检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Peng, Rui Xu, Wangze Tang, Luyang Liao, Liwei Jiao, Jianbo Wang, Ronggang Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology Peking University Shenzhen Graduate School China Peng Cheng Laboratory China University of Birmingham United Kingdom

Despite the substantial progress of novel view synthesis, existing methods, either based on the Neural Radiance Fields (NeRF) or more recently 3D Gaussian Splatting (3DGS), suffer significant degradation when the input becomes sparse. Numerous efforts have been introduced to alleviate this problem, but they still struggle to synthesize satisfactory results efficiently, especially in the large scene. In this paper, we propose SCGaussian, a Structure Consistent Gaussian Splatting method using matching priors to learn 3D consistent scene structure. Considering the high interdependence of Gaussian attributes, we optimize the scene structure in two folds: rendering geometry and, more importantly, the position of Gaussian primitives, which is hard to be directly constrained in the vanilla 3DGS due to the non-structure property. To achieve this, we present a hybrid Gaussian representation. Besides the ordinary non-structure Gaussian primitives, our model also consists of ray-based Gaussian primitives that are bound to matching rays and whose optimization of their positions is restricted along the ray. Thus, we can utilize the matching correspondence to directly enforce the position of these Gaussian primitives to converge to the surface points where rays intersect. Extensive experiments on forward-facing, surrounding, and complex large scenes show the effectiveness of our approach with state-of-the-art performance and high efficiency. Code is available at https://***/prstrive/SCGaussian. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Advancements in Coupled Aeropropulsive Design optimization for High-Bypass Turbofan Engines

Advancements in Coupled Aeropropulsive Design Optimization f...

引用

AIAA Aviation and Aeronautics Forum and Exposition, AIAA AVIATION Forum 2023

作者： Lamkin, Andrew H. R. Yildirim, Anil Martins Proff, Joaquim R. R. A. Wukie, Nathan A. Department of Aerospace Engineering University of Michigan Ann ArborMI48109 United States Multidisciplinary Science and Technology Ceneter Air Force Research Laboratory Wright-Patterson AFB United States

ISBN: (数字)9781624107047

ISBN: (纸本)9781624107047

To improve performance and reduce fuel consumption, we must address tightly connected aero-propulsive effects in the development of new and existing propulsion technologies. Aero propulsive design optimization considers the multidisciplinary coupled interactions between aerodynamics, thermodynamics, and geometry. Mixed-fidelity aero-propulsive methods integrate high-fidelity aerodynamic solvers with zero-dimensional thermodynamic cycle modeling. Combined with gradient-based optimization, this approach is a computationally efficient design tool that can accommodate large design spaces with many design variables and constraints. Previously, we developed a novel hybrid aero-propulsive coupling method for turbofan engines and demonstrated its feasibility using a single-design-point problem. In this work, we improve upon the prior approach and perform the first successful coupled aero-propulsive optimization of a high-bypass turbofan. We analyze the optimized turbofan design and validate the corrections to the hybrid coupling scheme. The updated coupling methods are a significant advancement in aero-propulsive optimization that enable the design of tightly integrated propulsion systems considering thermodynamic and aerodynamic performance. © 2023, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Aerodynamics

来源：评论

学校读者我要写书评

暂无评论

Enhanced metaheuristic evolution strategy for reliability based structural optimization of bridges

引用

Journal of Building Pathology and Rehabilitation 2025年第1期10卷 1-13页

作者： Lamouri, Hicham El Mkhalet, Mouna Lamdouar, Nouzha Department of Civil Engineering Civil Engineering and Construction Laboratory Mohammadia School of Engineers Mohammed V University Rabat Morocco

Metaheuristic methods are optimization techniques designed to find good solutions for complex problems, especially when traditional methods are impractical. These algorithms provide general approaches that can be applied to a wide range of problems, aiming to find solutions in a reasonable amount of time while guaranteeing the best possible outcome. Among these, Evolutionary Algorithms, which include methods like Genetic Algorithms and Evolution Strategy, are particularly popular for their ability to handle optimization tasks and their bio-inspiration aspect. This paper proposes a methodology called Evolution Strategy based Reliability optimization (ESRO), which integrates Evolution Strategy with reliability constraints defined by a probability of failure associated with the limit state function of the studied structure. The results obtained from the ESRO approach are compared with those from another methodology proposed by the authors, termed Reliability Genetic Algorithm optimization (RGAO). Two case studies illustrate these methodologies: the first concerns the reliability optimization of a bridge pier subjected to seismic loading based on response spectrum analysis. The reliability optimization problem is formulated considering minimum design requirements, buckling limits, and stress constraints to determine the optimal dimensions for the structural configuration. The second case focuses on optimizing the height of a prestressed bridge deck slab while ensuring its reliability by adhering to prestressing geometrical conditions. This study enhances the understanding of metaheuristic techniques in structural reliability analysis and optimization, providing valuable insights for researchers and engineers in the field. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Bridge engineering Evolution strategy Genetic algorithms Prestressed concrete structures Structural dynamics Structural optimization Structural reliability

来源：评论

学校读者我要写书评

暂无评论

Optimal design of uniform magnetic field coils within irregular magnetic shielding based on coupled SNOPT-finite element method analysis 3

Optimal design of uniform magnetic field coils within irregu...

