/pdf/using-machine-learning-in-photovoltaics-to-create-smarter-e2fpozte.pdf

Using machine learning in photovoltaics to create smarter and cleaner energy generation systems: A comprehensive review

Methods of photovoltaic fault detection and classification: A review

The world’s energy consumption is outpacing supply due to population growth and technological advancements. For future energy demands, it is critical to progress toward a dependable, cost-effective, and sustainable renewable energy source. Solar energy, along with all other alternative energy sources, is a potential renewable resource to manage these enduring challenges in the energy crisis. Solar power generation is expanding globally as a result of growing energy demands and depleting fossil fuel reserves, which are presently the primary sources of power generation. In the realm of solar power generation, photovoltaic (PV) panels are used to convert solar radiation into energy. They are subjected to the constantly changing state of the environment, resulting in a wide range of defects. These defects should be discovered and remedied as soon as possible so that PV panels efficiency, endurance, and durability are not compromised. This paper focuses on five aspects, namely, (i) the various possible faults that occur in PV panels, (ii) the online/remote supervision of PV panels, (iii) the role of machine learning techniques in the fault diagnosis of PV panels, (iv) the various sensors used for different fault detections in PV panels, and (v) the benefits of fault identification in PV panels. Based on the investigated studies, recommendations for future research directions are suggested.

An Effective Evaluation on Fault Detection in Solar Panels

To ensure the continuity of electric power generation for photovoltaic systems, condition monitoring frameworks are subject to major enhancements. The continuous uniform delivery of electric power depends entirely on a well-designed condition maintenance program. A just-in-time task to deal with several naturally occurring faults can be correctly undertaken via the cooperation of effective detection, diagnosis, and prognostic analyses. Therefore, the present review first outlines different failure modes to which all photovoltaic systems are subjected, in addition to the essential integrated detection methods and technologies. Then, data-driven paradigms, and their contribution to solving this prediction problem, are also explored. Accordingly, this review primarily investigates the different learning architectures used (i.e., ordinary, hybrid, and ensemble) in relation to their learning frameworks (i.e., traditional and deep learning). It also discusses the extension of machine learning to knowledge-driven approaches, including generative models such as adversarial networks and transfer learning. Finally, this review provides insights into different works to highlight various operating conditions and different numbers and types of failures, and provides links to some publicly available datasets in the field. The clear organization of the abundant information on this subject may result in rigorous guidelines for the trends adopted in the future.

Machine Learning-Based Condition Monitoring for PV Systems: State of the Art and Future Prospects

The increasing adoption of photovoltaic (PV) technology highlights the need for efficient and large-scale deployment-ready inspection solutions. In the thermal infrared imagery-based inspection framework, we develop a robust and versatile deep learning model for the classification of defect-related patterns on PV modules. The model is developed from big UAV imagery data, and designed as a layer-3 building block that can be implemented on top of any two-stage PV inspection workflow comprising: (1) An aerial Structure from Motion – MultiView Stereo (SfM-MVS) photogrammetric acquisition/processing stage, at which a georeferenced thermal orthomosaic of an inspected PV site is generated, and which enables to locate precisely defective modules on field; then (2) an instance segmentation stage that extracts the images of modules. Orthomosaics from 28 different PV sites were produced, comprising 93 220 modules with various types, layouts and thermal patterns. Modules were extracted through a developed semi-automatic workflow, then labeled into six classes. Data augmentation and balancing techniques were used to prepare a highly representative and balanced deep learning-ready dataset. The dataset was used to train, cross-validate and test the developed classifier, as well as benchmarking with the VGG16 architecture. The developed model achieves the state-of-art performance and versatility on the addressed classification problem, with a mean F1-score of 94.52%. The proposed three-layer solution resolves the issues of conventional imagery-based workflows. It ensures highly accurate and versatile defect detection, and can be efficiently deployed to real-world large-scale applications. 

Developing a deep learning-based layer-3 solution for thermal infrared large-scale photovoltaic module inspection from orthorectified big UAV imagery data

Photovoltaic (PV) modules are generally considered to be the most reliable components of PV systems. The PV module has a high probability of being able to perform adequately for 30 years under typical operating conditions. In order to evaluate the long-term performance of a PV module under diversified terrestrial conditions, outdoor-performance data should be used. However, this requires a wait of 25 years to determine the module reliability, which is highly undesirable. Thus, accelerated-stress tests performed in the laboratory by mimicking different field conditions are important for understanding the performance of a PV module. In this paper, we discuss PV-module degradation types and different accelerated-stress types that are used to evaluate the PV-module reliability and durability for life expectancy before using them in the real field. Finally, prevention and correction measures are described to minimize economic losses.

