Explore the vast range of titles available.

Photovoltaic systems (PV) are increasingly recognized as fundamental to the worldwide adoption of renewable energy technologies. Nonetheless, the efficiency and longevity of solar panels can be compromised by various anomalies, ranging from physical defects to environmental impacts. Early and accurate detection of these anomalies is crucial for maintaining optimal performance and preventing significant energy losses. This study presents SolarAttnNet, a novel convolutional neural network (CNN) architecture with integrated channel and spatial attention mechanisms for solar panel anomaly detection. The proposed model addresses the critical need for automated detection systems, which are crucial for maintaining energy production efficiency and optimizing maintenance. This approach leverages attention mechanisms that emphasize the most relevant features within thermal and visual imagery, improving detection accuracy across multiple anomaly types. SolarAttnNet is evaluated on three distinct solar panel datasets, demonstrating its effectiveness through comprehensive ablation studies that isolate the contribution of each architectural component. Experimental results show that SolarAttnNet achieves superior performance compared to state-of-the-art methods, with accuracy improvements of 3.9% on the PV Systems-AD dataset (94.2% vs. 90.3%), 3.6% on the InfraredSolarModules dataset (92.1% vs. 88.5%), and 3.5% on the RoboflowAnomalies dataset (89.7% vs. 86.2%) compared to baseline ResNet-50. For challenging subtle anomalies like cell cracks and PID, the proposed model demonstrates even more significant improvements with F1-score gains of 4.8% and 5.4%, respectively. Ablation studies reveal that the channel attention mechanism contributes a 2.6% accuracy improvement while spatial attention adds 2.3% across datasets. This work contributes to advancing automated inspection technologies for renewable energy infrastructure, supporting more efficient maintenance protocols and ultimately enhancing solar energy production.

Power quality disturbances (PQDs) are major obstacles to maintaining the reliability and stability of electrical systems. This study introduces a new multi-scale deep learning method to classify PQDs, aiming to enhance the accuracy and efficiency of power quality (PQ) analysis and monitoring systems. By combining 1-D convolutional neural networks (CNNs) with an attention mechanism, this approach overcomes the limitations of traditional techniques. Moreover, varying-size convolutional layers allow for the direct learning of complex patterns and features from PQ signals. To address the challenge of limited labeled PQ datasets, this research utilizes an open-source dataset generator to create large-scale datasets with annotated PQDs. Through a comparison with existing models in the field, the superiority of the proposed CNN-based approach is evident, achieving an accuracy level of up to 99.49%. The results demonstrate promising classification performance in terms of simplicity and accuracy, highlighting the potential of this approach to improve PQ analysis and disturbance identification.

The accurate forecasting of CO2 emissions from power stations is critical for effective climate policy and the transition to sustainable energy systems. However, the complexity of power generation processes and the high dimensionality of operational data present significant challenges to traditional modeling approaches. This paper introduces a novel multi-stage framework that integrates advanced feature selection with explainable machine learning (XAI) to deliver high-accuracy forecasts of power station CO2 emissions while maintaining full model transparency. The proposed methodology comprises a three-stage feature selection process—combining filter, wrapper, and embedded methods—to systematically identify the most influential emission drivers from a large set of potential variables. The selected features are then used to train a suite of machine learning models, including XGBoost, Random Forest, LSTM, and SVR. The best-performing model, XGBoost, achieved a Root Mean Square Error (RMSE) of 28.5, a Mean Absolute Error (MAE) of 19.8, and a coefficient of determination (R2) of 0.96 on a real-world dataset. To address the “black-box” nature of these models, we employ SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations) to interpret the model’s predictions, providing granular insights into the key factors driving emissions. The results demonstrate that the proposed framework not only outperforms state-of-the-art forecasting models but also offers a clear, interpretable, and actionable tool for policymakers and plant operators to support CO2 reduction strategies. The novelty of this work lies in its unique combination of a multi-stage feature selection pipeline and a comprehensive XAI-based analysis, providing a robust and transparent solution for a critical environmental challenge.

Accurate segmentation of the sky region is crucial for various applications, including object detection, tracking, and recognition, as well as augmented reality (AR) and virtual reality (VR) applications. However, sky region segmentation poses significant challenges due to complex backgrounds, varying lighting conditions, and the absence of clear edges and textures. In this paper, we present a new hybrid fast segmentation technique for the sky region that learns from object components to achieve rapid and effective segmentation while preserving precise details of the sky region. We employ Convolutional Neural Networks (CNNs) to guide the active contour and extract regions of interest. Our algorithm is implemented by leveraging three types of CNNs, namely DeepLabV3+, Fully Convolutional Network (FCN), and SegNet. Additionally, we utilize a local image fitting level-set function to characterize the region-based active contour model. Finally, the Lattice Boltzmann approach is employed to achieve rapid convergence of the level-set function. This forms a deep Lattice Boltzmann Level-Set (deep LBLS) segmentation approach that exploits deep CNN, the level-set method (LS), and the lattice Boltzmann method (LBM) for sky region separation. The performance of the proposed method is evaluated on the CamVid dataset, which contains images with a wide range of object variations due to factors such as illumination changes, shadow presence, occlusion, scale differences, and cluttered backgrounds. Experiments conducted on this dataset yield promising results in terms of computation time and the robustness of segmentation when compared to state-of-the-art methods. Our deep LBLS approach demonstrates better performance, with an improvement in mean recall value reaching up to 14.45%.

