Archives of Computational Methods in Engineering最新文献

New manufacturing expertise, along with user expectations for gradually modified products and facilities, is creating changes in manufacturing scale and distribution. Standardization is essential for every industrial manufactured sector that delivers goods to consumers. Digital manufacturing (DM) is a vital component in the scheduling of all knowledge-based manufacturing. Additive Manufacturing (AM) is recognized as a useful technique in the area of sustainable development goals (SDGs). Modern Development techniques are inspected as a tool for the practices that are being adopted. Additive Manufacturing (AM) was introduced as an advanced technology that includes a new era of complicated machinery and operating systems. Cloud manufacturing framework makes it much easier to gain access to a variety of AM resources while investing as little as possible. This paper contributes an overview of used technologies advancement in the era of Additive manufacturing such as IoT, Big Data, ML, Digital twins, and Blockchain, and their contribution to Industry 4.0 for better and effective design, development, and production while at the same time providing a richer and ethical environment.

Graphical Abstract

The practice of predicting the traffic that is headed toward a specific website is known as web traffic prediction. To govern a network, network traffic forecasting is crucial. Since clients could experience long wait times and leave a website without a suitable demand prediction, web service providers must evaluate web traffic on a web server very carefully. It is an objective that predicting network traffic is a proactive way to assure safe, dependable, and high-quality network communication. The aim of this paper is to find out the algorithms that can be best fitted for web traffic prediction. If the traffic is more than the server can handle, then it will show error to the people who are reaching the website. So, it becomes difficult to handle a large amount of traffic. One option is we can increase the number of servers but for this to know how many servers should be increased we have to forecast the web traffic. This is one of the applications of web traffic forecasting. To improve traffic control decisions, it is necessary to estimate future web traffic. In this paper, we have discussed the most efficient algorithms that can be utilized for web traffic prediction. Here, SVM, LSTM, and ARIMA are discussed which are comparatively more efficient and optimized algorithms. Many algorithms can be used to predict this website traffic, but the algorithms discussed in this paper are found to be more optimized. So, overall this algorithm can be used for website prediction with great efficiency. These algorithms are found to be quite fast as compared to others and they also give a good accuracy score. So, the results show that the prediction precision is high if these algorithms are utilized.

After conducting a comprehensive historical review of presently established methods for computational modeling of multilayered bending plates, the present work introduces a novel 2D multiscale strategy, termed the 2D+ approach. The proposed approach is based on the computational homogenization formalism and is envisaged to serve as an appealing alternative to current methodologies for modeling multilayered plates in bending-dominated situations. Such structural elements involve modern and relevant materials, such as laminated composites characterized by the heterogeneous distribution of low-aspect-ratio layers showing substantial non-linear mechanical behavior across their thickness.

Within this proposed approach, the 2D plate mid-plane constitutes the macroscopic scale, while a 1D filament-like Representative Volume Element (RVE), orthogonal to the plate mid-plane and spanning the plate thickness, represents the mesoscopic scale. Such RVE, in turn, is capturing the non-linear mechanical behavior throughout the plate thickness at each integration point of the 2D plate-midplane finite element mesh. The chosen kinematics and discretization at the considered scales are particularly selected to (1) effectively capture relevant aspects of non-linear mechanical behavior in multilayered plates under bending-dominated scenarios, (2) achieve affordable computational times (computational efficiency), and (3) provide accurate stress distributions compared to the corresponding high-fidelity 3D simulations (computational accuracy).

The proposed strategy aligns with the standard, first-order, hierarchical multiscale setting, involving the linearization of the macro-scale displacement field along the thickness. It employs an additional fluctuating displacement field in the RVE to capture higher-order behavior, which is computed through a local 1D finite element solution of a Boundary Value Problem (BVP) at the RVE. A notable feature of the presented 2D+ approach is the application of the Hill–Mandel principle, grounded in the well-established physical assumption imposing mechanical energy equivalence in the macro and meso scales. This links the 2D macroscopic plate and the set of 1D mesoscopic filaments, in a weakly-coupled manner, and yields remarkable computational savings in comparison with standard 3D modeling. Additionally, solving the resulting RVE problem in terms of the fluctuating displacement field allows the enforcement of an additional condition: fulfillment of linear momentum balance (equilibrium equations). This results in a physically meaningful 2D-like computational setting, in the considered structural object (multilayered plates in bending-dominated situations), which provides accurate stress distributions, typical of full 3D models, at the computational cost of 2D models.

