Early and precise diagnosis of brain tumors is essential for successful treatment planning and improved patient outcomes. This paper introduces a novel hybrid deep model that incorporates DenseNet121, a convolutional neural network (CNN), and the Swin Transformer, a vision transformer model, by feature-level fusion to classify brain tumors from magnetic resonance imaging (MRI) scans. The suggested method provides a more discriminative and better representation by uniting the global context capability of the Transformer model with the local feature extraction capability of the CNN model. The suggested method was trained and assessed on a publicly available brain MRI dataset of four classes: glioma, meningioma, pituitary tumor, and no tumor. Experimental results indicate that the proposed approach outperforms many baseline models including VGG16, MobileNetV2, and AlexNet with an accuracy of 99.39%, precision of 99.36%, recall of 99.34%, and F1-score of 99.35%. Grad-CAM was utilized to visualize class-discriminative regions in the MRI scans to enhance interpretability, hence validating the model's emphasis on tumor-relevant regions. These outcomes prove the efficacy of coupling Transformer and CNN architectures in obtaining accurate and interpretable brain tumor classification from MRI scans.

 Fuzzy Neural Networks (FNNs) enhance conventional Artificial Neural Networks (ANNs) by incorporating fuzzy membership functions, which enable the handling of uncertainty, ambiguity, and imprecise information. While Fuzzy Backpropagation Neural Networks (FBNNs) improve classification performance across noisy datasets, the effectiveness of fuzzification heavily depends on the proper tuning of membership function parameters—typically optimized manually. This paper presents a novel Artificial Immune System framework for optimizing Fuzzy Backpropagation Neural Networks used in the classification of biological image data. The approach integrates a fuzzy min–max fuzzification layer with a feed-forward backpropagation network and applies an optimization version of an Artificial Immune Network model, derived from opt-aiNet, to tune trapezoidal membership functions. Experimental results confirm that the proposed immune-driven optimization is an effective technique for enhancing FBNN robustness and generalization.

Marine water jet propulsion systems require optimized nozzle and duct geometries to maximize thrust and efficiency, yet design improvements are often limited by the lack of integrated hydrodynamic analysis. This study aimed to design an efficient marine water jet and evaluate its hydrodynamic performance through combined CAD modeling and CFD simulation. A three-dimensional model of the propulsion system was developed in SolidWorks, incorporating optimized nozzle and internal duct geometry. Computational Fluid Dynamics (CFD) simulations were performed to analyze velocity fields, pressure distributions, and thrust output under defined fluid properties and boundary conditions. Both the complete jet system (including a free-surface water interface) and a simplified nozzle-only configuration was examined. Simulations revealed clear correlations between geometric parameters and performance, identifying configurations that improved energy conversion and reduced wall friction. The optimized design achieved higher thrust efficiency compared to baseline geometries. Integrated CAD–CFD analysis provides a robust framework for marine water jet design, enabling targeted geometry refinements that enhance hydrodynamic performance. The findings support future development of high-efficiency propulsion systems for marine applications. 

Steel corrosion in reinforced concrete (RC) structures is a major concern in civil engineering, as it directly affects the safety, serviceability, and lifespan of infrastructures. This study focuses on understanding how corrosion-induced deterioration in steel reinforcement impacts the structural performance of concrete beams. In particular, it investigates how different levels of reinforcement loss influence the load-bearing capacity and failure mechanisms of RC beams under combined bending and shear. To achieve this, a numerical approach was adopted using the ABAQUS finite element software. Three beam models were developed, each representing a different degree of corrosion: intact reinforcement, 20% loss, and 25% loss in cross-sectional area. The models were designed to closely simulate the physical behavior of corroded beams, incorporating nonlinear material properties, bond degradation, and failure criteria. The findings reveal a clear decline in structural performance as corrosion severity increases. Beams with higher reinforcement loss exhibited reduced ultimate loads, increased deflections, and altered failure modes - particularly in shear-dominated regions. The simulation results aligned well with available experimental data, demonstrating the accuracy and reliability of the modeling approach. This research highlights the importance of early detection and quantification of corrosion damage in RC structures. By employing advanced finite element tools like ABAQUS, engineers can better predict structural degradation, evaluate safety margins, and plan timely interventions. The study provides valuable insights into infrastructure asset management and supports the development of effective maintenance strategies aimed at extending the service life of aging concrete structures exposed to aggressive environments.

KEYWORDS

Reinforcement, Deflection, Numerical, Analysis, ABAQUS, FE Modelling

Cite This Paper in IEEE or APA Citation Styles

(a). IEEE Format:

[1] Bashir Saleh , "Numerical Evaluation of Corrosion-Induced Degradation in Reinforced Concrete Beams Using Finite Element Analysis in ABAQUS," Civil Engineering and Architecture, Vol. 13, No. 5, pp. 3967 - 3974, 2025. DOI: 10.13189/cea.2025.130536.

(b). APA Format:

Bashir Saleh (2025). Numerical Evaluation of Corrosion-Induced Degradation in Reinforced Concrete Beams Using Finite Element Analysis in ABAQUS. Civil Engineering and Architecture, 13(5), 3967 - 3974. DOI: 10.13189/cea.2025.130536.

