]. Electric Power, 2020, 53(6): 41-47.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.201902032

https://www.electricpower.com.cn/CN/Y2020/V53/I6/41

参考文献

[1] 曾鸣, 杨雍琦, 李源非, 等. 能源互联网背景下新能源电力系统运营模式及关键技术初探[J]. 中国电机工程学报, 2016, 36(3): 681-691
ZENG Ming, YANG Yongqi, Li Yuanfei, et al. The preliminary research for key operation mode and technologies of electrical power system with renewable energy sources under energy internet[J]. Proceedings of the CSEE, 2016, 36(3): 681-691
[2] 孙宏斌, 郭庆来, 潘昭光. 能源互联网: 理念、架构与前沿展望[J]. 电力系统自动化, 2015, 39(19): 1-8
SUN Hongbin, GUO Qinglai, PAN Zhaoguang. Energy Internet: concept, architecture and frontier outlook[J]. Automation of Electric Power Systems, 2015, 39(19): 1-8
[3] 刘敦楠, 徐尔丰, 许小峰. 面向园区微网的“源-网-荷-储”一体化运营模式[J]. 电网技术, 2018, 42(3): 681-689
LIU Dunnan, XU Erfeng, XU Xiaofeng. “Source-network-load-storage” integrated operation model for microgrid in park[J]. Power System Technology, 2018, 42(3): 681-689
[4] 周京华, 刘劲东, 陈亚爱, 等. 大功率光伏逆变器的低电压穿越控制[J]. 电网技术, 2013, 37(7): 1799-1807
ZHOU Jinghua, LIU Jindong, CHEN Yaai, et al. Low voltage ride-through control of high power inverter for grid-connection of photovoltaic generation[J]. Power System Technology, 2013, 37(7): 1799-1807
[5] 陶顺, 姚黎婷, 廖坤玉, 等. 光伏逆变器直流电压扰动引起的间谐波电流解析模型[J]. 电网技术, 2018, 42(3): 878-885
TAO Shun, YAO Liting, LIAO Kunyu, et al. Analytical model for inter-harmonic current caused by DC voltage disturbance of photovoltaic inverter[J]. Power System Technology, 2018, 42(3): 878-885
[6] 边莉, 边晨源. 电网故障诊断的智能方法综述[J]. 电力系统保护与控制, 2014, 42(3): 146-153
BIAN Li, BIAN Chenyuan. Review on intelligence fault diagnosis in power networks[J]. Power System Protection and Control, 2014, 42(3): 146-153
[7] 张可, 周东华, 柴毅. 复合故障诊断技术综述[J]. 控制理论与应用, 2015, 32(9): 1143-1157
ZHANG Ke, ZHOU Donghua, CHAI Yi. Review of multiple fault diagnosis methods[J]. Control Theory & Applications, 2015, 32(9): 1143-1157
[8] 王少萍. 大型飞机机载系统预测与健康管理关键技术[J]. 航空学报, 2014, 35(6): 1459-1472
WANG Shaoping. Prognostics and health management key technology of aircraft airborne system[J]. Acta Aeronautica et Astronautica Sinica, 2014, 35(6): 1459-1472
[9] HAN Te, LIU Chao, WU Linjiang, et al. An adaptive spatiotemporal feature learning approach for fault diagnosis in complex systems[J]. Mechanical Systems and Signal Processing, 2019, 117: 170-187.
[10] COSME L B, CAMINHAS W M, D'ANGELO M F S V, et al. A novel fault-prognostic approach based on interacting multiple model filters and fuzzy systems[J]. IEEE Transactions on Industrial Electronics, 2019, 66(1): 519-528.
[11] 代杰杰, 宋辉, 盛戈皞, 等. 采用LSTM网络的电力变压器运行状态预测方法研究[J]. 高电压技术, 2018, 44(4): 1099-1106
DAI Jiejie, SONG Hui, SHENG Gehao, et al. Prediction method for power transformer running state based on LSTM network[J]. High Voltage Engineering, 2018, 44(4): 1099-1106
[12] 王恒, 马海波, 黄希, 等. 基于Kolmogrov-Smirnov检验和LS-SVM的机械设备故障预测[J]. 中南大学学报(自然科学版), 2016, 47(6): 1924-1929
WANG Heng, MA Haibo, HUANG Xi, et al. Prognostics of mechanical equipment based on Kolmogrov-Smirnov test and LS-SVM[J]. Journal of Central South University(Science and Technology), 2016, 47(6): 1924-1929
[13] ZHENG Jinde, JIANG Zhanwei, PAN Haiyang. Sigmoid-based refined composite multiscale fuzzy entropy and t-SNE based fault diagnosis approach for rolling bearing[J]. Measurement, 2018, 129: 332-342.
[14] DHALMAHAPATRA K, SHINGADE R, MAHAJAN H, et al. Decision support system for safety improvement: An approach using multiple correspondence analysis, t-SNE algorithm and K-means clustering[J]. Computers & Industrial Engineering, 2019, 128: 277-289.
[15] LAURENS Van Der Maaten, GEOFFREY Hinton. Visualizing data using t-SNE[J]. Journal of Machine Learning Research, 2008, 9: 2579-2605.
[16] 姚雪曼. 基于流形学习的降维技术的研究与实现[D]. 北京: 北京邮电大学, 2017.
YAO Xueman. The research and implementation of dimentionality reduction technology based on manifold learning[D]. Beijing: Beijing University of Posts and Telecom, 2017.
[17] 姜战伟, 郑近德, 潘海洋, 等. 基于多尺度时不可逆与t-SNE流形学习的滚动轴承故障诊断[J]. 振动与冲击, 2017, 36(17): 61-68, 84
JIANG Zhanwei, ZHENG Jinde, PAN Haiyang, et al. Rolling bearing fault diagnosis method based on multiscale time irreversibility and t-SNE manifold learning[J]. Journal of Vibration and Shock, 2017, 36(17): 61-68, 84
[18] RODRIGUEZ A, LAIO A. Clustering by fast search and find of density peaks[J]. Science, 2014, 344(6191): 1492-1496.
[19] ZHANG Xiaochen, JIANG Dongxiang, LONG Quan, et al. Rotating machinery fault diagnosis for imbalanced data based on decision tree and fast clustering algorithm[J]. Journal of Vibroengineering, 2017, 19(6): 4247-4259.
[20] MEHNOOD R, ZHANG Guangzhi, BIE Rongfang, et al. Clustering by fast search and find of density peaks via heat diffusion[J]. Neurocomputing, 2016, 208: 210-217.
[21] LEE J, WU Fangji, ZHAO Wenyu, et al. Prognostics and health management design for rotary machinery systems: Reviews, methodology and applications[J]. Mechanical Systems and Signal Processing, 2014, 42(1/2): 314-334.
[22] SAIDI L, BEN ALI J, BENBOUZID M, et al. An integrated wind turbine failures prognostic approach implementing Kalman smoother with confidence bounds[J]. Applied Acoustics, 2018, 138: 199-208.
[23] 李斌, 何佳伟. 多端柔性直流电网故障隔离技术研究[J]. 中国电机工程学报, 2016, 36(1): 87-95
LI Bin, HE Jiawei. Research on the DC fault isolating technique in multi-terminal DC system[J]. Proceedings of the CSEE, 2016, 36(1): 87-95

