A wide range of defects, failures, and degradation can develop at different stages in the lifetime of photovoltaic modules. To accurately assess their effect on the module performance, these failures need to be quantified. Electroluminescence (EL) imaging is a powerful diagnostic method, providing high spatial resolution images of solar cells and modules. EL images allow the identification and quantification of different types of failures, including those in high recombination regions, as well as series resistance-related problems. In this study, almost 46,000 EL cell images are extracted from photovoltaic modules with different defects. We present a method that extracts statistical parameters from the histogram of these images and utilizes them as a feature descriptor. Machine learning algorithms are then trained using this descriptor to classify the detected defects into three categories: (i) cracks (Mode B and C), (ii) micro-cracks (Mode A) and finger failures, and (iii) no failures. By comparing the developed methods with the commonly used one, this study demonstrates that the pre-processing of images into a feature vector of statistical parameters provides a higher classification accuracy than would be obtained by raw images alone. The proposed method can autonomously detect cracks and finger failures, enabling outdoor EL inspection using a drone-mounted system for quick assessments of photovoltaic fields.
Electroluminescence (EL) imaging is a PV module characterization technique, which provides high accuracy in detecting defects and faults such as cracks, broken cells interconnections, shunts, among many others; furthermore, the EL technique is used extensively due to a high level of detail and direct relationship to injected carrier density. However, this technique is commonly practiced only indoors-or outdoors from dusk to dawn-because the crystalline silicon luminescence signal is several orders of magnitude lower than sunlight. This limits the potential of such a powerful technique to be used in utility scale inspections, and therefore the interest in the development of electrical biasing tools to make outdoor EL imaging truly fast and efficient. With the focus of quickly acquiring EL images in daylight, we present in this article a drone-based system capable of acquiring EL images at a framerate of 120 frames per second. In a single second during high irradiance conditions, this system can capture enough EL and background image pairs to create an EL PV module image that has sufficient diagnostic information to identify faults associated with power loss. The final EL images shown in this work reached representative quality SNRAVG of 4.6, obtained with algorithms developed in previous works. These drone-based EL images were acquired with global horizontal solar irradiance close to one sun in the plane of the array.
Causal inference is at the heart of empirical research in natural and social sciences and is critical for scientific discovery and informed decision making. The gold standard in causal inference is performing randomized controlled trials; unfortunately these are not always feasible due to ethical, legal, or cost constraints. As an alternative, methodologies for causal inference from observational data have been developed in statistical studies and social sciences. However, existing methods critically rely on restrictive assumptions such as the study population consisting of homogeneous elements that can be represented in a single flat table, where each row is referred to as a unit. In contrast, in many real-world settings, the study domain naturally consists of heterogeneous elements with complex relational structure, where the data is naturally represented in multiple related tables. In this paper, we present a formal framework for causal inference from such relational data. We propose a declarative language called CaRL for capturing causal background knowledge and assumptions, and specifying causal queries using simple Datalog-like rules. CaRL provides a foundation for inferring causality and reasoning about the effect of complex interventions in relational domains. We present an extensive experimental evaluation on real relational data to illustrate the applicability of CaRL in social sciences and healthcare.
Despite recent technological advances for Photovoltaic panels maintenance (Electroluminescence imaging, drone inspection), only few large-scale studies achieve identification of the precise category of defects or faults. In this work, Electroluminescence imaged modules are automatically split into cells using projections on the x and y axes to detect cell boundaries. Regions containing potential defects or faults are then detected using Hough transform combined with mathematical morphology. Care is taken to remove most of the bus bars or cell boundaries. Afterwards, 25 features are computed, focusing on both the geometry of the regions (e.g. area, perimeter, circularity) and the statistical characteristics of their pixel values (e.g. median, standard deviation, skewness). Finally, features are mapped to the ground truth labels with Support Vector Machine (RBF kernel) and Random Forest algorithms, coupled with undersampling and SMOTE oversampling, with a stratified 5folds approach for cross validation. A dataset of 982 Electroluminescence images of installed multi-crystalline photovoltaic modules was acquired in outdoor conditions (evening) with a CMOS sensor. After automatic blur detection, 753 images or 47244 cells remain to evaluate faults. All images were evaluated by experts in PV fault detection that labelled: Finger failures, and three types of cracks based on their respective severity levels (A, B and C). Our results based on 6 data series, yield using Support Vector Machine an accuracy of 0.997 and a recall of 0.274. Improving the region detection process will most likely allow improving the performance.
In the learning-to-match framework for causal inference, a parameterized distance metric is trained on a holdout train set so that the matching yields accurate estimated conditional average treatment effects. This way, the matching can be as accurate as other black box machine learning techniques for causal inference. We use a new learning-to-match algorithm called Matching-After-Learning-To-Stretch (MALTS) (Parikh et al., 2018) to study an observational dataset from the Atlantic Causal Inference Challenge. Other than providing estimates for (conditional) average treatment effects, the MALTS procedure allows practitioners to evaluate matched groups directly, understand where more data might need to be collected and gain an understanding of when estimates can be trusted.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.