Explore the vast range of titles available.

Early fault detection and diagnosis of grid-connected photovoltaic systems (GCPS) is imperative to improve their performance and reliability. Low-cost edge devices have emerged as innovative solutions for real-time monitoring, reducing latency, and improving response times. In this work, a lightweight Convolutional Neural Network (CNN) is designed and fine-tuned using Energy Valley Optimizer (EVO) for fault diagnosis. The CNN input consists of two-dimensional scalograms generated using Continuous Wavelet Transform (CWT). The proposed diagnosis technique demonstrated superior performance compared to benchmark architectures, namely MobileNet, NASNetMobile, and InceptionV3, achieving higher test accuracies and lower losses on binary and multi-fault classification tasks on balanced, unbalanced, and noisy datasets. Further, a quantitative comparison is conducted with similar recent studies. The obtained results indicate good performance and high reliability of the proposed fault diagnosis method.

In this study, we present a comparative analysis of various trajectory optimization algorithms for Unmanned Aerial Vehicles (UAVs) navigating complex environments. The performance of the proposed FOPID-TID based HAOAROA (Hybrid Archimedes Optimization Algorithm-Rider Optimization Algorithm) is evaluated against traditional methods such as A*, JPS, Bezier, and L-BSGF algorithms. The FOPID-TID based HAOAROA approach integrates the advantages of fractional-order control with hybrid optimization techniques to improve UAV trajectory planning. Simulation results indicate that the proposed method carries significantly better performance than the traditional algorithms with respect to trajectory length, smoothness, and overall stability. Remarkably, the FOPID-TID based HAOAROA yields a 10% reduced trajectory length that is smoother than traditional methods while also being more computationally efficient. By using fractional-order parameters, the dynamic response becomes better and better in more challenging environments. This shows that disturbance rejection and control precision using the FOPID-TID based HAOAROA are much superior to the original two subroutines. The applications presented in this study allow future growth in UAV control system improvements and provide proof of concept of hybrid optimization in improving the performance of UAVs in dynamic, complex environments.

An automotive supply chain includes a range of activities from the concept of the product to its final transfer to a customer and subsequent vehicle maintenance. The three distinct stages of this chain are production, sales, and maintenance. In many countries, automobile records are not available to the public and anyone who has access to the central database or government systems can tamper with these records. In addition, used vehicle maintenance and transfer histories remain unavailable or inaccessible. These issues can be overcome by incorporating state-of-the-art blockchain technology into automotive supply chain management. Blockchain technology uses a chain of blocks for distributed transfer and storage of information, creating a decentralized data register that makes records of any digital asset tamper-proof and transparent. In this paper, we implement a permissioned blockchain-based framework for secure and efficient supply chain management of the automobile industry. We employed Hyperledger Fabric; an enterprise-grade distributed ledger platform for developing solutions. In our solution, the blockchain is customized and private in order to ensure system security. We evaluated our system in terms of memory cost, monetary cost, and speed of execution. Our results demonstrate that only 346 MB of extra memory space is required for storing the automotive data of 1 million users, thus rendering the memory cost negligible. The monetary cost is insignificant as all open source blockchain resources are employed, and the speed of record update is also fast. Our results also show that the decentralization of the automotive supply chain using blockchain can implement system security with minor modifications in the established configuration of the web application database.

Weather recognition is crucial due to its significant impact on various aspects of daily life, such as weather prediction, environmental monitoring, tourism, and energy production. Several studies have already conducted research on image-based weather recognition. However, previous studies have addressed few types of weather phenomena recognition from images with insufficient accuracy. In this paper, we propose a transfer learning CNN framework for classifying air temperature levels from human clothing images. The framework incorporates various deep transfer learning approaches, including DeepLabV3 Plus for semantic segmentation and others for classification such as BigTransfer (BiT), Vision Transformer (ViT), ResNet101, VGG16, VGG19, and DenseNet121. Meanwhile, we have collected a dataset called the Human Clothing Image Dataset (HCID), consisting of 10,000 images with two categories (High and Low air temperature). All the models were evaluated using various classification metrics, such as the confusion matrix, loss, precision, F1-score, recall, accuracy, and AUC-ROC. Additionally, we applied Gradient-weighted Class Activation Mapping (Grad-CAM) to emphasize significant features and regions identified by models during the classification process. The results show that DenseNet121 outperformed other models with an accuracy of 98.13%. Promising experimental results highlight the potential benefits of the proposed framework for detecting air temperature levels, aiding in weather prediction and environmental monitoring.