In recent decades, the constitutive modelling for frozen soils has attracted remarkable attention from scholars and engineers due to the continuously growing constructions in cold regions. Frozen soils exhibit substantial differences in mechanical behaviours compared to unfrozen soils, due to the presence of ice and the complexity of phase changes. Accordingly, it is more difficult to establish constitutive models to reasonably capture the mechanical behaviours of frozen soils than unfrozen soils. This study attempts to present a comprehensive review of the state of the art of constitutive models for frozen soils, which is a focal topic in geotechnical engineering. Various constitutive models of frozen soils under static and dynamic loads are summarised based on their underlying theories. The advantages and limitations of the models are thoroughly discussed. On this basis, the challenges and potential future research possibilities in frozen soil modelling are outlined, including the development of open databases and unified constitutive models with the aid of advanced techniques. It is hoped that the review could facilitate research on describing the mechanical behaviours of frozen soils, and promote a deeper understanding of the thermo-hydro-mechanical (THM) coupled process occurring in cold regions.

This study delves into the transformative influence of Machine Learning (ML), Deep Learning (DL), and Artificial Intelligence (AI) within the realm of Structural Engineering, emphasizing their profound implications for Information, Process, and Design Engineering. Through a meticulous analysis of existing literature, the study highlights the vast potential of ML, DL, and AI across diverse construction domains, particularly within structural engineering, including healthcare, performance evaluation, monitoring, and optimization. Notably, the integration of ML with the Internet of Things (IoT) for real-time structural health monitoring emerges as a pivotal advancement, promising enhanced durability and performance models. Moreover, the application of ML-supported multi-objective optimization in design processes showcases promising strides, effectively balancing factors such as cost and durability to bolster structural integrity. By leveraging these technologies to process data, identify patterns, and predict behaviour, structural health is significantly bolstered. Moving forward, the study advocates for continued exploration of ML and IoT integration for real-time monitoring, refinement of learning algorithms for process control, and the utilization of ML-assisted multi-objective optimization in design. Crucially, it underscores the imperative of addressing challenges such as data availability and algorithm robustness to fully harness the potential of ML, DL, and AI in revolutionizing structural engineering design. This research thus serves as a clarion call for further investigation and training to facilitate the widespread adoption of these transformative technologies in structural engineering practices.

Outstanding effectiveness of transformers in visual tasks has resulted in its fast growth and adoption in three dimensions (3D) vision tasks. Vision transformers have shown numerous advantages over earlier convolutional neural network (CNN) architectures including broad modelling abilities, more substantial modelling capabilities, convolution complementarity, scalability to model data size, and better connection for enhancing the performance records of many visual tasks. We present thorough review that classifies and summarizes the popular transformer-based approaches based on key features for transformer integration such as the input data, scalability element that enables transformer processing, architectural design, and context level through which the transformer functions as well as a highlight of the primary contributions of each transformer approach. Furthermore, we compare the results of these techniques with commonly employed non-transformer techniques in 3D object classification, segmentation, and object detection using standard 3D datasets including ModelNet, SUN RGB-D, ScanNet, nuScenes, Waymo, ShapeNet, S3DIS, and KITTI. This study also includes the discussion of numerous potential future options and limitation for 3D vision transformers.

Science and Engineering applications are typically associated with expensive optimization problem to identify optimal design solutions and states of the system of interest. Bayesian optimization and active learning compute surrogate models through efficient adaptive sampling schemes to assist and accelerate this search task toward a given optimization goal. Both those methodologies are driven by specific infill/learning criteria which quantify the utility with respect to the set goal of evaluating the objective function for unknown combinations of optimization variables. While the two fields have seen an exponential growth in popularity in the past decades, their dualism and synergy have received relatively little attention to date. This paper discusses and formalizes the synergy between Bayesian optimization and active learning as symbiotic adaptive sampling methodologies driven by common principles. In particular, we demonstrate this unified perspective through the formalization of the analogy between the Bayesian infill criteria and active learning criteria as driving principles of both the goal-driven procedures. To support our original perspective, we propose a general classification of adaptive sampling techniques to highlight similarities and differences between the vast families of adaptive sampling, active learning, and Bayesian optimization. Accordingly, the synergy is demonstrated mapping the Bayesian infill criteria with the active learning criteria, and is formalized for searches informed by both a single information source and multiple levels of fidelity. In addition, we provide guidelines to apply those learning criteria investigating the performance of different Bayesian schemes for a variety of benchmark problems to highlight benefits and limitations over mathematical properties that characterize real-world applications.

