Defects In Photovoltaic Modules Research Articles

Progress in Improving Photovoltaics Longevity

With the increase of photovoltaic (PV) penetration in the power grid, the reliability and longevity of PV modules are important for improving their payback period and reducing recycling needs. Although the performance of PV systems has been optimized to achieve a multi-fold increase in their electricity generation compared to ten years ago, improvements in lifespan have received less attention. Appropriate operation and maintenance measures are required to mitigate their aging. PV cells and modules are subject to various degradation mechanisms, which impact their long-term performance and reliability. Understanding these degradation processes is crucial for improving the lifetime and sustainability of solar energy systems. In this context, this review summarizes the current knowledge on key degradation mechanisms (intrinsic, extrinsic, and specific) affecting PV modules, as well as on-site and remote sensing methods for detecting PV module defects and the mitigation strategies employed for enhancing their operational lifetime under different climatic conditions in the global environment.

High-noise solar panel defect identification method based on the improved EfficientNet-V2

As a crucial element in photovoltaic power generation systems, the condition of solar panels significantly impacts the efficiency of power generation. The ability to accurately and promptly detect defects in solar panels is essential for enhancing system performance. This study introduces a novel model for identifying defects in photovoltaic modules, leveraging an enhanced version of EfficientNet-V2. This model aims to address challenges in identifying defects in infrared images of solar panels under conditions of high-noise and low-model efficiency. To address the challenges of high image noise and blur, this article initially presents a methodology that combines the Db4 wavelet transform with a blind deconvolution algorithm for comprehensive preprocessing of the original image. Furthermore, this study optimizes the model's feature representation capabilities by implementing key transformations within the EfficientNet-V2 network framework. Notably, we replaced the traditional SE block with the more efficient channel attention (ECA) mechanism module. Due to its lightweight structure and effective performance, ECA substantially improves the model's capacity to extract complex and abstract image features, while also accelerating the training process's convergence speed and enhancing overall computational efficiency. At the classifier level, this paper innovatively integrates the XGBoost ensemble learning algorithm into the model, substituting the conventional softmax classifier used in traditional convolutional neural network (CNN). With its superior generalization capabilities, robust nonlinear modeling skills, and efficient computational characteristics, XGBoost can more accurately detect minute defects in solar panels based on the deep features produced by EfficientNet-V2, thereby significantly improving the accuracy and robustness of defect detection. Simulation results demonstrate that the proposed model structure outperforms traditional CNN models in terms of accuracy and stability, underscoring the efficacy of the enhanced EfficientNet-V2 model in detecting solar panel defects under high-noise conditions.

Cell-Resolved PV Soiling Measurement Using Drone Images

The maintenance of photovoltaic (PV) power plants is of central importance for their yield. To reach higher efficiencies in PV parks, it is helpful to detect soiling such as dust deposition and to apply this information to optimize cleaning strategies. Furthermore, a periodic inspection of the PV modules with infrared (IR) imagery is of advantage to detect and potentially remove faulty PV modules. Soiling can be erroneously interpreted as PV module defects and hence spatially resolved soiling measurements can improve the results of IR-based PV inspection. So far, soiling measurements are mostly performed only locally in PV fields, thus not supporting the above-mentioned IR inspections. This study presents a method for measuring the soiling of PV modules at cell resolution using RGB images taken by aerial drones under sunny conditions. The increase in brightness observed for soiled cells under evaluation, compared to clean cells, is used to calculate the transmission loss of the soiling layer. Photos of a clean PV module and a soiled module for which the soiling loss is measured electrically are used to determine the relation between the brightness increase and the soiling loss. To achieve this, the irradiance at the time of the image acquisitions and the viewing geometry are considered. The measurement method has been validated with electrical measurements of the soiling loss yielding root mean square deviations in the 1% absolute range. The method has the potential to be applied to entire PV parks in the future.

