Transfer functions have a very important role in metaheuristic optimization-based feature selection algorithms as these functions map the continuous search space into binary space. The U-shaped transfer function (UTF)...
详细信息
Transfer functions have a very important role in metaheuristic optimization-based feature selection algorithms as these functions map the continuous search space into binary space. The U-shaped transfer function (UTF) is one of the transfer functions used to solve the problem of feature selection. However, the UTF requires the selection of parametric values, which can vary for different types of data. To address this issue, an approach to select the parameters of the UTF has been proposed based on a time-varying adaption method, resulting in the modified U-shaped transfer function (MUTF). Furthermore, a methodology has been proposed to enhance feature selection and classification for Parkinson's disease by utilizing z-score normalization in conjunction with a modified U-shaped transfer function and the binary self-adaptive bald eagle search (MUTF-SABES) optimization algorithm. The z-score normalization has been used to mitigate issues caused by outliers. Also, the performance of the k nearest neighbor classifier is improved by selecting an optimal parameter value using the proposed MUTF-SABES algorithm. The effectiveness of the proposed methodology is validated on seven different Parkinson's disease datasets and compared with five state-of-the-art optimization algorithms: Salp Swarm algorithm, Harris Hawks optimization, equilibrium optimizer, aquilla optimizer, and Honey Badger algorithm, to evaluate its performance superiority. The results achieved using the proposed approach have been superior or analogous to the erstwhile algorithms for performance comparability. Friedman's mean rank test is used to check the statistical significance of the propounded approach. The lowest Friedman's mean rank value obtained using the proposed approach indicates that the proposed approach has the potential to become an alternative to other well-known strategies.
A novel nature-inspired meta-heuristic optimization algorithm, named artificial ecosystem-based optimization (AEO), is presented in this paper. AEO is a population-based optimizer motivated from the flow of energy in ...
详细信息
A novel nature-inspired meta-heuristic optimization algorithm, named artificial ecosystem-based optimization (AEO), is presented in this paper. AEO is a population-based optimizer motivated from the flow of energy in an ecosystem on the earth, and this algorithm mimics three unique behaviors of living organisms, including production, consumption, and decomposition. AEO is tested on thirty-one mathematical benchmark functions and eight real-world engineering design problems. The overall comparisons suggest that the optimization performance of AEO outperforms that of other state-of-the-art counterparts. Especially for real-world engineering problems, AEO is more competitive than other reported methods in terms of both convergence rate and computational efforts. The applications of AEO to the field of identification of hydrogeological parameters are also considered in this study to further evaluate its effectiveness in practice, demonstrating its potential in tackling challenging problems with difficulty and unknown search space. The codes are available at.
A framework has been designed to optimize the performance of two-element airfoils using an open-source physics informed neural network solver under certain aerodynamics constraints, The solver used is the Nvidia Modul...
详细信息
ISBN:
(数字)9781624107115
ISBN:
(纸本)9781624107115
A framework has been designed to optimize the performance of two-element airfoils using an open-source physics informed neural network solver under certain aerodynamics constraints, The solver used is the Nvidia Modulus. The objective function is constructed such that with a single training, it can predict the flow fields and force coefficients for a range of angles of attack and airfoil thickness. optimization is then performed using the trained network to improve the airfoil performance. Results show that this trained network can predict the flow fields and force coefficients with reasonable accuracy much faster than traditional computational fluid dynamics solvers. When coupled with an optimization routine, it can also predict maximum cl, cl/cd and endurance coefficient.
Improved Henry gas solubility optimization algorithm is a better way to use an existing method (HGSO) inspired by gas dissolving in liquids, to find optimal solutions. It leverages the influence of pressure and temper...
详细信息
ISBN:
(纸本)9798350365740;9798350365757
Improved Henry gas solubility optimization algorithm is a better way to use an existing method (HGSO) inspired by gas dissolving in liquids, to find optimal solutions. It leverages the influence of pressure and temperature on gas solubility to guide their search for optimal solutions in optimization problems. It aims to overcome the limitations of the original Henry gas solubility optimization algorithm and enhance its performance in solving various optimization problems. It can be used in many applications, such as feature extraction, task scheduling, joint mining, and parameter optimization. This paper proposes a new approach called the beta-Hill operator, which builds upon the traditional hill climbing method. to improve the balance between finding better solutions (exploitation) and exploring new possibilities (exploration).
