Automatic classification of defective photovoltaic module cells in electroluminescence images

Abstract

Electroluminescence (EL) imaging is a useful modality for the inspection of photovoltaic (PV) modules. EL images provide high spatial resolution, which makes it possible to detect even finest defects on the surface of PV modules. However, the analysis of EL images is typically a manual process that is expensive, time-consuming, and requires expert knowledge of many different types of defects.In this work, we investigate two approaches for automatic detection of such defects in a single image of a PV cell. The approaches differ in their hardware requirements, which are dictated by their respective application scenarios. The more hardware-efficient approach is based on hand-crafted features that are classified in a Support Vector Machine (SVM). To obtain a strong performance, we investigate and compare various processing variants. The more hardware-demanding approach uses an end-to-end deep Convolutional Neural Network (CNN) that runs on a Graphics Processing Unit (GPU). Both approaches are trained on 1,968 cells extracted from high resolution EL intensity images of mono-and polycrystalline PV modules. The CNN is more accurate, and reaches an average accuracy of 88.42 %. The SVM achieves a slightly lower average accuracy of 82.44 %, but can run on arbitrary hardware. Both automated approaches make continuous, highly accurate monitoring of PV cells feasible.

Photovoltaic defect classification through thermal infrared imaging using a machine learning approach

“…Two data augmentation techniques are proposed, horizontal and vertical flipping of images and 90°, 180°, and 270° image rotations. The choice of these data augmentation techniques is due to its widespread use in the literature as can be seen in Bartler et al, Deitsch et al, Pierdicca et al, and Chollet et al…”

“…Two data augmentation techniques are proposed, horizontal and vertical flipping of images and 90 , 180 , and 270 image rotations. The choice of these data augmentation techniques is due to its widespread use in the literature as can be seen in Bartler et al, 14 Deitsch et al, 15 Pierdicca et al, 17 and Chollet et al 26 In order to optimise the MobileNet and VGG-16 models, an experimental approach is used to find an optimiser that yields the highest classification accuracy. This study proposes the use of the stochastic gradient descent (SGD) and Adam optimiser to maximise classification accuracy.…”

Fast and Robust Detection of Solar Modules in Electroluminescence Images

“…In Sec. 5.2, we quantitatively compare the results of our approach with our reference method [2]. In addition, we show that our method robustly handles cases, where multiple modules are visible in the image or the module is perspectively distorted.…”

“…Vetter et al [12] proposed an object detection pipeline that consists of several stacked filters followed by a Hough transform to detect solar modules in noisy infrared thermography measurements. Recently, Deitsch et al [2] proposed a processing pipeline for solar modules that jointly detects the modules in an EL image, estimates the configuration (i. e., the number of rows and columns of cells), estimates the lens distortion and performs segmentation into rectified cell images. Their approach consists of a preprocessing step, where a multiscale vesselness filter [5] is used to extract ridges (separating lines between cells) and bus bars.…”

Weakly Supervised Segmentation of Cracks on Solar Cells Using Normalized Lp Norm

“…The dataset used for this work 1 consists of 2426 electroluminescence 8-bit grayscale images of solar cells with a resolution of 300 × 300 pixels per image [3,4,5]. These images were extracted from 44 different solar modules.…”