Asphalt roads are one of the most important elements of infrastructure in any country, as they play a vital role in achieving comprehensive development and economic growth. They provide safe and reliable means of transportation for citizens and companies, which develops trade, contributes to the development of industry, and expands the investment base. In addition, asphalt roads contribute to enhancing tourism and developing the infrastructure of cities and rural areas. Therefore, it is necessary to invest heavily in the construction and maintenance of asphalt roads to ensure economic growth and social stability. The Superpave system is an important development in the field of paving, as it contributes to improving the design of hot asphalt mixes and evaluating the performance of paving facilities. This system relies on precise standards to evaluate the quality of asphalt mixes, which leads to improving the durability of the pavement and its efficiency in withstanding different traffic loads. This system is also the result of field and laboratory research and studies included in the Strategic Highway Research Program in the United States of America. Due to the importance of this system, we present this study to examine previous studies on the classification of asphalt binders in the high-performance asphalt paving system (Superpave) and to identify the significance of classifying the binder in this system.

Ischemic brain stroke is the most prevalent type of stroke caused by the occlusion of blood vessels via thrombi or blockages and is the second most common cause of mortality globally, after ischemic heart disease. To improve patient outcomes, ischemic stroke must be diagnosed timely and precise. This paper introduces a novel approach toward ischemic stroke detection from computed tomography (CT) images by integrating deep learning and optimization techniques for feature extraction and selection. The VGG16 model is utilized to extract high-dimensional spatially rich features that efficaciously capture the intricate texture and spatial patterns within the CT scans. To optimize these features, a genetic algorithm (GA) is leveraged to select the most discriminative subset and reduce redundancy. The new method was developed and evaluated on a unique, first-hand dataset gathered from a specialized private hospital in Palestine. The findings show that the suggested combined technique VGG16-GA highly enhances the performance of all classifiers. Notably, the VGG16-GA-XGB model attained superior outcomes, with an accuracy of 98.89%, precision of 98.85%, recall of 98.93%, and an F1-score of 98.92%.

Resonance occurs when the operating frequency of a system aligns with its natural frequency, resulting in amplified vibration amplitudes. To prevent potential damage and ensure optimal performance of a compressor's base frame at Souq Al-Khamis Cement Factory, researchers found the resonance in has been occurred when both the natural frequencies and rotating frequency were overlapped. Resonant Vibration in the base frames arises when the rotating vibration frequency aligns with the frame’s natural modes that leads to structural instability, fault unplanned shutdowns and production losses. This study analyzes resonant vibration in a cement factory compressor base frame and proposes a redesign using finite element methods to mitigate this issue. Four distinct modifications were made to the base frame on its shape, weight and boundary conditions: the first introduces fixed points to enhance rigidity, the second adds supports for increased stability, the third incorporates elements to improve durability, and the fourth enhances the thickness of the compressor. The results indicate that the redesigned configuration most effectively mitigates resonance and improves the system's natural frequency response.

The progressive deterioration of flexible pavements, driven by increasing traffic loads, environmental influences, and material aging, necessitates the implementation of effective structural reclamation strategies to restore functional performance and extend service life. This study focuses on a critical segment of the Libyan coastal road network, specifically the 27.5 km part from Tripoli Street Bridge to Al-Krarim Gate. An analytical and quantitative investigation is undertaken to evaluate the structural condition and rehabilitation potential of the existing flexible pavement system, with particular attention to distress mechanisms, material degradation, and the effectiveness of various rehabilitation techniques. The assessment integrates field investigations, laboratory testing, based on AASHTO 1993, and to evaluate pavement distress, base soil strength, and asphalt concrete layers performance; Pavement Condition Index (PCI) values and core sample analyses are employed to determine the extent of structural failure. Visual distress surveys supplement the data to provide a comprehensive understanding of surface and sub-surface conditions. Analytical modeling, based on layered elastic theory is used to simulate pavement response under rehabilitated conditions and forecast long-term performance under loading. The study examines several rehabilitation methods, including full-depth reclamation (FDR), cold in-place recycling (CIR), and mechanical stabilization using cementitious additives. Each method is evaluated based on structural capacity enhancement, cost-efficiency, and service life extension. Results demonstrate that the selection of reclamation techniques tailored to subgrade conditions and traffic loads significantly improves structural performance and minimizes maintenance needs. The study concludes that full-depth repaving offers the most sustainable and economically viable solution for restoring the targeted roadway section.

Countries located in temperate, hot and arid climates, such as Libya, face the critical need to cool houses whose internal temperatures rise due to these climatic conditions. This can be achieved by employing proper insulation techniques to prevent heat gain from solar radiation (insolation). This paper addresses the impact of not implementing thermal insulation for the roof of a building, in contrast to other external parts of the structure. The temperature distribution in a single-story building was studied using finite element analysis (FEA), along with how the building absorbs heat from its surroundings during a sunny day. The thermal analysis was conducted on a 3D concrete building with walls made of concrete masonry blocks, a floor height of 3.20 meters, and a total area of 40 square meters, using ANSYS 2020 R2 software. The building model includes thermal insulation for the external envelope, but the roof and openings remain uninsulated (as is often the case with home insulation practices in Libya). The finite element method is widely used due to its high effectiveness in simulation and achieving accurate results. The analysis results demonstrated the heat distribution gained from insolation, as well as variations in the rates of heat transfer from the building's exterior to its interior. The findings showed that neglecting the thermal insulation of the roof and window openings leads to an approximate 70% increase in the building's internal temperature. Furthermore, the results clearly indicated that insulating the building's walls alone is insufficient to prevent overheating. This provides a sufficient understanding of the prioritization required in applying insulation layers for buildings located in hot climates.