Reactive distillation process,a representative process intensification technology,has been widely applied in the chemical ***,due to the strong interaction between reaction and separation,the extension of reactive dis...
详细信息
Reactive distillation process,a representative process intensification technology,has been widely applied in the chemical ***,due to the strong interaction between reaction and separation,the extension of reactive distillation technology is restricted by the difficulties in process analysis and *** overcome this problem,the design and optimization of reactive distillation have been widely studied and illustrated for plenty of reactive mixtures over the past three *** design and optimization methods of the reactive distillation process are classified into three categories:graphical,optimization-based,and evolutionary/heuristic *** primary objective of this article is to provide an up-to-date review of the existing design and optimization *** and output information,advantages and limitations of each method are stated,the modification and development for original methodologies are also *** on future research on the design and optimization of reactive distillation method are proposed for further research.
Beam splitters are an important part of optical systems and have a wide range of applications in wireless communications and target detection. In this study, bendable structures based on subwavelength nanostructured m...
详细信息
Beam splitters are an important part of optical systems and have a wide range of applications in wireless communications and target detection. In this study, bendable structures based on subwavelength nanostructured metasurfaces with an arbitrary number of beams are constructed. To achieve multiple beams, the phase distribution of a multi-beam splitting metasurface in the 2D direction is calculated directly by an optimized phase recovery algorithm. The cells exhibiting high polarization conversion efficiency are arranged periodically according to the discrete phase. By full-wave simulation, the beam-splitting metasurfaces realize 2 x 2, 4 x 4, and 6 x 6 main beams with high power efficiency and homogeneity from 0.2 THz to 0.37 THz. In addition, the effect of metasurface bending on beam splitting is further investigated using flexible materials that can be fitted into more devices. It is demonstrated that the performance remains optimal at curvatures of less than 1/10,000 mu m-1. Due to the 2D structure, this beam splitter allows electromagnetic waves to be incident at an angle of more than 40 degrees for more demanding applications. Finally, a flexible beam splitter fabrication method based on commercially available polyimide films is proposed and measured, and the results are in agreement with the simulation results. Compared to other beam splitters, the flexible metasurface is fabricated in this paper to reduce the cost, is suitable for large-scale production, and is easy to integrate. These devices can be used in THz optical systems, as well as in mobile applications.
Insulated gate bipolar transistors (IGBTs) are the key component in power electronics, and the intricate relationship between their performance and structural parameters poses a formidable challenge in the design proc...
详细信息
Insulated gate bipolar transistors (IGBTs) are the key component in power electronics, and the intricate relationship between their performance and structural parameters poses a formidable challenge in the design process. This article proposes an automatic optimal design method for IGBT structural parameters to leverage the pretrained machine learning (ML) model to efficiently predict the initial IGBT device's performance, followed by utilizing the differential evolution (DE) algorithm to automatically adjust structural parameters based on the disparity between predicted and expected device performance until the expected performance is achieved. The method is validated in the design of punch-through IGBTs (PT-IGBTs) and trench gate field-stop IGBTs (FS-IGBTs), and the performance of technology computer-aided design (TCAD) simulation of the designed device is similar to the target performance. In particular, the simulation results of the designed FS-IGBT are highly fitted to the datasheet of the commercial device, which verifies the generalizability and effectiveness of the method. In addition, comparative analyses with various algorithms show DE provides the fastest optimization and extraordinary robustness under the exact specifications. Crucially, the proposed design scheme aligns with semiconductor physics. The method simplifies IGBT design without the need for manual tuning and TCAD tool simulation.
Interval model updating is typically performed when gathering data is expensive, time-consuming, or complex and only a limited amount of data is available to perform non-deterministic model updating. In these situatio...