基于t-SNE流形学习与快速聚类算法的光伏逆变器故障预测技术

Photovoltaic Inverter Fault Prediction Technology Based on t-SNE Manifold Learning and Fast Clustering Algorithm

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	潘鹏程, 韩文舜, 郭雪丽. 基于有源和无源阻尼协同控制的光伏直流升压汇集系统谐振抑制[J]. 中国电力, 2025, 58(3): 20-30.
[2]	沃建栋, 潘武略, 李跃辉, 吴佳毅. 基于综合谐波驱动的光伏场站集电线路保护新方案[J]. 中国电力, 2025, 58(2): 133-139.
[3]	孙通, 张沈习, 曹毅, 曹佳晨, 程浩忠. 计及5G基站可调特性的配电网分布式光伏准入容量鲁棒优化[J]. 中国电力, 2025, 58(2): 140-146.
[4]	周才期, 刘静利, 孙鹏凯, 张玉敏. 分布式光伏波动事件多级区间滚动预警方法[J]. 中国电力, 2024, 57(8): 96-107.
[5]	王海军, 居蓉蓉, 董颖华. 基于时空关联特征与B-LSTM模型的分布式光伏功率区间预测[J]. 中国电力, 2024, 57(7): 74-80.
[6]	胡满琳, 李楠, 李一鸣, 皮志勇, 朱益, 李振兴. 基于负序分量的含光伏电源配电网故障区段定位方法[J]. 中国电力, 2024, 57(5): 188-199.
[7]	刘韵艺, 汤渊, 苏盛, 吴裕宙, 王晓倩. 基于STL-Bayesian时空模型的分布式光伏系统异常检测[J]. 中国电力, 2024, 57(5): 222-231.
[8]	张宇, 魏新迟, 冯凯辉, 时珊珊, 孟子涵, 梁媛. 计及分布式光伏承载力的配电网侧独立储能充放电策略[J]. 中国电力, 2024, 57(4): 111-117.
[9]	杨帆, 卫水平, 任意, 陈秭龙, 乐健. 变权-混合决策评估的复合功能并网逆变器多目标协同优化控制方法[J]. 中国电力, 2024, 57(3): 113-125.
[10]	战文华, 车建峰, 王勃, 丁禹. 基于网格化数值天气预报的区域光伏发电多输出功率预测方法[J]. 中国电力, 2024, 57(3): 144-151.
[11]	周于清, 李大虎, 姚伟, 宗启航, 周泓宇, 文劲宇. 受端近区光伏电站对LCC-HVDC系统稳定性影响分析[J]. 中国电力, 2024, 57(3): 170-182.
[12]	覃海, 陈胜, 张洪略, 夏天, 马覃峰, 段展宇, 颜伟. 并网光伏电站关口无功调节能力的分时段等值方法[J]. 中国电力, 2024, 57(2): 27-33.
[13]	刘宁, 张驰, 王栋, 杨明杰. 西北地区扶贫光伏整县开发决策演化博弈[J]. 中国电力, 2024, 57(2): 149-160.
[14]	李翰章, 冯江涛, 王鹏程, 荣澔洁, 柴宇唤. 基于TDE-SO-AWM-GRU的光伏发电功率预测模型[J]. 中国电力, 2024, 57(12): 41-49.
[15]	陈璨, 苏紫诺, 马原, 刘佳林, 王玉庆, 王飞. 基于分层关联性建模的分布式光伏功率超短期概率预测[J]. 中国电力, 2024, 57(12): 50-59.

模态框（Modal）标题

基于t-SNE流形学习与快速聚类算法的光伏逆变器故障预测技术

Photovoltaic Inverter Fault Prediction Technology Based on t-SNE Manifold Learning and Fast Clustering Algorithm

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics