Archives of Computational Methods in Engineering最新文献

Research on Microstrip Patch Antennas (MPAs) has significantly increased in recent years, due to their compact design, ease of fabrication, and cost-effectiveness. However, certain aspects of MPAs, such as narrow bandwidth, low gain, and suboptimal polarization purity still need improvement. It is crucial to optimize the performance parameters of MPAs, including bandwidth and gain while maintaining a compact form factor. Although traditional optimization techniques have been employed to address these challenges, they often struggle to achieve global optima and effectively manage multiple design variables. To address these limitations, nature-inspired metaheuristic optimization algorithms have emerged as a popular alternative. This comprehensive review examines recent research on applying optimization algorithms in MPA design, discussing their advantages, drawbacks, and effectiveness in addressing MPA design challenges. The review covers widely used algorithms such as Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Differential Evolution (DE), Artificial Bee Colony (ABC) optimization, Bacterial Foraging Optimization (BFO), and Ant Colony Optimization (ACO). Additionally, it explores the potential of novel metaheuristic algorithms, including Cuckoo Search (CS), Firefly Algorithm (FA), Grey Wolf Optimization (GWO), Bat Algorithm (BA), and Invasive Weed Optimization (IWO) to enhance MPA performance. This study summarizes the impact of various optimization methods on key performance metrics of MPAs, including bandwidth, return loss, gain, radiation efficiency, and miniaturization. It synthesizes findings from previously published research, emphasizing the growing need for multi-objective and hybrid optimization techniques in MPA design. These optimization techniques facilitate the development of high-performance, compact antenna solutions for a wide range of wireless communication applications while ensuring computational efficiency. Furthermore, the paper suggests several intriguing avenues for future research in MPA optimization.

Accurately estimating the discharge coefficient (C_d) in spillways remains a complex challenge, critical to hydraulic engineering. Recent advancements suggest that hybrid Machine Learning (ML) models offer significant potential for improving C_d predictions. This study explores the application of four novel hybrid ML models to estimate C_d in Hydrofoil-Crested Stepped Spillways (HCSSs): Light Gradient Boosting Machine with Pelican Optimization Algorithm (LightGBM-POA), Neural Gradient Boosting with Osprey Optimization Algorithm (NGBoost-OOA), Tabular Neural Network with Moth Flame Optimization (TabNet-MFO), and Support Vector Regression with Improved Whale Optimization Algorithm (SVR-IWOA). Outlier detection was performed using the Isolation Forest algorithm, and dimensional analysis identified the hydrofoil formation index (t) and the ratio of upstream flow depth to total spillway height (y_up/P) as the most influential parameters for C_d estimation. The parameters were validated through ANOVA, while SHapley Additive exPlanations (SHAP) and Explainable Boosting Machine (EBM) quantified their contributions to C_d modeling, highlighting the dominant influence of t. Data normalization employed the StandardScaler method, with the dataset split into training (75%; 342 records) and testing (25%; 115 records) subsets. Model performance was assessed using metrics such as R², RMSE, SI, WMAPE, and sMAPE, and further evaluated using Taylor diagrams and a performance index (PI). During training stage, NGBoost-OOA achieved the highest accuracy, followed by LightGBM-POA, TabNet-MFO, and SVR-IWOA, with centered root mean square error (E’) values of 0.0057, 0.0064, 0.0067, and 0.0068, and PI scores of 165.5, 165.17, 123.25, and 123.25, respectively. In testing stage, TabNet-MFO and SVR-IWOA outperformed the other models, achieving equal E′ values of 0.0060 and PI scores of 165.34, ranking first. NGBoost-OOA and LightGBM-POA ranked third and fourth, respectively. These findings demonstrate the potential of hybrid ML models in accurately predicting C_d for complex hydraulic structures like HCSSs, offering valuable insights for future engineering applications.