A Review of the Degradation of Photovoltaic Modules for Life Expectancy

https://www.koreascience.or.kr:443/article/JAKO202028851206913.pdf

A Review on Floating Photovoltaic Technology (FPVT)

The tunnel oxide passivated contact (TOPCon) structure got more consideration for development of high performance solar cells by the introduction of a tunnel oxide layer between the substrate and poly-Si is best for attaining interface passivation. The quality of passivation of the tunnel oxide layer clearly depends on the bond of SiO in the tunnel oxide layer, which is affected by the subsequent annealing and the tunnel oxide layer was formed in the suboxide region (SiO, Si2O, Si2O3) at the interface with the substrate. In the suboxide region, an oxygen-rich bond is formed as a result of subsequent annealing that also improves the quality of passivation. To control the surface morphology, annealing profile, and acceleration rate, an oxide tunnel junction structure with a passivation characteristic of 700 mV or more (Voc) on a p-type wafer could achieved. The quality of passivation of samples subjected to RTP annealing at temperatures above 900°C declined rapidly. To improve the quality of passivation of the tunnel oxide layer, the physical properties and thermal stability of the thin layer must be considered. TOPCon silicon solar cell has a boron diffused front emitter, a tunnel-SiOx/n + poly-Si/ SiNx:H structure at the rear side, and screen-printed electrodes on both sides. The saturation currents Jo of this structure on polished surface is 1.3 fA/cm 2 and for textured silicon surfaces is 3.7 fA/cm 2 before printing the silver contacts. After printing the Ag contacts, the Jo of this structure increases to 50.7 fA/cm 2 on textured silicon surfaces, which is still manageably less for metal contacts. This structure was applied to TOPCon solar cells, resulting in a median efficiency of 23.91%, and a highest efficiency of 24.58%, independently. The conversion efficiency of interdigitated back-contact solar cells has reached up to 26% by enhancing the optoelectrical properties for both-sides-contacted of the cells.

A Review on TOPCon Solar Cell Technology

A 60-cell photovoltaic (PV) module was analyzed by optimizing the interconnection parameters of the solar cells to enhance the efficiency and increase the power of the PV module setup. The cell-to-module (CTM) losses and gains varied substantially during the various simulation iterations. Optimization was performed to inspect and augment the gain and loss parameters for the 60-cell PV module. The power and efficiency of the module were improved by refining several parameters, such as number of busbars, size of the contact pads, interconnected ribbon width, thickness of the core, and distance between the solar cells and strings, to obtain the maximum efficiency of 21.09%; the CTM efficiency achieved was 94.19% for the proposed strategy related to the common interconnection setup of the ribbon-based system. The CTM efficiency was improved by optimizing the geometrical, optical, and electrical parameters precisely, the power enhancement was up to 325.3 W, and a CTM power of 99.1% was achieved from a standard PV module with rectangular ribbon interconnections.

/pdf/cell-to-module-simulation-analysis-for-optimizing-the-f1ph0acy.pdf

Cell-to-Module Simulation Analysis for Optimizing the Efficiency and Power of the Photovoltaic Module

In addition to the different technologies of silicon solar cells in crystalline form, TOPCon solar cells have an exceptionally great efficiency of 26%, accomplished by the manufacturing scale technique for industrialization, and have inordinate cell values of 732.3 mV open-circuit voltage (Voc) and a fill factor (FF) of 84.3%. The thickness of tunnel oxide, which is less than 2 nm in the TOPCon cell, primarily affects the electrical properties and efficiency of the cell. In this review, various techniques of deposition were utilized for the layer of SiOx tunnel oxide, such as thermal oxidation, ozone oxidation, chemical oxidation, and plasma-enhanced chemical vapor deposition (PECVD). To monitor the morphology of the surface, configuration of annealing, and rate of acceleration, a tunnel junction structure of oxide through a passivation quality of better Voc on a wafer of n-type cell might be accomplished. The passivation condition of experiments exposed to rapid thermal processing (RTP) annealing at temperatures more than 900 °C dropped precipitously. A silicon solar cell with TOPCon technology has a front emitter with boron diffusion, a tunnel-SiOx/n+-poly-Si/ SiNx:H configuration on the back surface, and electrodes on both sides with screen printing technology. The saturation current density (J0) for such a configuration on a refined face remains at 1.4 fA/cm2 and is 3.8 fA/cm2 when textured surfaces of the cell are considered, instead of printing with silver contacts. Following the printing of contacts with Ag, the J0 of the current configuration improves to 50.8 fA/cm2 on textured surface of silicon, which is moderately lesser for the metal contact. Tunnel oxide layers were deposited using many methods such as chemical, ozone, thermal, and PECVD oxidation are often utilized to deposit the thin SiOx layer in TOPCon solar cells. The benefits and downsides of each approach for developing a SiOx thin layer depend on the experiment. Thin SiOx layers may be produced using HNO3:H2SO4 at 60 °C. Environmentally safe ozone oxidation may create thermally stable SiOx layers. Thermal oxidation may build a tunnel oxide layer with low surface recombination velocity (10 cm/s). PECVD oxidation can develop SiOx on several substrates at once, making it cost-effective.

/pdf/tunnel-oxide-deposition-techniques-and-their-parametric-7eas3rpq.pdf

Hasnain Yousuf

Papers

A Review of the Degradation of Photovoltaic Modules for Life Expectancy

A Review on Floating Photovoltaic Technology (FPVT)

A Review on TOPCon Solar Cell Technology

Cell-to-Module Simulation Analysis for Optimizing the Efficiency and Power of the Photovoltaic Module

Tunnel Oxide Deposition Techniques and Their Parametric Influence on Nano-Scaled SiOx Layer of TOPCon Solar Cell: A Review