A dual-band, compact, high-gain, simple geometry, wideband antenna for 5G millimeter-wave applications at 28 and 38 GHz is proposed in this paper. Initially, an antenna operating over dual bands of 28 and 38 GHz was designed. Later, a four-port Multiple Input Multiple Output (MIMO) antenna was developed for the same dual-band applications for high data rates, low latency, and improved capacity for 5G communication devices. To bring down mutual coupling between antenna elements, a parasitic element of simple geometry was loaded between the MIMO elements. After the insertion of the parasitic element, the isolation of the antenna improved by 25 dB. The suggested creation was designed using a Rogers/Duroid RT-5870 laminate with a thickness of 0.79 mm. The single element proposed has an overall small size of 13 mm × 15 mm, while the MIMO configuration of the proposed work has a miniaturized size of 28 mm × 28 mm. The parasitic element-loaded MIMO antenna offers a high gain of 9.5 and 11.5 dB at resonance frequencies of 28 GHz and 38 GHz, respectively. Various MIMO parameters were also examined, and the results generated by the EM tool CST Studio Suite® and hardware prototype are presented. The parasitic element-loaded MIMO antenna offers an Envelop Correlation Coefficient (ECC) < 0.001 and Channel Capacity Loss (CCL) < 0.01 bps/Hz, which are quite good values. Moreover, a comparison with existing work in the literature is given to show the superiority of the MIMO antenna. The suggested MIMO antenna provides good results and is regarded as a solid candidate for future 5G applications according to the comparison with the state of the art, results, and discussion.

There is increasing growth in load demands and financial strain to upgrade the present power distribution system. It faces challenges such as power losses, voltage deviations, lack of reliability and voltage instability. There is also a sense of responsibility in the wake of environmental and energy crises to adopt distributed renewable resources for power generation. These challenges can be resolved by optimally allocating distributed generators (DGs) at different suitable locations in the radial power distribution system. Optimal allocation is a non-linear problem which is solved by powerful metaheuristic optimization algorithms. In this work, an objective function is introduced to optimally size four different types of DGs by utilizing honey badger algorithm (HBA), and comparison is drawn with grey wolf optimization (GWO) and whale optimization algorithm (WOA). The objective is to boost the voltage profile and minimize the power losses of the standard IEEE 33bus and 69-bus radial power distribution system. It is observed from the simulation results that honey badger algorithm is faster than grey wolf optimization and whale optimization algorithm in reaching accurate and optimum results in a mere one and two iterations for IEEE 33-bus and 69-bus systems, respectively. Additionally, power losses are reduced to 71% and 70% for IEEE 33-bus and 69-bus, respectively.

Lightweight high-strength concrete (LWHSC) is increasingly used as a sustainable material that reduces structural weight while maintaining performance. Promoting sustainability involves using less high-carbon cement and more supplementary cementitious materials (SCMs) like fly ash, silica fume, and slag. However, testing LWHSC’s mechanical behavior is costly and time-consuming, highlighting the need for reliable prediction tools. To address this, this study employs machine learning models multi-expression programming (MEP) and random forest (RF) to forecast the mechanical properties of LWHSC containing SCMs using a large dataset with eight key parameters, including water-to-binder ratio, cement, fly ash, slag, silica fume, aggregate, lightweight aggregate, and basalt fiber. Performance was evaluated with R 2 , MAE, RMSE, and MSE. Both models captured strength trends, but MEP was more accurate, especially for compressive strength (R 2  = 0.98–0.99) versus RF (0.87–0.91), and similarly for tensile and flexural strengths. Errors mostly stayed below 3 MPa for CS, 0.5 MPa for TS, and 2 MPa for FS. Taylor diagrams confirmed MEP predictions closely matched experimental data. Additionally, SHapely Additive ExPlanations (SHAP) investigation demonstrated that the water-to-binder ratio and lightweight aggregate had a favorable impact on the mechanical properties of the LWHSC. The study highlights MEP as a robust, dependable tool for designing sustainable LWHSC by effectively combining SCMs with machine learning.

