Improved similarity-based modeling approach for dust deposition monitoring of photovoltaic modules

doi:10.3785/j.issn.1008-973X.2022.04.011

Journal of ZheJiang University (Engineering Science)

2022, Vol. 56

Issue (4): 718-726 DOI: 10.3785/j.issn.1008-973X.2022.04.011

Improved similarity-based modeling approach for dust deposition monitoring of photovoltaic modules

Zhong-hao WANG1(

),Zheng-guo XU1,*(

),Yun ZHANG2

1. College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China
2. Shanghai Electric Distributed Energy Technology Limited Company, Shanghai 200070, China

Download:

HTML

PDF(1572KB) HTML
Export: BibTeX | EndNote (RIS)

Abstract

A weakly-supervised data-driven approach, improved similarity-based modeling (SBM) approach, was proposed aiming at the problem of dust deposition monitoring of photovoltaic modules. The great error of theoretical formulas approaches, the high cost of computer vision approaches and the large requirements for training data of classical machine learning approaches were considered. Improvements in the steps of parameters selection, state matrix construction and update and similarity operator were made based on the original SBM in order to adapt the approach to the PV systems monitoring and increase the estimated accuracy and response rate. The improved SBM and five other approaches, theoretical formulas, feedforward neural network (FNN), support vector regression (SVR), random forest (RF), and the original SBM were employed for the dust estimation, and their performances were evaluated based on the real data from a dust deposition experiment. Results show that the improved SBM has the best accuracy at the cost of acceptable response time increase.

Key words： photovoltaic system dust deposition system condition monitoring comparative experiment similarity-based modeling (SBM)

Received: 10 May 2021 Published: 24 April 2022

CLC:

TM 615

Fund: 国家自然科学基金资助项目（61751307，61973269）

Corresponding Authors: Zheng-guo XU E-mail: 11632028@zju.edu.cn;xzg@zju.edu.cn

	Service
	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Zhong-hao WANG
	Zheng-guo XU
	Yun ZHANG

Cite this article:

Zhong-hao WANG,Zheng-guo XU,Yun ZHANG. Improved similarity-based modeling approach for dust deposition monitoring of photovoltaic modules. Journal of ZheJiang University (Engineering Science), 2022, 56(4): 718-726.

URL:

https://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2022.04.011 OR https://www.zjujournals.com/eng/Y2022/V56/I4/718

基于改进型相似性建模的光伏积灰监测方法

针对光伏系统积灰程度监测的问题，考虑到基于理论公式的方法误差较大，基于计算机视觉的方法成本较高，传统机器学习方法对训练数据有较高需求，提出弱监督的数据驱动方法：改进型相似性建模（SBM）方法. 在原始的SBM方法的基础上，对参数选取、状态矩阵构建与更新、相似性算子设计进行针对性的改进，使得该方法更加适用于光伏系统的应用，提高准确性与响应速度. 利用真实的积灰实验数据，对改进型SBM方法与其他5种方法的积灰诊断效果进行对比，包括基于理论公式的方法、前馈神经网络（FNN）、支持向量回归（SVR）、随机森林（RF）和原始SBM方法. 结果表明，改进型SBM方法可以以可接受的响应速度劣势实现最佳的积灰程度监测准确性.

关键词： 光伏系统, 积灰, 系统状态监测, 对比实验, 相似性建模（SBM）

Fig.1 Flowchart of SBM approach

Fig.2 Diagram of PV work principle

Tab.1 Correlation analysis of selected parameters

Fig.3 Flowchart of improved SBM with classified state matrix

Fig.4 Photo of clean-dusty comparative experiment system

Fig.5 Diagram of clean-dusty comparative experiment system

Tab.2 Nominal values of PV panel parameters

Fig.6 Power of control group and experimental group

Fig.7 Relative difference of power of control group and experimental group

Tab.3 Evaluation of dust diagnostic results

Fig.8 Diagnostic results of FNN

Fig.9 Diagnostic results of SVR

Fig.10 Diagnostic results of RF

Fig.11 Evaluation results for dust deposition of FNN, SVR, and RF

Fig.12 Comparision of dust diagnostic results of all methods

Fig.13 Evaluation results for dust deposition of all methods

Fig.14 Evaluation results for dust deposition of all methods: R²

Tab.4 Response time of methods


[1]	WANG Z, XU Z, ZHANG Y, et al Optimal cleaning scheduling for photovoltaic systems in the field based on electricity generation and dust deposition forecasting[J]. IEEE Journal of Photovoltaics, 2020, 10 (4): 1126- 1132 doi: 10.1109/JPHOTOV.2020.2981810

[2]	KAZEM H A, CHAICHAN M T Experimental analysis of the effect of dust’s physical properties on photovoltaic modules in Northern Oman[J]. Solar Energy, 2016, 139: 68- 80 doi: 10.1016/j.solener.2016.09.019