Defect detection of photovoltaic modules based on improved VarifocalNet

Detecting and replacing defective photovoltaic modules is essential as they directly impact power generation efficiency. Many current deep learning-based methods for detecting defects in photovoltaic modules focus solely on either detection speed or accuracy, which limits their practical application. To address this issue, an improved VarifocalNet has been proposed to enhance both the detection speed and accuracy of defective photovoltaic modules. Firstly, a new bottleneck module is designed to replace the first bottleneck module of the last stage convolution group in the backbone. This new module includes both standard convolution and dilated convolution, enabling an increase in network depth and receptive field without reducing the output feature map size. This improvement can help to enhance the accuracy of defect detection for photovoltaic modules. Secondly, another bottleneck module is also designed and used to replace the original bottleneck module used in the fourth stage convolution group of the backbone. This new module has smaller parameters than the original bottleneck module, which is useful to improve the defect detection speed of the photovoltaic module. Thirdly, a feature interactor is designed in the detection head to enhance feature expression in the classification branch. This helps improve detection accuracy. Besides, an improved intersection over union is proposed and introduced into the loss function to measure the difference between the predicted and ground truth boxes. This is useful for improving defect detection accuracy. Compared to other methods, the proposed method has the highest detection accuracy. Additionally, it also has a faster detection speed than other methods except for the DDH-YOLOv5 method and the improved YOLOv7 method.

Bird Droppings Defects Detection in Photovoltaic Modules Based on CA-YOLOv5

Due to the characteristics of different forms and small bird droppings-related defects in photovoltaic modules, problems of missing detection, wrong detection, and low detection accuracy often exist in the bird droppings covering the detection of photovoltaic modules. In this paper, a defect identification method based on the improved Coordinate Attention—You Only Look Once (CA-YOLOv5) network is proposed. Firstly, a layer of the Coordinate Attention module is added between the Backbone and Neck network, which takes into account channel and location information to enhance the feature extraction ability of the network model. Secondly, the small target detection layer is added to fuse different feature information from shallow networks and deep networks so as to improve the multi-scale feature detection ability of the network structure and effectively improve the detection effect of small targets. Finally, the experimental results show that, compared with the original algorithm, the proposed improved algorithm based on YOLOv5s has a mean average precision (mAP) value of 92%, an increase of 5.2%, and the model volume is also reduced in different degrees compared with other mainstream algorithms, achieving a good balance between detection accuracy and model volume. The results show that the model has a more accurate detection result for the bird droppings-related defect detection of photovoltaic modules and can provide a reference for the detection of photovoltaic modules in real life.

Detection and classification of photovoltaic module defects based on artificial intelligence

Photovoltaic (PV) system performance and reliability can be improved through the detection of defects in PV modules and the evaluation of their effects on system operation. In this paper, a novel system is proposed to detect and classify defects based on electroluminescence (EL) images. This system is called Fault Detection and Classification (FDC) and splits into four modules, which are (1) Image Preprocessing Module (IPM), (2) Feature Extraction Module (FEM), (3) Feature Selection Module (FSM), and (4) Classification Module (CM). In the first module (i.e., IPM), the EL images are preprocessed to enhance the quality of the images. Next, the two types of features in these images are extracted and fused together through FEM. Then, during FSM, the most important and informative features are extracted from these features using a new feature selection methodology, namely, Feature Selection-based Chaotic Map (FS-CM). FS-CM consists of two stages: filter stage using chi-square to initially select the most effective features and a modified selection stage using an enhanced version of Butterfly Optimization Algorithm (BOA). In fact, BOA is a popular swarm-based metaheuristic optimization algorithm that has only recently found success. While BOA has many benefits, it also has some drawbacks, including a smaller population and an increased likelihood of getting stuck in a local optimum. In this paper, a new methodology is proposed to improve the performance of BOA, called chaotic-based butterfly optimization algorithm. Finally, these selected features are used to feed the proposed classification model through CM. During CM, Hybrid Classification Model (HCM) is proposed. HCM consists of two stages, which are binary classification stage using Naïve Bayes (NB) and multi-class classification stage using enhanced multi-layer perceptron. According to the experimental results, the proposed system FDC outperforms the most recent methods. FDC introduced 98.2%, 89.23%, 87.2%, 87.9%, 87.55%, and 88.20% in terms of accuracy, precision, sensitivity, specificity, g-mean, and f-measure in the same order.

