光伏阵列非线性输出的特性以及最大功率点跟踪算法,会影响光伏阵列保护设备的工作。为了正确辨识光伏阵列的运行状态,本研究提出一种基于贝叶斯优化算法（BOA）、堆栈自动编码器（SAE）以及集成极限学习机（EELM）相结合的故障诊断方法。首先,将光伏阵列的时序波形进行标准化处理;接着,使用SAE对标准化后的时序波形进行特征自动提取,并训练一个EELM的故障分类模型;最后,利用BOA对诊断模型的超参数进行优化。实验结果表明所提方法对仿真和实验的故障诊断准确率分别达到了98.40%和98.10%,优于反向传播（BP）神经网络、支持向量机、随机森林等方法。
Abstract
The nonlinear characteristics of the output of the photovoltaic（PV） array and the maximum power point tracking algorithm will affect the operation of PV array protection equipment. In order to identify correctly the operating status of PV array, a novel fault diagnosis method that combines Bayesian optimization algorithm（BOA）, stacked autoencoder（SAE）, and ensemble extreme learning machine（EELM） is proposed in this study. First, the time sequence waveform of PV array is standardized. Then, SAE is used to automatically extract the features of the standardized time sequence waveforms, and an EELM model is trained for fault classification. Finally, BOA optimizes the overall diagnosis model. The experimental results show that the proposed method has 98.40% and 98.10% fault diagnosis accuracy for simulation and experiment, respectively, which is better than that of backpropagation neural network, support vector machine, random forest, etc.
关键词
光伏阵列 /
故障诊断 /
堆栈自动编码器 /
极限学习机 /
贝叶斯优化算法 /
时序波形
Key words
photovoltaic array /
fault diagnosis /
stacked autoencoder（SAE） /
extreme learning machine（ELM） /
Bayesian optimization algorithm（BOA） /
sequence waveform
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 李光辉, 段晨东, 武珊.基于半监督机器学习法的光伏阵列故障诊断[J]. 电网技术, 2020, 44(5): 1908-1913.
LI G H, DUAN C D, WU S.Fault diagnosis of PV array based on semi-supervised machine learning[J]. Power system technology, 2020, 44(5): 1908-1913.
[2] ZHAO Y, PALMA J D, MOSESIAN J, et al. Line-line fault analysis and protection challenges in solar photovoltaic arrays[J]. IEEE transactions on industrial electronics, 2013, 60(9): 3784-3795.
[3] 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(3): 21-23.
HU Y H, DENG Y, HE X N.A summary of PV array fault diagnosis method[J]. Power electronics, 2013(3): 21-23.
[4] MADETI S R, SINGH S N.A comprehensive study on different types of faults and detection techniques for solar photovoltaic system[J]. Solar energy, 2017, 158: 161-185.
[5] 毛峡, 李亚豪.光伏阵列故障检测中的无人机红外图像拼接[J]. 太阳能学报, 2020, 41(3): 262-269.
MAO X, LI Y H.Infrared image stitching of UAV in fault detection of photovoltaic array[J]. Acta energiae solaris sinica, 2020, 41(3): 262-269.
[6] 陈宇航, 闫腾飞, 谢添, 等. 基于功率损失和U-I特性综合考虑的光伏组件故障诊断方法[J]. 电机与控制应用, 2016, 43(11): 92-97.
CHEN Y H, YAN T F, XIE T, et al. A novel fault diagnosis method of photo voltaic module based on power loss and U-I characteristics[J]. Electric machines & control application, 2016, 43(11): 92-97.
[7] 毕锐, 丁明, 徐志成, 等. 基于模糊C均值聚类的光伏阵列故障诊断方法[J]. 太阳能学报, 2016, 37(3): 730-736.
BI R, DING M, XU Z C, et al. PV array fault diagnosis based on FCM[J]. Acta energiae solaris sinica, 2016, 37(3): 730-736.
[8] YI Z H, ETEMADI A H.Line-to-line fault detection for photovoltaic arrays based on multiresolution signal decomposition and two-stage support vector machine[J]. IEEE transactions on industrial electronics, 2017, 64(11): 8546-8556.
[9] ALAM M K, KHAN F, JOHNSON J, et al. A comprehensive review of catastrophic faults in PV arrays:Types, detection, and mitigation techniques[J]. IEEE journal of photovoltaics, 2015, 5(3): 982-997.
[10] PEI D Y, BURNS M, CHANDRAMOULI R, et al. Decoding asynchronous reaching in electro- encephalography using stacked autoencoder[J]. IEEE access, 2018, 6: 52889-52898.
[11] PRINCIPI E, ROSSETTI D, SQUARTINI S, et al. Unsupervised electric motor fault detection by using deep autoencoders[J]. IEEE/CAA journal of automatica sinica, 2019, 6(2): 441-451.
[12] HUANG G B, ZHOU H M, DING X J.Extreme learning machine for regression and multiclass classification[J]. IEEE transactions on systems, man and cybernetics, Part B(cybernetics), 2012, 42(2): 513-529.
[13] CHO H, KIM Y, RHEE W, et al. Basic enhancement strategies when using Bayesian optimization for hyperparameter tuning of deep neural networks[J]. IEEE access, 2020, 8: 52588-52608.
[14] LAURENS V D M, HINTON G.Visualizing data using t-SNE[J]. Journal of machine learning research, 2008, 9: 2579-2605.
[15] 贾嵘, 李云桥, 马富齐, 等. 基于改进BP神经网络的光伏阵列多传感器故障检测定位方法[J]. 太阳能学报, 2018, 39(1): 110-116.
JIA R, LI Y Q, MA F Q, et al. Multi-sensor fault detection and positioning method of photovoltaic array based on improved BP neural network[J]. Acta energiae solaris sinica, 2018, 39(1): 110-116.
[16] CHEN Z C, HAN F C, WU L J, et al. Random forest based intelligent fault diagnosis for PV arrays using array voltage and string currents[J]. Energy conversion and management, 2018, 178: 250-264.
基金
国家自然科学基金（51677030）; 晋江市福大科教园区发展中心科研项目（2019-JJFDKY-23）
PDF(2760 KB)
