检索结果-内蒙古大学图书馆

Supercomputing Frontiers and Innovations 2022年第4期9卷 69-84页

作者： Bobkov, Vladimir G. Kozubskaya, Tatiana K. Kudryavtseva, Liudmila N. Tsvetkova, Valeriia O. Keldysh Institute of Applied Mathematics Moscow Russia Dorodnicyn Computing Center FRC CSC RAS Moscow Russia

A novel hybrid dynamic mesh redistribution – immersed boundary method for simulation of turbulent flows around rotating obstacles of complex geometry and analysis of tonal acoustics is proposed. The feasibility of the approach is demonstrated by considering a drone propeller problem. The results of three-dimensional Reynolds-averaged Navier–Stokes simulations using the proposed approach are compared to the results of body-fitted unstructured simulations in noninertial reference frame. The dynamic mesh redistribution method allows the reposition of mesh points taking into account the shape of the moving body while retaining the mesh topology. The cell size and quality of the dynamically redistributed mesh strongly depend on the curvature of the body surface. The position and shape of the moving obstacle is prescribed by a distance function defined on an adaptive octree. The results of simulations using the proposed method are in good agreement with both the results of body-fitted simulations and the experimental data © The Authors 2022. This paper is published with open access at ***

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

A roulette wheel-based pruning method to simplify cumbersome deep neural networks

引用

Neural computing and Applications 2024年第22期36卷 13915-13933页

作者： Chan, Kit Yan Yiu, Ka Fai Cedric Guo, Shan Jiang, Huimin School of Electrical Engineering Computing and Mathematics Sciences Curtin University Bentley Australia Department of Applied Maths The Hong Kong Polytechnic University Hong Kong School of Business Macau University of Science and Technology China

Deep neural networks (DNNs) have been applied in many pattern recognition or object detection applications. DNNs generally consist of millions or even billions of parameters. These demanding computational storage and requirements impede deployments of DNNs in resource-limited devices, such as mobile devices, micro-controllers. Simplification techniques such as pruning have commonly been used to slim DNN sizes. Pruning approaches generally quantify the importance of each component such as network weight. Weight values or weight gradients in training are commonly used as the importance metric. Small weights are pruned and large weights are kept. However, small weights are possible to be connected with significant weights which have impact to DNN outputs. DNN accuracy can be degraded significantly after the pruning process. This paper proposes a roulette wheel-like pruning algorithm, in order to simplify a trained DNN while keeping the DNN accuracy. The proposed algorithm generates a branch of pruned DNNs which are generated by a roulette wheel operator. Similar to the roulette wheel selection in genetic algorithms, small weights are more likely to be pruned but they can be kept;large weights are more likely to be kept but they can be pruned. The slimmest DNN with the best accuracy is selected from the branch. The performance of the proposed pruning algorithm is evaluated by two deterministic datasets and four non-deterministic datasets. Experimental results show that the proposed pruning algorithm generates simpler DNNs while DNN accuracy can be kept, compared to several existing pruning approaches. © The Author(s) 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

On a class of nonlinear elliptic problems with double phase effects and laplacian-type operators in Musielak-Orlicz-Sobolev spaces

引用

Annali dell'Universita di Ferrara 2025年第2期71卷 1-20页

作者： Moujani, Hasna El Mfadel, Ali Kassidi, Abderrazak El Omari, M.’hamed Laboratory of Applied Mathematics and Scientific Computing Sultan Moulay Slimane University Beni Mellal Morocco Higher School of Technology Sultan Moulay Slimane University Khenifra Morocco

This paper addresses the existence of weak solutions for a class of nonlinear Dirichlet boundary value problems governed by a double phase operator. The main results are established under precise assumptions on the nonlinearity of the second term. The analysis is carried out within the advanced framework of Musielak-Orlicz-Sobolev spaces, which accommodate the variable growth conditions induced by the double phase structure. To handle challenges related to weak convergence, we employ the Young measures technique. Additionally, approximate solutions are systematically constructed through the Galerkin method, ensuring a rigorous and structured approach to the problem. © The Author(s) under exclusive license to Università degli Studi di Ferrara 2025.