Optical Filter Design for Daylight Outdoor Electroluminescence Imaging of PV Modules

This paper presents an advanced outdoor electroluminescence (EL) imaging system for inspecting solar photovoltaic (PV) modules under varying daylight conditions. EL imaging, known for its effectiveness in non-destructively detecting PV module defects, is enhanced through specialized optical filters. These filters, including a bandpass filter targeting EL emissions and a neutral density filter to reduce background light, significantly improve the system’s signal-to-noise ratio (SNR). The experimental results demonstrate the system’s enhanced performance, with superior clarity and detail in EL emissions, enabling precise defect localization and characterization at the cellular level. Notably, the system achieves an SNR improvement, with values consistently above two, outperforming previous systems and confirming its suitability for efficient solar PV maintenance and diagnostics. This research offers a flexible approach to optimizing EL imaging quality across various solar irradiance levels and angles, essential for improved PV module performance and reliability. The system effectively handles different PV module configurations, orientations, and types, including monofacial and bifacial arrays. It showcases robust imaging capabilities under high solar irradiance and different sun illumination levels, maintaining high-quality imaging due to its optimized filter design. Additionally, the system’s adaptability in detecting EL emissions from series-connected PV modules is highlighted, demonstrating its comprehensive evaluation capabilities for PV array performance.

Enhancing solar photovoltaic modules quality assurance through convolutional neural network-aided automated defect detection

Detecting cracks in solar photovoltaic (PV) modules plays an important role in ensuring their performance and reliability. The development of convolutional neural networks (CNNs) has introduced a game-changing dimension in the detection of defects in PV modules. This paper proposes an automated defect detection method for PV, by leveraging custom-designed CNN to accurately analyse electroluminescence (EL) images, identifying defects such as cracks, mini-cracks, potential induced degradation (PID), and shaded areas. The proposed system achieves a high level of validation accuracy of 98.07%, reducing manual inspection demands, enhancing quality standards, and saving costs. The system was validated in a case study for PV installations faulty with PID, where it identified all defective modules with a high degree of precision of 96.6%, surpassing existing methods. This methodology holds promise for revolutionizing PV industry quality control, improving module reliability, and supporting sustainable solar energy growth.

Higher accuracy detection strategy for electroluminescent defects in photovoltaic modules based on improved Yolov5

AbstractAt present, the domestic photovoltaic (PV) industry is developing rapidly. In order to improve the production efficiency of PV cells, a fast and accurate automatic detection model of PV modules’ defects that can be applied in the production line is essential. In this paper, based on the characteristics of significant differences in PV module defect size and a large number of fine defects, an improved defect detection algorithm based on Yolov5 is proposed. Thirteen mainstream defects are divided into two categories according to size, and a series‐connected detection network is constructed for a two‐stage detection. In order to better detect fine defects, this paper proposes the TR‐ResNet module, a residual module composed of the self‐attention, based on the self‐attention mechanism, to replace some fully convolutional residual modules (CNN‐ResNet module) in the Yolov5 backbone network. After testing, the Precision, Recall and mAP of the model are greatly improved and gained 0.904, 0.845, and 0.840. Moreover, the model performs well in stability detection, which can adapt to different production environments and quality requirements. The present study may make the detection work more efficient and improve productivity.

Monitoring of PV systems installed in an extremely hostile climate in southern Algeria: Performance evaluation extended to degradation assessment of various PV panel of single-crystalline technologies

Any photovoltaic (PV) system technology must have been experienced for at least a year to provide valuable information about its seasonal behavior, which requires knowledge of the effects of each component of the PV installation chain. An experimental bench of different PV pumping systems using different PV panels was tested, which these PV systems (PVSs) consist of many brands of single-crystalline silicon (sc-Si) based technologies, including three manufacturers: ET-M53675, Isofotón (I-75 and I-100). This paper used the SV (sophisticated verification) method of analyzing and evaluating PVS performances in detail, for which we have developed a process to achieve good accuracy calculation, intended to estimate their various losses. This method was applied to the databases collected between 2014 and 2020. The output of real energy relative to its installed energy for four PVS configurations is between 72.7 % and 93.6 %, and in some cases it goes down to 48.8 %. This experimental study was extended to assess the degradation rate (DR) of PV panels exposed for long periods in the Saharan environment. Results show that after 2.5 years of operation for the ET-M53675 panels that are newly installed keep the same peak power, while PV panels that have been in operation for between 8 and 10 years have lost between 14.2 % and 19.5 % of their initial power value for Isofotón I-100 and Isofotón I-75 modules, respectively. The installed power in the Isofotón I-100 modules that have operated for more than 14 years has degraded by 23.59 %. This study is an effort to check and assess the feasibility of PVSs and the defects in PV modules found in newer and older installations in a desert environment at real operating conditions to enrich the databases concerning the DR of the various PV panels in the various environments around the world.

