Explore the vast range of titles available.

Physics-Informed Neural Networks (PINNs) integrate physics principles with machine learning, offering innovative solutions for complex modeling challenges. Laminated composites, characterized by their anisotropic behavior, multi-layered structures, and intricate interlayer interactions, pose significant challenges for traditional computational methods. PINNs address these issues by embedding governing physical laws directly into neural network architectures, enabling efficient and accurate modeling. This review provides a comprehensive overview of PINNs applied to laminated composites, highlighting advanced methodologies such as hybrid PINNs, k-space PINNs, Theory-Constrained PINNs, optimal PINNs, and disjointed PINNs. Key applications, including structural health monitoring (SHM), structural analysis, stress-strain and failure analysis, and multi-scale modeling, are explored to illustrate how PINNs optimize material configurations and enhance structural reliability. Additionally, this review examines the challenges associated with deploying PINNs and identifies future directions to further advance their capabilities. By bridging the gap between classical physics-based models and data-driven techniques, this review advances the understanding of PINN methodologies for laminated composites and underscores their transformative role in addressing modeling complexities and solving real-world problems.

Structural health monitoring (SHM) is essential for ensuring the safety and longevity of laminated composite structures. Their favorable strength-to-weight ratio renders them ideal for the automotive, marine, and aerospace industries. Among various non-destructive testing (NDT) methods, ultrasonic techniques have emerged as robust tools for detecting and characterizing internal flaws in composites, including delaminations, matrix cracks, and fiber breakages. This review concentrates on recent developments in ultrasonic NDT techniques for the SHM of laminated composite structures, with a special focus on guided wave methods. We delve into the fundamental principles of ultrasonic testing in composites and review cutting-edge techniques such as phased array ultrasonics, laser ultrasonics, and nonlinear ultrasonic methods. The review also discusses emerging trends in data analysis, particularly the integration of machine learning and artificial intelligence for enhanced defect detection and characterization through guided waves. This review outlines the current and anticipated trends in ultrasonic NDT for SHM in composites, aiming to aid researchers and practitioners in developing more effective monitoring strategies for laminated composite structures.

This review paper addresses the critical need for structural prognostics and health management (SPHM) in aircraft maintenance, highlighting its role in identifying potential structural issues and proactively managing aircraft health. With a comprehensive assessment of various SPHM techniques, the paper contributes by comparing traditional and modern approaches, evaluating their limitations, and showcasing advancements in data-driven and model-based methodologies. It explores the implementation of machine learning and deep learning algorithms, emphasizing their effectiveness in improving prognostic capabilities. Furthermore, it explores model-based approaches, including finite element analysis and damage mechanics, illuminating their potential in the diagnosis and prediction of structural health issues. The impact of digital twin technology in SPHM is also examined, presenting real-life case studies that demonstrate its practical implications and benefits. Overall, this review paper will inform and guide researchers, engineers, and maintenance professionals in developing effective strategies to ensure aircraft safety and structural integrity.

Due to their precision, compact size, and high torque transfer, Rotate vector (RV) reducers are becoming more popular in industrial robots. However, repetitive operations and varying speed conditions mean that these components are prone to mechanical failure. Therefore, it is important to develop effective health monitoring (HM) strategies. Traditional approaches for HM, including those using vibration and acoustic emission sensors, encounter such challenges as noise interference, data inconsistency, and high computational costs. Deep learning-based techniques, which use current electrical data embedded within industrial robots, address these issues, offering a more efficient solution. This research provides transfer learning (TL) models for the HM of RV reducers, which eliminate the need to train models from scratch. Fine-tuning pre-trained architectures on operational data for the three different reducers of health conditions, which are healthy, faulty, and faulty aged, improves fault classification across different motion profiles and variable speed conditions. Four TL models, EfficientNet, MobileNet, GoogleNet, and ResNET50v2, are considered. The classification accuracy and generalization capabilities of the suggested models were assessed across diverse circumstances, including low speed, high speed, and speed fluctuations. Compared to the other models, the proposed EfficientNet model showed the most promising results, achieving a testing accuracy and an F1-score of 98.33% each, which makes it best suited for the HM of robotic reducers.