Skin cancer is a significant global health concern, with its early detection and diagnosis playing a pivotal role in improving patient health outcomes. In recent years, artificial intelligence (AI) has emerged as a transformative force in the field of dermatology, revolutionizing the way skin cancer is detected and diagnosed. This comprehensive survey paper delves into the realm of AI-enhanced early skin cancer diagnosis, offering a thorough examination of the state-of-the-art techniques, methodologies, and advancements in this critical domain. Our survey begins by providing a comprehensive overview of the different types of skin cancer, emphasizing the importance of early detection in preventing disease progression. It then explores the pivotal role that AI and machine learning algorithms play in automating the detection and classification of skin lesions, making dermatology more accessible and accurate. A critical analysis of various AI-driven approaches, including image-based classification, feature extraction, and deep learning models, is presented to elucidate their strengths and limitations. Furthermore, this survey examines the integration of AI into clinical practice, discussing real-world applications, challenges, and ethical considerations. It explores the potential of AI to assist dermatologists in making faster and more accurate diagnoses, ultimately enhancing patient care. The paper also addresses the need for large, diverse datasets and standardization in the development and validation of AI models for skin cancer diagnosis. In conclusion, “Revolutionizing Dermatology” presents a comprehensive synthesis of the current landscape of AI-enhanced early skin cancer diagnosis, offering insights into its transformative potential, challenges, and future directions. By bridging the gap between dermatology and cutting-edge AI technologies, this survey aims to facilitate informed decision-making among researchers, clinicians, and stakeholders in the pursuit of more effective skin cancer detection and treatment strategies.

Over the past few years, the increasing occurrence of catastrophic accidents in aviation owing to human factors has raised several devastating threats to mankind. Recent progress in fatigue recognition among pilots made by Artificial intelligence (AI) has intensely begun to enhance the safety of the aviation sector by identifying and warning the potential catastrophic incidents caused by the impaired cognitive condition of aviation professionals. In this review, we have thoroughly investigated the implementation of AI-based approaches in the domain of aviation for fatigue detection. To the extent of our knowledge, it is clear that this review article is a new paper extremely devoted for investigating the advancements and challenges rendered by the AI-based approaches for addressing sleep and fatigue issues in aviation. Initially, we provided the basic definition of fatigue, various aspects provoking these problems among aviation professionals, and its effects in compromising aviation safety. Secondly, we illustrated a review of AI-based approaches developed for assessing fatigue and sleep problems in the context of aviation. Thirdly, the comparisons of various approaches are provided to summarize the efficiency of the existing works. Finally, we talked about the challenges encountered by the state-of-the-art approaches for identifying future research direction, and our suggested solutions are well presented for improving the efficiency of the fatigue detection approaches. This comprehensive research clearly depicts that the advancement of fatigue recognition approaches based on AI has a wider scope for mitigating pilot’s fatigue by identifying the mental state of the pilot earlier and providing adequate interventions.

This research aims to comprehensively analyze the most essential uses of artificial intelligence in Aerospace Engineering. We obtained papers initially published in academic journals using a Systematic Quantitative Literature Review (SQLR) methodology. We then used bibliometric methods to examine these articles, including keyword co-occurrences and bibliographic coupling. The findings enable us to provide an up-to-date sketch of the available literature, which is then incorporated into an interpretive framework that enables AI's significant antecedents and effects to be disentangled within the context of innovation. We highlight technological, security, and economic factors as antecedents prompting companies to adopt AI to innovate. As essential outcomes of the deployment of AI, in addition to identifying the disciplinary focuses, we also identify business organizations' product innovation, process innovation, aerospace business model innovation, and national security issues. We provide research recommendations for additional examination in connection to various forms of innovation, drawing on the most critical findings from this study.