Automatic detection, classification and localization of defects in large photovoltaic plants using unmanned aerial vehicles (UAV) based infrared (IR) and RGB imaging

This study aims to build a photovoltaic (PV) plant maintenance and operation system, using an unmanned aerial vehicle (UAV) carrying a thermal imager to take images. In the proposed system, the infrared (IR) image was used for detecting PV module thermal defects, and the RGB image was used for detecting module surface defects. The two images were employed to cross validate the causes for module defects.In Part I, the PV plant information pattern was created, and the Taiwan PV plant (1,482 PV modules, 410 kW) was taken as an example. The PV system image feature points were detected by using the Scale Invariant Feature Transform (SIFT), in order to solve the feature variation problems, such as image luminance, rotation, and zoom in/out. The same feature points of multiple local power plant images were matched. Afterwards, the optimal number of feature points was calculated by homography transformation and random sample consensus (RANSAC) to form the PV plant panorama by image stitching. The PV plant panorama background noise was removed by image hue. The module segmentation of PV systems was performed by using image luminance, and the PV module was geometrically reconstructed by using morphology. The PV module edge contour was extracted by the Laplace operator to obtain the perimeter, area, and centroid features. The quantity and positions of PV modules were recognized and calculated to form the PV plant information pattern. In Part II, the PV module defect recognition and classification system was built. The defects in seven PV plants in Taiwan were collected, and the image features were enhanced using a convolutional neural network (CNN). Besides using the convolution layer to capture the image features, Max Pooling and local response normalization were used to enhance the image features. Color space transform was used to intensify the color features, increase the accuracy of the classification modules, and recognize and position the PV module defects. The IR image hot spot recognition accuracy was 100%. The classification accuracy of eight modules, including one normal module and seven defect modules, is 97.52%. The classification accuracy of six modules, including the appearances of one normal module and five defects in RGB images, is 99.17%. The classification accuracy of 14 defects in IR thermal images and RGB images is 97.52%. The causes of defects were cross validated by IR thermal image and RGB image. This study applied the K-fold cross validation to select the optimal model, and the recognition time of one image was shorter than 0.3 s, which is lower than the camera time constant. The results show that the system is applicable to real-time detections. In Part III, the PV plant defect information pattern was created. The PV module with defects was labeled during detection, and the defects in the power plant PV module and the positions thereof were obtained, which would be favorable for PV plant maintenance.

PSOPruner: PSO-Based Deep Convolutional Neural Network Pruning Method for PV Module Defects Classification

Photovoltaic (PV) modules can be damaged by external environment, which can significantly reduce power generation efficiency. Electroluminescent (EL) imaging is an economical and widely applied technique for PV module defects detection. The analysis of EL images, however, is still labor-consuming. To solve this problem, a deep convolutional neural network (DCNN) is proposed to automatically detect and classify defects. The proposed DCNN performs well on a large public EL dataset with more than 2600 images extracted from both monocrystalline and polycrystalline PV modules. Nevertheless, the proposed DCNN cannot be directly applied on portable or embedded devices due to its requirement of large-size memory and intensive computation. To handle this challenge, an evolutionary algorithm-based DCNN pruning method, dubbed PSOPruner, is further developed. The pruning problem of DCNN is formulated as a search problem, which is solved by particle swarm optimization (PSO) algorithm. To improve the quality of the pruning scheme, a tailored trick is considered that the automatic searching process with PSO algorithm is repeated for multiple rounds. To illustrate the effectiveness of the proposed PSOPruner, we compare it with mainstream DCNNs and lightweight CNNs in terms of model complexity and model accuracy. Experimental results demonstrate that the proposed method could efficiently reduce the amount of model parameters with slight drop of accuracy.