Abstract Energy efficiency, longevity, and environmental benefits have made light emitting diodes (LEDs) indispensable in modern lighting and display applications. However, degradation mechanisms influenced by thermal stress, electrical overstress, and environmental conditions mean that their reliability remains a significant challenge. Prognostics and Health Management (PHM) has emerged as a promising approach for monitoring and predicting LED failures, enabling predictive maintenance whilst optimizing operational efficiency. This review comprehensively explores PHM methodologies for LEDs, encompassing physics-of-failure (PoF) models, data-driven approaches, and hybrid techniques that integrate both methodologies. While PoF models offer insights into physics-based failure, data-driven methods leverage statistical analysis, machine learning (ML), and deep learning (DL) for predictive analytics. Hybrid PHM frameworks combine these approaches to enhance prediction accuracy and robustness. The integration of Internet of Things (IoT)-enabled real-time monitoring, digital twins, and edge computing has further improved LED PHM capabilities. Despite these advances, challenges persist in sensor placement limitations, variability in LED architecture, data availability issues, and high computational costs. Overcoming these challenges through standardization, the development of adaptive hybrid models, and the application of advanced Artificial Intelligence (AI)-driven analytics will be essential for enabling the widespread adoption of PHM in LED applications across various industrial sectors. This review highlights key advances, current limitations, and future research directions to improve LED reliability and extend operational life through PHM strategies. Graphical Abstract Graphical Abstract

Background/Objectives: Accurate implant positioning in total knee arthroplasty (TKA) depends on reliable intraoperative landmark registration. In imageless TKA, registration errors can alter cutting-plane orientation and compromise alignment. This study quantitatively evaluated how anatomical landmark registration errors affect cutting-plane orientation in imageless TKA. Methods: A CAD-based simulation with controlled experimental validation using 3D-printed bone models was performed to reproduce the imageless TKA workflow. Controlled errors were introduced into key femoral and tibial landmarks, and the resulting deviations were quantified. The primary evaluation metrics were angular deviations in varus/valgus, flexion/extension, and internal/external rotation. Results: Coronal and rotational alignment showed the greatest sensitivity to registration error. In the femur, anteroposterior epicondylar displacement had the strongest rotational influence, with sensitivity reaching about 0.5°/mm, whereas mediolateral displacement of the tibial anteroposterior landmarks showed the highest sensitivity at about 1.4°/mm. Similar trends were observed in both simulation and experimental validation cases. Conclusions: The findings indicate that small registration errors can produce clinically significant cutting-plane deviations in imageless TKA, particularly at the femoral transepicondylar and tibial anteroposterior landmarks, and may approach commonly accepted alignment thresholds.

This study aims to develop an efficient and accurate breast cancer classification model using meta-learning approaches and multiple convolutional neural networks. This Breast Ultrasound Images (BUSI) dataset contains various types of breast lesions. The goal is to classify these lesions as benign or malignant, which is crucial for the early detection and treatment of breast cancer. The problem is that traditional machine learning and deep learning approaches often fail to accurately classify these images due to their complex and diverse nature. In this research, to address this problem, the proposed model used several advanced techniques, including meta-learning ensemble technique, transfer learning, and data augmentation. Meta-learning will optimize the model’s learning process, allowing it to adapt to new and unseen datasets quickly. Transfer learning will leverage the pre-trained models such as Inception, ResNet50, and DenseNet121 to enhance the model’s feature extraction ability. Data augmentation techniques will be applied to artificially generate new training images, increasing the size and diversity of the dataset. Meta ensemble learning techniques will combine the outputs of multiple CNNs, improving the model’s classification accuracy. The proposed work will be investigated by pre-processing the BUSI dataset first, then training and evaluating multiple CNNs using different architectures and pre-trained models. Then, a meta-learning algorithm will be applied to optimize the learning process, and ensemble learning will be used to combine the outputs of multiple CNN. Additionally, the evaluation results indicate that the model is highly effective with high accuracy. Finally, the proposed model’s performance will be compared with state-of-the-art approaches in other existing systems’ accuracy, precision, recall, and F1 score.