The construction industry continues to struggle with inefficiencies, high resource wastage, and persistent safety risks, which hinder progress toward sustainability and productivity goals. This study aims to investigate the functional impacts of hyperautomation an integration of AI, IoT, RPA, and machine learning on efficiency, sustainability, resource optimization, precision, scalability, and worker safety in construction projects. A structured questionnaire was developed from prior literature and expert insights, using a 5-point Likert scale to capture perceptions across six critical factors. Data were collected from 211 construction professionals, representing engineers, managers, safety officers, and architects. The responses were analysed using structural equation modelling (SEM), supported by reliability tests (Cronbach’s alpha, CR, AVE), discriminant validity checks (HTMT, Fornell–Larcker, cross-loadings), and multicollinearity diagnostics (VIF). Results indicate that streamlined processes and enhanced efficiency exert the strongest influence on hyperautomation adoption, followed by optimized resource management and sustainability goals, while precision, scalability, and worker safety also demonstrate significant but lesser effects. These findings extend theoretical understanding of digital transformation in construction by empirically validating hyperautomation’s multidimensional contributions and highlight practical pathways for improving sustainability, productivity, and safety outcomes. The novelty of this study lies in its comprehensive framework and empirical validation across multiple performance dimensions, offering actionable insights for both practitioners and policymakers to accelerate hyperautomation adoption in construction.

The unconvertible portion of incident radiation on solar panels causes an increase in their temperature and a decrease in efficiency due to the negative temperature coefficient of the maximum power. This problem is dealt with through the use of cooling systems to lower the temperature of photovoltaic (PV) panels. However, the developments are focused on the loss of efficiency or extract the heat out of the solar panel, rather than optimizing the solution to produce a net gain in the electric power output. Therefore, this study proposes the analytical model for the cell temperature, irradiance and design of absorbers. Furthermore, the cooling systems for the hybrid solar panels were developed through analytical modeling of the solar cell temperature behavior and heat exchange between the fluid and back surface of the PV module in MATLAB. The design parameters such as mass flow rate, input power, solar cell temperature, velocity, height, number of passes and maximum power output were optimized through a multi-objective, multivariable optimization algorithm to produce a net gain in the electrical power. Three layouts of heat absorbers were considered—i.e., single-pass ducts, multi-pass ducts, and tube-type heat absorbers. Water was selected as a cooling medium in the three layouts. The optimized results were achieved for the multi-pass duct with 31 passes that delivered a maximum power output of 186.713 W at a mass flow rate of 0.14 kg/s. The maximum cell temperature achieved for this configuration was 38.810 °C at a velocity of 0.092 m/s. The results from the analytical modeling were validated through two-way fluid-solid interaction simulations using ANSYS fluent and thermal modules. Analyses revealed that the multi-pass heat absorber reduces the cell temperature with the least input power and lowest fluid mass flow rate to produce the highest power output in the hybrid PV system.

The broad acceptance of sustainable and renewable energy sources as a means of integrating them into electrical power networks is essential to promote sustainable development. Microgrids using direct currents (DCs) are becoming more and more popular because of their great energy efficiency and straightforward design. In this work, we discuss the control of a PV-based renewable energy system and a battery- and supercapacitor-based energy storage system in a DC microgrid. We describe a hierarchical control approach based on sliding-mode controllers and the Lyapunov stability theory. To balance the load and generation, a fuzzy logic-based energy management system has been created. Using a neural network, maximum power defects for the PV system were determined. The global asymptotic stability of the framework has been verified using Lyapunov stability analysis. In order to simulate the proposed DC microgrid and controllers, MATLAB/SimulinkR (2019a) was utilized. The outcomes show that the system operates effectively with changing production and consumption.