Solar panels play a crucial role in producing renewable electricity power for the grid, and this role grows more significant each year. However, defects in solar panels can significantly drop power output, leading to grid instability. Therefore, employing an efficient Artificial Intelligence (AI) algorithm to autonomously detect defects in solar panels is crucial. In this study, we employ the You Only Look Once (YOLO) v9, v10, and v11 algorithms to detect defects in solar panels. To this end, we examined their performance results via training on three datasets. The first dataset includes 191 thermal images with an image size of 200 × 160 pixels to identify a cell, multi-cell levels, and shadow defects. The second dataset consists of 792 optical images of solar panels with an image size of 244 × 244 to identify dust, snow, bird droppings, physical damage, and electrical defects. The third dataset includes 316 thermal images with an image size of 200 × 160 pixels, an enhanced version of the first dataset. Moreover, we examined the training and test performance results of YOLO v5, v9, v10, and v11. We achieved improved performance in detecting defects in solar panels compared to existing solutions by using the YOLO v10 and v11 algorithms. Additionally, we compared their performance results against Support Vector Machine (SVM) and Faster Region-based Convolutional Neural Network (R-CNN) to demonstrate the efficiency of the YOLO v10 algorithm. In conclusion, YOLO v11-X delivered the best performance among the algorithms tested. It reached a precision rate, recall rate, mean average precision, and F1 score of about 89.7%, 87.7%, 92.7%, and 90%, respectively.

Solar panels are an environmentally friendly alternative to fossil fuels; however, their useful life is limited to approximately 25 years, after which they become a waste management issue. Proper management and recycling of end-of-life (EOL) solar panels are paramount. It protects the environment because of the high energy consumption of silicon production. We can effectively decrease energy and cost requirements by recovering silicon from recycled solar panels. This is one-third of those needed for manufacturing silicon directly. Moreover, solar panels include heavy metals, such as lead, tin, and cadmium, which pose risks to human health and the environment. Empirical evidence suggests that the costs of mining materials can exceed those of recycled materials, thereby making recycling a more cost-effective means of resource harvesting. This review paper focuses on the techniques developed to delaminate solar panels, which are considered a crucial step in the recycling of EOL solar panels. Initially, various classifications of solar panels are given. Subsequently, an analysis of the diverse methods of solar panel delamination and their efficacy in the retrieval of valued materials is presented. This investigation has identified three primary modes of delamination, namely mechanical, thermal, and chemical. Among these, mechanical delamination is deemed to be a sustainable and cost-effective option when compared to thermal and chemical delamination. The current most popular method of thermal delamination is characterized by its high energy consumption and potential emission, and the chemical delamination generates hazardous liquids that pose their own threat to the environment. This study emphasizes the mechanical delamination techniques, characterized by their environmentally friendly nature, minimal ecological footprint, and capacity to retrieve entire glass panels intact. This paper also discusses the current gaps and potential enhancements for mechanical delamination techniques. For example, some delamination techniques result in crushed materials. Thus, the handling and recovery of materials such as glass and silicon cells require the implementation of an appropriate sorting technique. Also, the value obtained from recovering crushed materials is lower than that of intact glass and silicon cells.

While using multirotor UAVs for transport of suspended payloads, there is a need for stability along the desired path, in addition to avoidance of any excessive payload oscillations, and a good level of precision in maintaining the desired path of the vehicle. However, due to the nonlinear and underactuated nature of the system, in addition to the presence of mismatched uncertainties, the development of a control system for this application poses an interesting research problem. This paper proposes a control architecture for a multirotor slung load system by integrating a Multi-Surface Sliding Mode Control, aided by a Radial Basis Function Neural Network, with a Deep Q-Network Reinforcement Learning agent. The former will be used to ensure asymptotic tracking stability, while the latter will be used to suppress payload oscillations. First, we will present the dynamics of a multirotor slung load system, represented here as a quadrotor with a single pendulum load suspended from it. We will then propose a control method in which a multi-surface sliding mode controller, based on an adaptive RBF Neural Network for trajectory tracking of the quadrotor, works in tandem with a Deep Q-Network Reinforcement Learning agent whose reward function aims to suppress the oscillations of the single pendulum slung load. Simulation results demonstrate the effectiveness and potential of the proposed approach in achieving precise and reliable control of multirotor slung load systems.

The estimation of soil wet bulk density (ρ_n) and dry bulk density (ρ_b) using the novel digital electromechanical system (DES) has provided information about important parameters for the assessment of soil quality and health with a direct application for agronomists. The evaluation of the DES performance is particularly appropriate for different tillage methods, mulching systems, and fertilizers used to increase soil fertility and productivity, but currently, there is a lack of information, particularly in the arid areas in underdeveloped countries. Therefore, the main aim of this study was the application of a novel digital electromechanical system (DES) to evaluate bulk density, wet (ρ_n) and dry (ρ_b), under different soil treatments according to the variations in thermal efficiencies (η_th), microwave penetration depths (M_DP), and specific energy consumption (Q_con) in an experimental area close to Baghdad (Iraq). The experimental design consisted of 72 plots, each 4 m². The agronomic practices included two different tillage systems (disc plough followed by a spring disk and mouldboard plough followed by a spring disk) and twelve treatments involving mulching plastic sheeting combined with fertilizers, to determine their effect on the measured soil ρ_n and ρ_b and the DES performance in different soils. The results indicated that soil ρ_n and ρ_b varied significantly with both the tillage systems and the mulching systems. As expected, the soil ρn and ρb, M_DP, and Q_con increased with an increase in the soil depth. Moreover, the tillage, soil mulching, and soil depth value significantly affected η_th and Q_con. A strong relationship was identified between the soil tillage and M_DP for different soil treatments, leading to the changes in soil ρ_b and the soil dielectric constant (ε’).