Nickel is a hormetic micronutrient for plants. This study investigates the comparative impact of seed priming with nickel in the form of bulk particles, and green-synthesized nanoparticles fabricated using leaf extract of Berberis baluchistanica , as reducing and capping agent, on germination, phenotypic characteristics, antioxidants, stomata, and photosynthetic activity of two wheat cultivars in a laboratory pot experiment. The synthesis of NiO-NPs was confirmed by using UV-spectrophotometer (peak at 203 nm) and their size observed was 22 nm. Furthermore, SEM, XRD, EDX, FTIR and evaluation of zeta potential were performed to study the physiochemical characteristics of NiO-NPs. Maximum root-to-shoot Ni translocation was observed under NiO-NPs, while bulk NiNO 3 accumulated maximum Ni in root. Both nano and bulk form of Ni had stimulatory effects on urease activity, ammonia, and nitrate content. NiO-NPs increased the root length, shoot length and biomass, which were downregulated under bulk NiNO 3 treatment. Bulk NiNO 3 exacerbated oxidative stress in the form of MDA, H 2 O 2 and membrane damage, which in turn elicited enzymatic and non-enzymatic antioxidants. This study suggests that green-synthesized NiO-NPs at low concentration are non-toxic and effective in improvement of plant growth and photosynthetic activity.

Wireless charging has become an emerging challenge to reduce the cost of a conventional plug-in charging system in electric vehicles especially for supercapacitors that are utilized for quick charging and low-energy demands. In this article, the design of an efficient wireless power transfer system has been presented using resonant inductive coupling technique for supercapacitor-based electric vehicle. Mathematical analysis, simulation, and experimental implementation of the proposed charging system have been carried out. Simulations of various parts of the systems are carried out in two different software, ANSYS MAXWELL and MATLAB. ANSYS MAXWELL has been used to calculate the various parameters for the transmitter and receiver coils such as self-inductance (L), mutual inductance (M), coupling coefficient (K), and magnetic flux magnitude (B). MATLAB has been utilized to calculate output power and efficiency of the proposed system using the mathematical relationships of these parameters. The experimental setup is made with supercapacitor banks, electric vehicle, wattmeters, controller, and frequency generator to verify the simulation results. The results show that the proposed technique has better power transfer efficiency of more than 75% and higher power transfer density using a smaller coil size with a bigger gap of 4–24 cm.

Food security remains a pressing global concern, exacerbated by population growth, diminishing agricultural lands, and climate uncertainties. As the demand for high-quality protein sources like eggs, meat, and milk escalates, conventional feed ingredients face challenges in meeting the burgeoning needs of livestock production. The projected increase in poultry and pig consumption further strains the availability of protein-rich feed sources, necessitating sustainable alternatives. Insects, notably black soldier fly larvae (BSFL), offer numerous advantages, including efficiently converting organic substrates into high-quality protein, fat, minerals, and vitamins. Their rapid reproduction, minimal environmental footprint, and ability to thrive on various organic materials make them an attractive protein source. However, consumer acceptance remains a hurdle, hindering their direct consumption despite their nutritional value. Incorporating BSFL into animal diets, especially poultry and swine, demonstrates promising results regarding growth and production. This review comprehensively overviews BSFL production systems, processing techniques, and nutritional profiles. Various factors influencing BSFL growth and feed quality are discussed, highlighting the importance of optimizing breeding systems and feed formulations. Processing methods are elucidated to ensure the safety and quality of BSFL-based products. Nutritional analysis reveals BSFL as a rich source of essential amino acids, fatty acids, and minerals, making them suitable replacements for soybean meal and fish meal. Despite the economic and environmental benefits of BSFL utilization, challenges persist, including regulatory issues, consumer perceptions, and production scalability. Standardized production protocols and legislative frameworks are needed to facilitate the widespread adoption of BSFL in animal feed industries. In conclusion, integrating BSFL into animal diets presents a promising solution to address protein shortages in livestock production while promoting sustainable resource utilization.