关键词： (α,β)-Laplacian-like operator Fractional double phase problem Galerkin method Weak solution Young measure

来源：评论

学校读者我要写书评

暂无评论

Physics-informed neural networks with residual/gradient-based adaptive sampling methods for solving partial differential equations with sharp solutions

引用

applied mathematics and Mechanics(English Edition) 2023年第7期44卷 1069-1084页

作者： Zhiping MAO Xuhui MENG School of Mathematical Sciences Fujian Provincial Key Laboratory of Mathematical Modeling and High-Performance Scientific ComputingXiamen UniversityXiamen 361005Fujian ProvinceChina Institute of Interdisciplinary Research for Mathematics and Applied Science School of Mathematics and StatisticsHuazhong University of Science and TechnologyWuhan 430074China

We consider solving the forward and inverse partial differential equations(PDEs)which have sharp solutions with physics-informed neural networks(PINNs)in this *** particular,to better capture the sharpness of the solution,we propose the adaptive sampling methods(ASMs)based on the residual and the gradient of the *** first present a residual only-based ASM denoted by ASMⅠ.In this approach,we first train the neural network using a small number of residual points and divide the computational domain into a certain number of sub-domains,then we add new residual points in the sub-domain which has the largest mean absolute value of the residual,and those points which have the largest absolute values of the residual in this sub-domain as new residual *** further develop a second type of ASM(denoted by ASMⅡ)based on both the residual and the gradient of the solution due to the fact that only the residual may not be able to efficiently capture the sharpness of the *** procedure of ASMⅡis almost the same as that of ASMⅠ,and we add new residual points which have not only large residuals but also large *** demonstrate the effectiveness of the present methods,we use both ASMⅠand ASMⅡto solve a number of PDEs,including the Burger equation,the compressible Euler equation,the Poisson equation over an Lshape domain as well as the high-dimensional Poisson *** has been shown from the numerical results that the sharp solutions can be well approximated by using either ASMⅠor ASMⅡ,and both methods deliver much more accurate solutions than the original PINNs with the same number of residual ***,the ASMⅡalgorithm has better performance in terms of accuracy,efficiency,and stability compared with the ASMⅠ*** means that the gradient of the solution improves the stability and efficiency of the adaptive sampling procedure as well as the accuracy of the ***,we also employ the similar adaptive sampling technique fo

关键词： physics-informed neural network(PINN) adaptive sampling high-dimension L-shape Poisson equation accuracy

来源：评论

学校读者我要写书评

暂无评论

Human-Machine Pilot Navigation Method Using Nonlinear Model Predictive Control, Simulation and Inflight Testing 43

Human-Machine Pilot Navigation Method Using Nonlinear Model ...

引用

43rd AIAA DATC/IEEE Digital Avionics Systems Conference, DASC 2024

作者： Bertoncini, Jeremy Dudek, Adrian Ostler, Johannes Russ, Martin Gerdts, Matthias Institute of Applied Mathematics and Scientific Computing Institute of Flight Systems University of the Bundeswehr Munich Department of Aerospace Engineering Neubiberg85577 Germany

ISBN: (纸本)9798350349610

In military or civil aviation, depending on the mission to be accomplished, an aircraft may need to avoid prohibited or dangerous areas that are not always within line of sight. However, these areas can be identified by external information and communicated from a ground station. The aim of this work is to provide an optimal control method that generates trajectories and assists the pilot in navigating. Using a human-machine interface, the pilot has access to a digital twin of the actual airspace, where the route is modeled using a tunnel-in-the-sky method. The research can be applied to airborne mission management, airport maneuver management or military operations. The path planning task is formulated as an optimal control problem and solved on a fixed time horizon using a nonlinear model predictive controller (NMPC) [5]. © 2024 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Collective Certified Robustness against Graph Injection Attacks 41