详细信息
ISBN:
(数字)9781624107115
ISBN:
(纸本)9781624107115
Interval model updating is typically performed when gathering data is expensive, time-consuming, or complex and only a limited amount of data is available to perform non-deterministic model updating. In these situations, the fitted intervals will only provide an estimate of the exact interval bounds. This is because the limited data available is unlikely to include any samples that fall precisely on the interval boundaries. In these situations, an analyst could use a metric to assess the accuracy of identified model uncertainties against unseen missing data. Furthermore, when this metric is able to estimate the required amount of data for accurate uncertainty quantification, data-gathering efforts are minimized. This paper defines this metric as the reliability of a data-enclosing set as the probability that future unseen data will fall within the set. Recently, Crespo et al. [1] presented a scenario optimization approach to determine a lower bound for this reliability without having to characterize the underlying distribution of the data generation mechanism. To calculate the reliability, the scenario optimization approach needs the number of hyper-parameters to fit the data enclosing set, the number of samples, and the dimension of the data enclosing set. Once these are obtained, and a confidence level is determined, the approach calculates the lower bound of the reliability. Additionally, analysts can calculate the number of samples required to fit the data enclosing set with predefined lower bound reliability before the measurement campaign. The goals of this paper are to develop the certified interval model updating based on scenario optimization and to apply this to a dynamical modal analysis of a structural finite element model. A four-level building numerical model is used to illustrate the accuracy and the practical application of the developed methodologies.
The transonic buffet is a critical phenomenon that limits the flight envelope of commercial aircraft. For years, RANS-based criteria like the lift-curve-break method have been applied to predict the buffet onset, but ...
详细信息
ISBN:
(数字)9781624107115
ISBN:
(纸本)9781624107115
The transonic buffet is a critical phenomenon that limits the flight envelope of commercial aircraft. For years, RANS-based criteria like the lift-curve-break method have been applied to predict the buffet onset, but it requires flowfield simulations under multiple angles of attack, which is still too time-consuming for optimization. This paper presents a prior-based neural network model to predict pressure profiles under different angles of attack with reference to the one at cruise condition. The model is utilized to replace the offdesign CFD simulations in the lift-curve-break criterion so that only one simulation is needed to predict the buffet onset of an airfoil. It is then employed in a multi-objective genetic algorithm to optimize the buffet onset and the cruise lift-drag ratio simultaneously. To test the optimization procedure, the model is trained on an airfoil database and applied to optimize four airfoils not similar to the training database. The results show that all the optimizations receive positive gains of buffet onset, which affirm that the proposed model and optimization procedure can be reliably employed in search for airfoils with better buffet performance.
Stiffened Variable Angle Tow (VAT) Laminates with optimized curvilinear fiber paths and curvilinear stiffeners are known to significantly improve structural performance over traditional laminates by increasing the buc...
详细信息
ISBN:
(数字)9781624107115
ISBN:
(纸本)9781624107115
Stiffened Variable Angle Tow (VAT) Laminates with optimized curvilinear fiber paths and curvilinear stiffeners are known to significantly improve structural performance over traditional laminates by increasing the buckling loads as a result of tailored stiffness and redistribution of the in-plane loads. optimization of such laminates is highly non-convex and non-linear with a large design space. optimization space can be made convex with the use of lamination parameters;however, that necessitates a second-level optimization for fiber path recovery. Further, the presence of manufacturing defects can highly impact the final performance of the design. Therefore, the current study focuses on designing a robust framework for the optimization of curvilinearly stiffened VAT composite laminates with fiber angles of each layer directly as design variables along with curvilinear stiffener layout and sizing parameters as well as manufacturability constraints. A novel approach is proposed to consider the fiber angles at the nodes of a coarse design mesh as design variables for steering the tow path and interpolate them to a finer analysis mesh using Lagrange shape functions. UGENS subroutine in Abaqus is employed to obtain the sectional forces and moments at each integration point for static and buckling analysis of the laminate. Tie constraints are used to enforce the displacement and rotation compatibility at the stiffener plate interface. Tow path recovery is done to obtain the realizable layout from the design fiber angles using a median based seeding strategy and parallel shifting techniques. The relationship between divergence of the 2D vector field obtained from the tow streamlines and the gap/overlap propagation is used to implement manufacturability constraints in the top-level optimization. Simulia's Isight package is used for integrating different analysis and data I/O components into a single optimization framework. Built-in particle swarm optimization (PSO) in Isig
暂无评论