arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2009.14712cs.CVcs.LGeess.IV
收藏

基于深度学习的流水线,用于根据EL测量进行模块功率预测

Deep Learning-based Pipeline for Module Power Prediction from EL Measurements

Universität Erlangen-Nürnberg (FAU)(埃尔朗根-纽伦堡大学);Forschungszentrum Jülich GmbH(于利希研究中心有限公司);Helmholtz-Institute Erlangen-Nuremberg for Renewable Energies(亥姆霍兹埃尔朗根-纽伦堡可再生能源研究所);School of Advanced Optical Technologies, Erlangen(埃尔朗根高等光学技术学院)

Mathis Hoffmann, Claudia Buerhop-Lutz, Luca Reeb, Tobias Pickel, Thilo Winkler, Bernd Doll, Tobias Würfl, Ian Marius Peters, Christoph Brabec, Andreas Maier, Vincent Christlein

摘要:

自动化检测在大型光伏电站的监控中发挥着重要作用。通常,电致发光测量用于识别太阳能模块上的各种类型的缺陷,但尚未用于确定模块的功率。然而,了解最大功率点的功率也很重要,因为单个模块的功率下降会影响整个串的性能。到目前为止,这通常是通过需要断开甚至拆卸模块的测量来确定的,这使得对单个模块进行定期检查变得不可行。在这项工作中,我们弥合电致发光测量和模块的功率确定之间的差距。我们编译了一个大型数据集的719电致发光测量模块在不同阶段的退化,特别是细胞裂缝和骨折,以及相应的功率在最大功率点。在这里,我们专注于非活性区域和裂纹作为主要类型的缺陷。我们建立了一个基线回归模型来预测电致发光测量的功率,平均绝对误差为9.0+/-3.7 $W_P$(4.0+/-8.4%)。然后,我们证明了深度学习可以用来训练一个性能明显更好的模型(7.3+/-2.7 $W_P$或3.2+/-6.5%),并提出了一个类激活图的变体来获得模型预测的每个单元的功率损耗。通过这项工作,我们的目标是开辟一个新的研究课题。因此,我们公开发布数据集,代码和训练模型,以使其他研究人员能够与我们的结果进行比较。最后,我们对某些边界条件进行了全面评估,例如数据集大小和现场测量的自动预处理管道,同时显示多个模块。

英文摘要:

Automated inspection plays an important role in monitoring large-scale photovoltaic power plants. Commonly, electroluminescense measurements are used to identify various types of defects on solar modules but have not been used to determine the power of a module. However, knowledge of the power at maximum power point is important as well, since drops in the power of a single module can affect the performance of an entire string. By now, this is commonly determined by measurements that require to discontact or even dismount the module, rendering a regular inspection of individual modules infeasible. In this work, we bridge the gap between electroluminescense measurements and the power determination of a module. We compile a large dataset of 719 electroluminescense measurementsof modules at various stages of degradation, especially cell cracks and fractures, and the corresponding power at maximum power point. Here,we focus on inactive regions and cracks as the predominant type of defect. We set up a baseline regression model to predict the power from electroluminescense measurements with a mean absolute error of 9.0+/-3.7$W_P$ (4.0+/-8.4%). Then, we show that deep-learning can be used to train a model that performs significantly better (7.3+/-2.7$W_P$ or 3.2+/-6.5%) and propose a variant of class activation maps to obtain the per cell power loss, as predicted by the model. With this work, we aim to open a new research topic. Therefore, we publicly release the dataset, the code and trained models to empower other researchers to compare against our results. Finally, we present a thorough evaluation of certain boundary conditions like the dataset size and an automated preprocessing pipeline for on-site measurements showing multiple modules at once.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