Collective Certified Robustness against Graph Injection Atta...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Lai, Yuni Pan, Bailin Chen, Kaihuang Yuan, Yancheng Zhou, Kai Department of Computing The Hong Kong Polytechnic University Hong Kong Department of Applied Mathematics The Hong Kong Polytechnic University Hong Kong

We investigate certified robustness for GNNs under graph injection attacks. Existing research only provides sample-wise certificates by verifying each node independently, leading to very limited certifying performance. In this paper, we present the first collective certificate, which certifies a set of target nodes simultaneously. To achieve it, we formulate the problem as a binary integer quadratic constrained linear programming (BQCLP). We further develop a customized linearization technique that allows us to relax the BQCLP into linear programming (LP) that can be efficiently solved. Through comprehensive experiments, we demonstrate that our collective certification scheme significantly improves certification performance with minimal computational overhead. For instance, by solving the LP within 1 minute on the Citeseer dataset, we achieve a significant increase in the certified ratio from 0.0% to 81.2% when the injected node number is 5% of the graph size. Our paper marks a crucial step towards making provable defense more practical. Our source code is available at https://***/Yuni-Lai/CollectiveLPCert. Copyright 2024 by the author(s)

关键词： Integer linear programming

来源：评论

学校读者我要写书评

暂无评论

On Error-Based Step Size Control for Discontinuous Galerkin Methods for Compressible Fluid Dynamics

引用

应用数学与计算数学学报 2025年第1期7卷 3-39页

作者： Hendrik Ranocha Andrew R.Winters Hugo Guillermo Castro Lisandro Dalcin Michael Schlottke-Lakemper Gregor J.Gassner Matteo Parsani Applied Mathematics University of HamburgBundesstr.5520146 HamburgGermany Department of Mathematics Applied Mathematics Linköping UniversityLinköpingSweden Extreme Computing Research Center(ECRC) Computer Electrical and Mathematical Science and Engineering Division(CEMSE)King Abdullah University of Science and Technology(KAUST)Thuwal 23955-6900Saudi Arabia Applied and Computational Mathematics RWTH Aachen UniversityAachenGermany High-Performance Computing Center Stuttgart University of StuttgartStuttgartGermany Department of Mathematics and Computer Science University of CologneCologneGermany Center for Data and Simulation Science University of CologneCologneGermany Extreme Computing Research Center(ECRC) Computer Electrical and Mathematical Science and Engineering Division(CEMSE)King Abdullah University of Science and Technology(KAUST)Thuwal 23955-6900Saudi Arabia Physical Science and Engineering Division(PSE) King Abdullah University of Science and Technology(KAUST)Thuwal 23955-6900Saudi Arabia

We study a temporal step size control of explicit Runge-Kutta(RK)methods for com-pressible computational fluid dynamics(CFD),including the Navier-Stokes equations and hyperbolic systems of conservation laws such as the Euler *** demonstrate that error-based approaches are convenient in a wide range of applications and compare them to more classical step size control based on a Courant-Friedrichs-Lewy(CFL)*** numerical examples show that the error-based step size control is easy to use,robust,and efficient,e.g.,for(initial)transient periods,complex geometries,nonlinear shock captur-ing approaches,and schemes that use nonlinear entropy *** demonstrate these properties for problems ranging from well-understood academic test cases to industrially relevant large-scale computations with two disjoint code bases,the open source Julia pack-ages *** with *** and the C/Fortran code SSDC based on PETSc.

关键词： Explicit Runge-Kutta(RK)methods Step size control Compressible fluid dynamics Adaptivity in space and time Shock capturing

来源：评论

学校读者我要写书评

暂无评论

On intuitionistic fuzzy laplace transforms for solving intuitionistic fuzzy partial Volterra integro-differential equations 8

On intuitionistic fuzzy laplace transforms for solving intui...