A novel framework on intelligent detection for module defects of PV plant combining the visible and infrared images

Solar Photovoltaic (PV) industry has achieved rapid development in recent years. However, it is difficult and costly to detect the micro fault area in a large PV power plant due to environmental factors and missing data. Most faults can be detected by the infrared temperature measurement method, but the infrared camera characteristics constrain it. This paper proposed a novel framework, consisting of image acquirement, image segmentation, fault orientation and defect warning, to remedy the limitations for PV module defects. The visible and infrared PV array images are taken under the same conditions by a dual infrared camera at low altitudes. The deep learning methods, including the fifth version of You Only Look Once (YOLOv5) algorithm and Deep Residual Network (ResNet) algorithm, are introduced to this framework. Hence, this framework has strong capability to suit almost all brightness conditions, by the combination of image segmentation from visible images and fault location on infrared images. The results show that this framework dramatically improves the separation speed of photovoltaic array to 36 Fps and the accuracy of fault detection to 95% by infrared image marked with the segmented area.

75MW AC PV Module Field Anomaly Detection Using Drone-Based IR Orthogonal Images With Res-CNN3 Detector

In recent years, the use of solar photovoltaic (PV) technologies for generating electricity has gained much popularity due to their efficiency, cost-effectiveness, reliability and the need to reduce carbon emissions and air pollution levels around the world in order to control and limit global climate change. Drone-based inspection of Solar Plants is an efficient method to perform preventative and corrective maintenance on the Solar PV arrays installed in large-scale grid-connected Solar PV Plants. Quite a few studies have been made in detecting PV module anomalies from these drone-captured thermal images. The main challenge that most of the applied techniques and models in these studies experience is the capability to detect and localize various PV module defects with high and consistent confidence scores and accuracy. The efficiency and robustness of anomaly detection of these models are also reduced when the testing image scales vary. In this article, we propose the Res-CNN3 framework for defective PV modules region object detection. Res-CNN3 follows a bipartite process for defect regions detection to process the thermal delta of a thermal PV module image using a combination of concatenated CNNs and residual networks to identify whether the thermal image is characteristic of defect regions or not. Logistic regression is employed as the loss function whist the Selective Search (SS) algorithm is utilized to predict the regions of interest (RoI) of the input thermal images for PV module defect regions object detection. Several categories of experiments are performed on the consolidated dataset. The results of these experiments demonstrate that the proposed model surpasses the advanced benchmarked methods in accuracy and computing resource efficiency.

Cover Image

The cover image is based on the Research Article Deep learning-based automatic detection of multitype defects in photovoltaic modules and application in real production line by Yang Zhao et al., https://doi.org/10.1002/pip.3395.

Online Distributed Measurement of Dark I-V Curves in Photovoltaic Plants

The inspection techniques for defects in photovoltaic modules are diverse. Among them, the inspection with measurements using current–voltage (I-V) curves is one of the most outstanding. I-V curves, which can be carried under illumination or in dark conditions, are widely used to detect certain defects in photovoltaic modules. In a traditional way, these measurements are carried out by disconnecting the photovoltaic module from the string inside the photovoltaic plant. In this work, the researchers propose a methodology to perform online dark I-V curves of modules in photovoltaic plants without the need of disconnecting them from the string. For this, a combination of electronic boards in the photovoltaic modules and a bidirectional inverter are employed. The results are highly promising, and this methodology could be widely used in upcoming photovoltaic plants.

Deep learning‐based automatic detection of multitype defects in photovoltaic modules and application in real production line

AbstractAutomatic defect detection in electroluminescence (EL) images of photovoltaic (PV) modules in production line remains as a challenge to replace time‐consuming and expensive human inspection and improve capacity. This paper presents a deep learning‐based automatic detection of multitype defects to fulfill inspection requirements of production line. At first, a database composed of 5983 labeled EL images of defective PV modules is built, and 19 types of identified defects are introduced. Next, a convolutional neural network is trained on top‐14 defects, and the best model is selected and tested, achieving 70.2% mAP50 (mean average precision with at least 50% localization accuracy). Then, through analyzing an object detection‐based confusion matrix, recognition bias and detection compensation in missed defects that restrain the best model's mAP50 are discovered to be harmless to normal/defective module classification in real production line. Finally, after setting specific screen criteria for different types of defects, normal/defective module classification is conducted on additionally collected 4791 EL images of PV modules on 3 days, and the best model achieves balanced scores of 95.1%, 96.0%, and 97.3%, respectively. As a result, this method surely has a highly promising potential to be adopted in real production line.