[3]	SCHILL C, BRACHMANN S, KOEHL M Impact of soiling on IV-curves and efficiency of PV-modules[J]. Solar Energy, 2015, 112: 259- 262 doi: 10.1016/j.solener.2014.12.003

[4]	赵波, 张姝伟, 曹生现, 等基于状态监测的电池板积灰清洗周期确定与费用评估[J]. 中国电机工程学报, 2019, 39 (14): 4205- 4213 ZHAO Bo, ZHANG Shu-wei, CAO Sheng-xian, et al Cleaning cycle determination and cost estimation for photovoltaic modules based on dust accumulating condition monitoring[J]. Proceedings of the Chinese Society for Electrical Engineering, 2019, 39 (14): 4205- 4213

[5]	MATTEI M, NOTTON G, CRISTOFARI C, et al Calculation of the polycrystalline PV module temperature using a simple method of energy balance[J]. Renewable Energy, 2006, 31 (4): 553- 567 doi: 10.1016/j.renene.2005.03.010

[6]	ZAPATA J W, PEREZ M A, KOURO S, et al Design of a cleaning program for a pv plant based on analysis of energy losses[J]. IEEE Journal of Photovoltaics, 2015, 5 (6): 1748- 1756 doi: 10.1109/JPHOTOV.2015.2478069

[7]	ARANEO R, GRASSELLI U, CELOZZI S Assessment of a practical model to estimate the cell temperature of a photovoltaic module[J]. International Journal of Energy and Environmental Engineering, 2014, 5 (72): 1- 16

[8]	RAMLI M A M, PRASETYONO E, WICAKSANA R W, et al On the investigation of photovoltaic output power reduction due to dust accumulation and weather conditions[J]. Renewable Energy, 2016, 99: 836- 844 doi: 10.1016/j.renene.2016.07.063

[9]	张姝伟. 基于视觉的光伏板积灰状态监测与性能评估[D]. 吉林: 东北电力大学, 2019. ZHANG Shu-wei. Vision-based monitoring and performance evaluation of photovoltaic panel dust deposition [D]. Jilin: Northeast Electric Power University, 2019.

[10]	YANG M, JI J, GUO B Soiling quantification using an image-based method: effects of imaging conditions[J]. IEEE Journal of Photovoltaics, 2020, 10 (6): 1780- 1787 doi: 10.1109/JPHOTOV.2020.3018257

[11]	SIMONAZZI M, CHIORBOLI G, COVA P, et al Smart soiling sensor for PV modules[J]. Microelectronics Reliability, 2020, 114: 113789 doi: 10.1016/j.microrel.2020.113789

[12]	PULIPAKA S, MANI F, KUMAR R Modeling of soiled PV module with neural networks and regression using particle size composition[J]. Solar Energy, 2016, 123: 116- 126 doi: 10.1016/j.solener.2015.11.012

[13]	PULIPAKA S, KUMAR R Power prediction of soiled PV module with neural networks using hybrid data clustering and division techniques[J]. Solar Energy, 2016, 133: 485- 500 doi: 10.1016/j.solener.2016.04.004

[14]	HEINRICH M, MEUNIER S, SAMé A, et al Detection of cleaning interventions on photovoltaic modules with machine learning[J]. Applied Energy, 2020, 263: 114642 doi: 10.1016/j.apenergy.2020.114642

[15]	SINGER R M, GROSS K C, HERZOG J P, et al. Model-based nuclear power plant monitoring and fault detection: theoretical foundations [R]. Lemont: Argonne National Lab. , IL, 1997.

[16]	GERTLER J. Fault detection and diagnosis in engineering systems [M]. New York: CRC Press, 1998.

[17]	WEGERICH S W. Similarity based modeling of time synchronous averaged vibration signals for machinery health monitoring [C]// Proceedings of 2004 IEEE Aerospace Conference. Big Sky: IEEE, 2004: 3654–3662.

[18]	WEGERICH S Similarity-based modeling of vibration features for fault detection and identification[J]. Sensor Review, 2005, 25: 114- 122 doi: 10.1108/02602280510585691

[19]	国家市场监督管理总局. 光伏发电效率技术规范: GB/T 39857–2021 [S]. 北京: 中国标准出版社, 2021.

[20]	ZHU J, CHEN N, PENG W Estimation of bearing remaining useful life based on multiscale convolutional neural network[J]. IEEE Transactions on Industrial Electronics, 2018, 66 (4): 3208- 3216

[21]	MOHAMMADI B, MEHDIZADEH S Modeling daily reference evapotranspiration via a novel approach based on support vector regression coupled with whale optimization algorithm[J]. Agricultural Water Management, 2020, 237: 106145 doi: 10.1016/j.agwat.2020.106145

[1]	CAO Wei-Hua, LI Meng-Yang, CHEN Xin, TUN Min. Novel high-efficient charge controller in independent photovoltaic system[J]. Journal of ZheJiang University (Engineering Science), 2010, 44(7): 1260-1265.

Viewed

Full text

Abstract

Cited

Shared

Discussed