The multi-verse optimiser (MVO) algorithm, inspired by the metaphor of multiple universes and their interactions, has emerged as a promising metaheuristic optimisation technique. This review paper provides an in-depth analysis of the MVO algorithm and its progression throughout the years, with a particular focus on developments from 2020 to 2024. We begin by elucidating the fundamental principles and components of MVO, highlighting its unique characteristics and historical context. Subsequently, we delve into recent advancements, modifications, and hybridisation of MVO with other optimisation methods, illustrating how these innovations have enhanced its performance and applicability. Our survey encompasses a broad range of publications that have employed MVO and its variants, examining its efficacy across diverse problem domains. We discuss empirical studies that benchmark MVO against other optimisation algorithms, providing insights into its strengths and limitations. Furthermore, we address prevalent criticisms and challenges faced by MVO, along with potential avenues for improvement and resolution. Real-world applications of MVO across various fields are showcased, emphasising its impact and utility in solving complex optimisation problems. We analyse how MVO has been adapted to tackle specific challenges in engineering, finance, logistics, and beyond. Finally, we outline prospective research directions aimed at refining the efficiency and effectiveness of the MVO algorithm, including avenues for exploring novel hybridisation and theoretical enhancements. This review is a significant resource for scholars and practitioners aiming to comprehend the latest developments, applications, and prospects of the MVO algorithm.

In this article, we look at how intuitionistic fuzzy programming (IFP) for MOO works in several real-life situations. Problems in the real world frequently have non-linear properties, in contrast to the majority of MOO research, which has traditionally relied on linear assignment functions in an intuitionistic setting. To tackle this, our research takes into account non-linear functions such as hyperbolic, parabolic, exponential, and s-curved functions. These functions handle the constraints caused by convexity and concavity in certain areas of the domain, as well as the impact of the functions' slopes. We then investigate 25 potential hybrid scenarios involving various membership and non-membership functions in IFP methods. Evaluating how these hybrid scenarios affect IFP's ability to handle the complexity of MOO is our main goal. By evaluating how various scenarios perform, we attempt to determine the best setups and comprehend their advantages and disadvantages. The results of our quantitative evaluations and practical implementations shed light on multi-objective optimization in real-world settings, which is useful for practitioners and decision makers. To further illustrate the real-world consequences of different IFP approaches, we offer an engaging case study in the agricultural sector. This study not only consolidates current knowledge but also provides practical assistance for achieving optimal results in diverse situations, enhancing our grasp of optimization strategies based on IFP.

In this study, a historical review of the Finite Element Method (FEM) and Molecular Dynamics (MD), widely used at the macro and nanoscale respectively is presented, emphasizing the actual parallelisms between their development and applications. After this historical introduction, where certain similarities between both methods are pointed out, different FEM-like methods are analyzed and compared as for first order analysis of structures at the nanoscale. Firstly, the Structural Mechanics (SM) approach is analyzed, where it is assumed that the use of Euler Bernoulli beam elements is equivalent to working directly from the force field. On the other hand, the Molecular Element Method (MEM), which provides the stiffness matrices directly from the potentials, is analyzed. Several analytical static cases are studied for the validation and comparison of both methods. Finally, it is shown that, other branch of methods such as Elastic Network Models (ENM) can be viewed as a particular sub-case of the MEM, or as truss-type finite elements. As an example, the analysis of SARS-CoV2 spikes vibrations is included, comparing with both experimental results and continuous models.

Towards a better groundwater management, developing a prediction model for groundwater quality is of utmost importance. The conventional method of measuring groundwater quality data often associated with errors due to the lengthy duration of investigation of the parameters as well as the tremendous effort and time involved in gathering and analysing the samples. The expense associated with determining the parameters’ values via laboratory testing is substantial. There has been a notable increase in machine learning (ML) application for modelling groundwater quality as of recent, evidenced by a wealth of studies reporting impressive results. This paper provides an extensive examination of 91 relevant articles picked from the Web of Science and PubMed, from 2015 to 2024. The focus of the review revolves on significant ML algorithms, including artificial neural networks (ANN), random forest (RF), support vector machines (SVM), hybrid models, and other algorithms that have demonstrated efficacy in predicting groundwater quality, such as k-nearest neighbours and extreme gradient boosting (XGBoost). Critical modelling concepts such as data splitting, utilized parameters, performance metrics, and study areas were addressed, emphasizing optimal practices for effective groundwater quality prediction with ML.