Edge-Computing-Enabled Unmanned Module Defect Detection and Diagnosis System for Large-Scale Photovoltaic Plants

The power efficiency of photovoltaic (PV) modules is highly correlated with their health status. Under dynamically changing environments, PV defects could spontaneously form and develop into fatal faults during the daily operation of PV power plants. To facilitate defect detection with less human intervention, a nondestructive, contactless, and automatical visual inspection system with the help of unmanned aerial vehicles and edge computing is proposed in this article. During the processing of the incoming data stream, the system may collect some new, unknown, and unlabeled defects that have not been identified yet in the existing database. To distinguish them from the existing ones, a deep embedded restricted cluster algorithm is designed to identify the unknown and unlabeled PV module defects in an unsupervised manner. Limited by the resources of edge devices and the availability of images of PV defects for training, we developed an online solution combined with deep learning, data argumentation, and transfer learning to properly address the issues of running resource-hungry applications on edge devices and lack of training samples faced by the deep learning approaches used in the field. In addition, pointwise convolution layers are introduced into the network to reduce the parameters and the size of the model. With the reduction of the network depth of the deep convolutional neural network model and the features transferred from the learned defects, the resource consumption of our proposed approach is significantly reduced, and thus can be used on a wide range of edge devices to complete defect detection in a timely manner with high accuracy. The experimental results clearly demonstrate the practicality and effectiveness.

Detection of Typical Defects in Silicon Photovoltaic Modules and Application for Plants with Distributed MPPT Configuration

During their operational life, photovoltaic (PV) modules may exhibit various defects for poor sorting of electrical performance during manufacturing, mishandling during transportation and installation, and severe thermo-mechanical stresses. Electroluminescence testing and infrared thermographic imaging are the most common tests for checking these defects, but they are only economically viable for large PV plants. The defects are also manifested as abnormal electrical properties of the affected PV modules. For defect diagnosis, the appropriate parameters on their I-V curves are open circuit voltage, photo-generated current, series resistance, and the shunt resistance. The health of PV modules can be assessed by calculating these values and comparing them with the reference parameters. If these defects are diagnosed in time, the power loss is avoided and safety hazards are mitigated. This paper first presents a review of common defects in PV modules and then a review of the methods used to find the above-mentioned parameters during the normal PV operation. A simple approach to determine the resistances of the equivalent circuit is discussed. Finally, through a modification in an ordinary maximum power point tracking (MPPT) algorithm, information about the state of health of PV modules is obtained. This method is effective, especially if applied to submodule-integrated MPPT architectures.

Diagnosis of Photovoltaic (PV) Panel Defects Based on Testing and Evaluation of Thermal Image

Abstract Photovoltaic (PV) solar energy can only be economical if the PV module operates reliably for 25–30 years under field conditions. The PV module and it overall reliability can be radically affected by faults during the manufacturing process, in real field conditions, transportation, and installation. So, there is a need for diagnosing defects in PV modules to improve their reliability. Operating temperature plays the key role for improving the efficiency of PV panels. The temperature within the PV cell unevenly increases because of such defects in the cell. As such, it is very important to monitor the temperature and temperature distribution in PV panels in order to locate such defects. Infrared thermography (IRT) plays a major role in predictive and preventive maintenance of PV panels and can determine the severity of the problem. This article investigates the delamination, snail trails, and bubbled faults of PV panels using digital thermal image analysis and their feature extraction. Real time experiments were conducted, and the test results are presented in this article. Thermal images of panels are captured using a (FLIR) T420bx® thermal imager. The thermal images of panels are analyzed by segmenting the image using the k-means clustering algorithm. Histogram statistical features such as mean, standard deviation, variance, entropy, skew, and kurtosis are extracted from the segmented thermal image. Based on these features, the defects in PV panels are identified with reasonable accuracy.