Manufacturing, one of the most valuable industries in the world, is boundlessly automatable yet still quite stuck in traditionally manual and slow processes. Industry 4.0 is racing to define a new era of digital manufacturing through Internet of Things‐ (IoT‐) connected machines and factory systems, fully comprehensive data gathering, and seamless implementation of data‐driven decision‐making and action taking. Both academia and industry understand the tremendous value in modernizing manufacturing and are pioneering bleeding‐edge strides every day to optimize one of the largest industries in the world. IoT production, functional testing, and fault detection equipment are already being used in today’s maturing smart factory paradigm to superintend intelligent manufacturing equipment and perform automated defect detection in order to enhance production quality and efficiency. This paper presents a powerful and precise computer vision model for automated classification of defect product from standard product. Human operators and inspectors without digital aid must spend inordinate amounts of time poring over visual data, especially in high volume production environments. Our model works quickly and accurately in sparing defective product from entering doomed operations that would otherwise incur waste in the form of wasted worker‐hours, tardy disposition, and field failure. We use a convolutional neural network (CNN) with the Visual Geometry Group with 16 layers (VGG16) architecture and train it on the Printed Circuit Board (PCB) dataset with 3175 RBG images. The resultant trained model, assisted by finely tuned optimizers and learning rates, classifies defective product with 97.01% validating accuracy.

For WLAN/WIMAX applications, a brand-new tree-shaped metamaterial-loaded microstrip antenna is suggested. The reduced ground plane size and 4.4 dielectric constant (r) and 0.02 loss tangent (δ) dielectric are used to manufacture the 15×16×1.6mm³ microstrip antenna. Two X-shaped slots are added to achieve the characteristics needed for WIMAX applications at 5.5GHz. Additionally, a split-ring resonator is added to the structure to increase its bandwidth. It runs for WLAN applications with a center frequency of 5.8GHz. The proposed structures measured impedance bandwidth is 45.39 with SRR and 53.48 without SRR, respectively. The proposed antenna is capable of satisfying the major requirements of modern wireless devices such as multiband operation, compact size, large bandwidth, and planar structure. The best outcomes are attained with the aid of parametric analysis of feed width, ground height, and slot width. All electromagnetic simulations were performed using CST Studio software. The measured results and the simulation agree. The waveguide extraction approach is used to demonstrate the SRRs permeability property. The suggested antenna had adequate impedance matching, was small, and had a wide bandwidth.

The optimization of floating bifacial solar panels (FBS PV) in tropical freshwater systems is explored by employing response surface methodology (RSM) and central composite design (CCD). Previous studies have yet to explore the long-term durability, environmental impact, economic viability, and performance of FBS PV systems under various climatic conditions. This study addresses this gap by focusing on panel height, water depth, and tilt angle to improve performance. The quadratic model reveals significant non-linear relationships impacting FBS PV power generation with freshwater cooling. Our models demonstrate high explanatory power, with R-squared values of 0.9831 for output power and 0.9900 for Bi-Facial gain. Experimental validation using conventional white surface (CWS) and proposed freshwater surface (PFS) indicates notable improvements in power generation, achieving a 4.34 to 4.86% gain in bifacial efficiency across various irradiation levels. Under 950 W/m² irradiation, freshwater cooling achieves a 3.19% higher bifacial gain compared to CWS cooling. Panel temperature analysis shows consistent reductions with freshwater cooling, ranging from 1.43 to 2.72 °C, enhancing overall efficiency and longevity. This research highlights the potential of freshwater cooling in optimizing bifacial solar systems, offering actionable insights for sustainable energy solutions in tropical regions.

Background: Deep learning in brain tumor detection has become an important breakthrough in medical imaging to facilitate a fast and accurate diagnosis. Conventional models such as VGG, SVM, and common CNNs are competitive, yet fail to provide the sensitivity and specificity needed in real-time diagnosis purposes. Objectives: The objective of the proposed study is to generate a hybrid deep learning architecture of the DenseNet and a self-developed Convolutional Neural Network (CNN) in order to increase the classification accuracy, sensitivity, and specificity of a brain tumor detection medical image. Design: A Hybrid architecture consisting of DenseNet feature reuse and connectivity with a domain-specific custom CNN is suggested to retrieve high-level semantic and fine-grained features. The design focuses on performance evaluation with respect to the state-of-the-art models and ensemble frameworks. Methods: The brain tumor data set was preprocessed, and the augmentation methods, such as translation and rotation, were applied. A training and testing subsets of the dataset were formed. The hybrid approach, formed by DenseNet layers and a self-created CNN model, was implemented and tested. The performance of the model was contrasted with that of other benchmark classifiers such as SVM and VGG, DenseNet (single), CNN ensembles, and Hybrid Ensembles. Results: The hybrid DenseNet-Custom CNN model was more accurate and had better classification results than the standard models. In particular, it surpassed the accuracy of SVM (96%), VGG (94%), DenseNet (92%), and Hybrid Ensemble models (~95.2%), while the FPS remained equivalent to SVM and substantially lower than VGG. It proved better sensitivity and specificity with better feature representation and interpretation, as it made more accurate tumor classification. Conclusion: Incorporating DenseNet with a custom CNN model can increase the capabilities of brain tumor detection in medical imaging. This hybrid performance can use both general-purpose deep learning and domain-specific feature engineering, and it provides a practical suggestion of the approach that involves a satisfactory solution in the diagnostic sense. It verifies that the combination of more than 2 methods is productive in enhancing the results of medical image classification activities.

This manuscript proposes a novel nonisolated negative output buck-boost converter topology for wide voltage conversion applications. To design this converter, a typical buck-boost converter configuration is used. In conventional buck-boost converter, the active switches designed are replaced by two switches-two inductors (2S2L) cells. The proposed converter operates in the continuous conduction mode (CCM) operation under steady-state conditions. This converter has a lower component count and low voltage stress on the switches and diodes. Moreover, the major advantage of this buck-boost converter topology is that a wide range of step-down and step-up voltage conversions can be achieved. The performance of the proposed system is designed in MATLAB/SIMULINK. A few other comparisons are also presented to demonstrate the competitiveness of the proposed buck-boost converter.

Integrating renewable energies into the grid creates many problems, including the injection of harmonics. This research aims to maximize the energy extracted from PV arrays and wind turbines while minimizing total harmonic distortion (THD) injected into the grid. For that, we propose to study a grid-connected hybrid power system with a hybrid storage system consisting of batteries and a supercapacitor. Several control loops are required for the system, such as: MPPT for wind systems, Machine-Side Converter for the Permanent Magnet Synchronous Generator (PMSG), Battery Energy Storage System (BESS), Supercapacitor, and Grid-Side Converter (GSC). Previous works have used traditional PI controllers in these loops, but in our work, we propose a cascade PI-PID controller optimized with the COOT bird algorithm and the results were compared with a GA-tuned PI controller. The proposed approach demonstrated superior performance in settling time and reducing current and voltage oscillations, achieving a 30% and 81% reduction in [Formula: see text] and [Formula: see text], respectively. To eliminate peaks produced by the PI-PID controller, a supercapacitor system was incorporated and it effectively reduced these peaks. Additionally, a more realistic simulation scenario was proposed to test the system, involving variable sunlight, fluctuating wind speed, battery limits, and a load similar to real-life scenarios. Our energy management strategy efficiently maximized renewable energy exploitation while ensuring system stability.