Meta-heuristic algorithms aim to achieve near-optimal solutions to complex optimization problems by taking inspiration from nature. The last three decades have seen an increased focus on the use of meta-heuristics in optimization, with the direct result that a great number of new meta-heuristics have been created to tackle challenging real-world situations in various sectors. Swarm intelligence is one of the most important families of bio-inspired algorithms and the artificial bee colony (ABC) algorithm is a prominent member. This paper presents a comprehensive survey of the ABC algorithm and describes its variants, modifications, applications, and developments. The primary purpose of this survey is to provide a complete analysis of the current developments in the ABC algorithm which will include improvements, variations, hybridizations, multi-objectives, and its applications in a variety of domains. This research presents the results of several studies that have been carried out to improve the ABC algorithm’s performance in various fields using different methodologies. Finally, we discuss the future opportunities and challenges for ABC algorithm research, including potential areas for further development and the need for rigorous testing and benchmarking. We conclude that the ABC algorithm is a promising and versatile optimization algorithm that has the potential to be applied to a wide range of real-world problems.

Skin cancer is one of the most frequent and deadly form of cancer. Essentially, it is an abnormal growth of skin cells that primarily occurs after contaminated hands with the sun. These days, it also appears on skin surfaces that are not exposed to sunlight. Skin cancer is smoothly curable only if it is diagnosed in its initial days. There are some prominent types of skin cancer named as melanoma, squamous cell carcinoma, basal cell carcinoma, and many others. Many machine learning and deep learning methods have been developed to interpret medical images, specifically those of skin lesions, it is difficult and tiresome to analyze these to find cancer manually. Computer-aided diagnosis systems have two essential procedures: classification and segmentation of lesions. These two procedures improve the quality of features retrieved from medical images. An overview of some methods used to diagnose skin cancer is provided to identify the most efficient preprocessing, segmentation, feature extraction, and classification of medical images. Various research methods for specific skin cancer classification are also explored in this study. A further hurdle to creating an optimal diagnosis algorithm is the absence of a dataset on skin cancer. In order to assist researchers in developing useful algorithms that rapidly and accurately diagnose skin cancer, the study offers to provide a current overview of the proposed solutions to the issues in skin cancer detection. We gathered the results in tabular form after analyzing the efficiency of the most recent research based on a variety of factors, including techniques, and the performance of the applied datasets. We have discussed the current Deep Learning and Machine Learning techniques for detecting skin cancer along with their limitations. Along with outlining the various assessment metrics, we have also discussed the research gaps and challenges, such as imbalanced datasets, intra-class variance, inter-class similarity, etc., in skin cancer detection. The survey demonstrates its superiority over various other surveys currently in use.

In order to solve complex optimization problems, swarm intelligence (SI) techniques that draw inspiration from the collective behavior of fish schools, ant foraging, and bird flocking are gaining popularity. Particle Swarm Optimization (PSO) and Ant Colony Optimization (ACO) are two widely recognized techniques in the fields of metaheuristics. This article provides a comprehensive examination of PSO and ACO, assessing their fundamental concepts, working mechanisms, algorithmic variations, and an extensive range of applications. We thoroughly compare the advantages and disadvantages of PSO and ACO, and examine their respective successes and failures in various scenarios. These approaches have demonstrated their effectiveness in practical scenarios, as evidenced by various case studies. This paper explores innovative advancements, ongoing challenges that require resolution, and thrilling new avenues for future research in swarm intelligence-based optimization. This paves the way for further advancements in this swiftly evolving domain.

Even with the state-of-the-art technology of computer-aided design and topology optimization, the present structural design still faces the challenges of high dimensionality, multi-objectivity, and multi-constraints, making it knowledge/experience-demanding, labor-intensive, and difficult to achieve or simply lack of global optimality. Structural designers are still searching for new ways to cost-effectively to achieve a possible global optimality in a given structure design, in particular, we are looking for decreasing design knowledge/experience-requirements and reducing design labor and time. In recent years, Artificial Intelligence (AI) technology, characterized by the large language model (LLM) of Machine Learning (ML), for instance Deep Learning (DL), has developed rapidly, fostering the integration of AI technology in structural engineering design and giving rise to the concept and notion of Artificial Intelligence-Aided Design (AIAD). The emergence of AIAD has greatly alleviated the challenges faced by structural design, showing great promise in extrapolative and innovative design concept generation, enhancing efficiency while simplifying the workflow, reducing the design cycle time and cost, and achieving a truly global optimal design. In this article, we present a state-of-the-art overview of applying AIAD to enhance structural design, summarizing the current applications of AIAD in related fields: marine and naval architecture structures, aerospace structures, automotive structures, civil infrastructure structures, topological optimization structure designs, and composite micro-structure design. In addition to discussing of the AIAD application to structural design, the article discusses its current challenges, current development focus, and future perspectives.