引用

8th International Conference on Optimization and Applications, ICOA 2022

作者： Belhallaj, Zineb Elomari, Mhamed Melliani, Said Chadli, Lalla Saadia Laboratory of Applied Mathematics and Scientific Computing Beni mellal Morocco

ISBN: (数字)9781665476812

ISBN: (纸本)9781665476812

In this paper, our purpose is to solve the intuitionistic fuzzy convolution Volterra partial integro-differential equation using the intuitionistic fuzzy Laplace transform (FLTM) method under strongly Hukuhara differentiability, the intuitionistic fuzzy convolution operator is proposed and the associated theorem is given which is helpful for solving IFPVIDEs. Finally, the effectiveness and applicability of the presented method is studied with the help of a numerical example. © 2022 IEEE.

关键词： Integrodifferential equations

来源：评论

学校读者我要写书评

暂无评论

Investigation of transonic aerodynamics on a triple-delta wing in side slip conditions

引用

CEAS Aeronautical Journal 2022年第2期13卷 453-470页

作者： Di Fabbio, Tony Tangermann, Eike Klein, Markus Numerical Methods in Aerospace Engineering Institute of Applied Mathematics and Scientific Computing Bundeswehr University Munich Neubiberg85577 Germany

The vortex-dominated flow around the triple-delta wing ADS-NA2-W1 aircraft is investigated in order to achieve a better understanding of the flow physics phenomena that occur over the aircraft particularly at the transonic speed condition. Both URANS and scale-resolving DDES have been employed in order to explore the range of suitability of current CFD methods. The Spalart–Allmaras One-Equation Model with corrections for negative turbulent viscosity and Rotation/Curvature (SA-negRC) is employed to close the RANS equations, whereas the SAneg-based DDES model is applied in the scale-resolving computations. The DLR TAU-Code is used to perform the numerical simulations. The deficiencies of the URANS results are illustrated and promising improvements are reached employing the SAneg-DDES numerical method. The hybrid method results show great advancement in the prediction of the multiple-delta wing flow by revealing physical aspects which have not been seen from URANS with sufficient accuracy like vortex–vortex interaction and shock-vortex interaction. These phenomena furthermore explain in a clear way the improved prediction of the surface pressure coefficient over the aircraft and consequently of the aerodynamic force and moment coefficients. © 2022, The Author(s).

关键词： Vortex flow

来源：评论

学校读者我要写书评

暂无评论

Degree-Based Entropy Descriptors of Graphenylene Using Topological Indices

引用

Computer Modeling in Engineering & Sciences 2023年第10期137卷 939-964页

作者： M.C.Shanmukha Sokjoon Lee A.Usha K.C.Shilpa Muhammad Azeem Department of Mathematics Bapuji Institute of Engineering&TechnologyDavanagere577004India Department of Computer Engineering(Smart Security) Gachon UniversitySeongnam13120South Korea Department of Mathematics Alliance School of Applied MathematicsAlliance UniversityBangalore562106India Department of Computer Science and Engineering Bapuji Institute of Engineering&TechnologyDavanagere577004India Department of Mathematics Riphah Institute of Computing and Applied SciencesRiphah International UniversityLahore54660Pakistan

Graph theory plays a significant role in the applications of chemistry,pharmacy,communication,maps,and aeronautical *** molecules of chemical compounds are modelled as a graph to study the properties of the *** geometric structure of the compound relates to a few physical properties such as boiling point,enthalpy,π-electron energy,andmolecular *** article aims to determine the practical application of graph theory by solving one of the interdisciplinary problems describing the structures of benzenoid hydrocarbons and *** topological index is an invariant of a molecular graph associated with the chemical structure,which shows the correlation of chemical structures using many physical,chemical properties and biological *** study aims to introduce some novel degree-based entropy descriptors such as ENTSO,ENTGH,ENTHG,ENTSS,ENTNSO,ENTNReZ1,ENTNReZ2 and ENTNSS using the respective topological ***,the above-mentioned entropy measures and physico-chemical properties of benzenoid hydrocarbons are fitted using linear regression models and calculated for graphenylene structure.

关键词： Topological descriptors weighted entropy graphenylene

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：