The aim of this study is to design a control strategy for the angular rate (speed) of a DC motor by varying the terminal voltage. This paper describes various designs for the control of direct current (DC) motors. We derive a transfer function for the system and connect it to a controller as feedback, taking the applied voltage as the system input and the angular velocity as the output. Different strategies combining proportional, integral, and derivative controllers along with phase lag compensators and lead integral compensators are investigated alongside the linear quadratic regulator. For each controller transfer function, the step response, root locus, and Bode plot are analysed to ascertain the behaviour of the system, and the results are compared to identify the optimal strategy. It is found that the linear quadratic controller provides the best overall performance in terms of steady-state error, response time, and system stability. The purpose of the study that took place was to design the most appropriate controller for the steadiness of DC motors. Throughout this study, analytical means like tuning methods, loop control, and stability criteria were adopted. The reason for this was to suffice the preconditions and obligations. Furthermore, for the sake of verifying the legitimacy of the controller results, modelling by MATLAB and Simulink was practiced on every controller.

The accurate forecasting of CO[sub.2] emissions from power stations is critical for effective climate policy and the transition to sustainable energy systems. However, the complexity of power generation processes and the high dimensionality of operational data present significant challenges to traditional modeling approaches. This paper introduces a novel multi-stage framework that integrates advanced feature selection with explainable machine learning (XAI) to deliver high-accuracy forecasts of power station CO[sub.2] emissions while maintaining full model transparency. The proposed methodology comprises a three-stage feature selection process—combining filter, wrapper, and embedded methods—to systematically identify the most influential emission drivers from a large set of potential variables. The selected features are then used to train a suite of machine learning models, including XGBoost, Random Forest, LSTM, and SVR. The best-performing model, XGBoost, achieved a Root Mean Square Error (RMSE) of 28.5, a Mean Absolute Error (MAE) of 19.8, and a coefficient of determination (R[sup.2]) of 0.96 on a real-world dataset. To address the “black-box” nature of these models, we employ SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations) to interpret the model’s predictions, providing granular insights into the key factors driving emissions. The results demonstrate that the proposed framework not only outperforms state-of-the-art forecasting models but also offers a clear, interpretable, and actionable tool for policymakers and plant operators to support CO[sub.2] reduction strategies. The novelty of this work lies in its unique combination of a multi-stage feature selection pipeline and a comprehensive XAI-based analysis, providing a robust and transparent solution for a critical environmental challenge.

Purpose - Unified power flow controller (UPFC) and advanced static VAR compensator (ASVC) devices are now recognized as the most important flexible AC transmission systems (FACTS) devices. This paper aims to focus on this.Design methodology approach - The effects of the location of such installation FACTS devices are examined.Findings - The UPFC as a voltage regulator and ASVC devices applied to a non-linear load are modeled and analyzed. It was found that the optimum installation position for a UPFC device is at the sending end bus where wide range of receiver terminal line voltage and active power can be controlled. However, it was also found that the optimum installation position for an ASVC device is at the receiving end bus where a wide range of receiver terminal line voltage and active power can be controlled. In both cases, it was found that a wider range of reactive power could be controlled when the devices are installed closer to the receiving end bus.Originality value - Shows that the mid-point of a transmission line is the optimal location for some FACTS devices or reactive power support. The proof is based on a fixed receiving end voltage magnitude, which is practically not valid.

In recent years it has been illustrated that the Unified Power Flow Controller (UPFC) installation location plays an important role in effecting nonlinearly its steady state performance. A Pulse Width Modulation (PWM) based UPFC used as a voltage regulator is modeled and analyzed to investigate its optimal position in the transmission line. From the simulation results it is demonstration that by varying the modulation index of the device it can control the distribution of the active and reactive power flows. In addition, this paper deals with the definition and simulation of the control strategy of the closed-loop UPFC with a series compensation block when it operates as a terminal voltage regulator using Electromagnetic Transients Program (EMTP). The design and simulation of two types of digital controller strategies for the study system in this paper have been carried out. The dynamic performance in terms of speed stability, accuracy, robustness and simplicity of a PI controller with gain scheduling and a fuzzy logic controller have been tested and compared.

This study aimed to assess Jordanian pharmacists' knowledge of the human microbiome and the impact of their knowledge on their attitudes and practices toward antibiotics and probiotics. A self-administered survey was designed after reviewing the literature. Participants' demographics were collected, and questions to evaluate pharmacists' knowledge, attitudes, and practices toward antibiotic and probiotic dispensing were asked. The data were analyzed using the Statistical Package for the Social Sciences V.26. Pearson correlations and one-way ANOVA were employed to calculate the significance of knowledge, attitudes, and practices. Statistical significance was considered at p < 0.05. Of the 333 respondents, around 75% (n=250) had a high level of general knowledge regarding the human gut microbiome. Almost equal proportions of participants had either intermediate or high levels of knowledge about the role of gut bacteria in health (n=164, 49.2%) (n=166, 49.8%), respectively, while almost two-thirds had an intermediate level of knowledge of the role of gut bacteria in disease (n=197, 59.2%). More than half of the participants had a positive attitude toward antibiotics, probiotics, and the human microbiome (n=179, 53.8%), and the majority (n=239, 71.8%) had an intermediate level of practice with them. There was a significant positive correlation between pharmacists' general knowledge of the human microbiome and their positive attitudes ( =0.306, p < 0.01) and practices ( =0.331, p < 0.01) toward antibiotics and probiotics. Study results raise the importance of interventional educational measures to promote healthcare professionals' knowledge of the human microbiome and their potential beneficence on pharmacists' attitudes and practices regarding antibiotics and probiotics dispensing. The results also denote the urgent need for probiotics' clinical guidelines to ensure practice uniformity.