引用

2024 3rd International Conference on Aerospace, Aerodynamics and Mechatronics Engineering, AAME 2024

作者： Jie, Shaofeng Liu, Zhanchao Zhang, Shuai Wang, Jingsong Wu, Zekun Zhao, Kangnan School of Instrumentation and Optoelectronic Engineering Beihang University Beijing100191 China Hefei National Laboratory Hefei230026 China

The highly uniform magnetic field coil is one of the most important components of miniaturized atomic inertial sensors. However, the development of the magnetic field model of coils in magnetic shielding with irregular shapes is difficult in practice. In this study, an optimization method for the design of coil structure parameters based on hybrid modelling with the finite element method and the SNOPT algorithm was proposed. The finite element method was used to characterize the geometric structure of the magnetic shield accurately and incorporate the characteristic B-H parameters of the material into the optimization model to improve the design accuracy. The three-dimensional model was reduced to two dimensions, and the parameters of the coil structure were optimized by an intelligent algorithm, which improved the solution efficiency. The effectiveness of the proposed approach was demonstrated by optimizing the design of a solenoid coil inside the cylindrical magnetic shielding with holes and stovepipes, which reduced the design error caused by the magnetic leakage flux. © Published under licence by IOP Publishing Ltd.

关键词： Magnetic leakage

来源：评论

学校读者我要写书评

暂无评论

A Novel Class of Energy-Preserving Runge-Kutta methods for the Korteweg-de Vries Equation

引用

Numerical Mathematics(Theory,methods and Applications) 2022年第3期15卷 768-792页

作者： Yue Chen Yuezheng Gong Qi Hong Chunwu Wang Department of Mathematics Nanjing University of Aeronautics and AstronauticsNanjing 211106China Key Laboratory of Mathematical Modelling and High Performance Computing of Air Vehicles(NUAA) MIITNanjing 211106China Jiangsu Key Laboratory for Numerical Simulation of Large Scale Complex Systems Nanjing 210023China

In this paper,we present a quadratic auxiliary variable approach to develop a new class of energy-preserving Runge-Kutta methods for the Korteweg-de Vries *** quadratic auxiliary variable approach is first proposed to reformulate the original model into an equivalent system,which transforms the energy conservation law of the Korteweg-de Vries equation into two quadratic invariants of the reformulated *** the symplectic Runge-Kutta methods are directly employed for the reformulated model to arrive at a new kind of time semi-discrete schemes for the original *** consistent initial conditions,the proposed methods are rigorously proved to maintain the original energy conservation law of the Korteweg-de Vries *** addition,the Fourier pseudo-spectral method is used for spatial discretization,resulting in fully discrete energy-preserving *** implement the proposed methods effectively,we present a very efficient iterative technique,which not only greatly saves the calculation cost,but also achieves the purpose of practically preserving *** numerical results are addressed to confirm the expected order of accuracy,conservative property and efficiency of the proposed algorithms.

关键词： Quadratic auxiliary variable approach symplectic Runge-Kutta scheme energypreserving algorithm Fourier pseudo-spectral method

来源：评论

学校读者我要写书评

暂无评论

Comparison of debris flow susceptibility assessment methods:support vector machine,particle swarm optimization,and feature selection techniques

引用

Journal of Mountain Science 2024年第2期21卷 397-412页

作者： ZHAO Haijun WEI Aihua MA Fengshan DAI Fenggang JIANG Yongbing LI Hui Key Laboratory of Shale Gas and Geoengineering Institute of Geology and GeophysicsChinese Academy of SciencesBeijing 100029China Innovation Academy for Earth Science Chinese Academy of SciencesBeijing 100029China Hebei Province Key Laboratory of Sustained Utilization&Development of Water Recourse Hebei GEO UniversityShijiazhuang 050031China School of Water Resources and Environment Hebei GEO UniversityShijiazhuang 050031China The Sixth Geological Brigade of Geological Mineral Exploration and Development Bureau of Hebei Province Shijiazhuang 050085China

The selection of important factors in machine learning-based susceptibility assessments is crucial to obtain reliable susceptibility *** this study,metaheuristic optimization and feature selection techniques were applied to identify the most important input parameters for mapping debris flow susceptibility in the southern mountain area of Chengde City in Hebei Province,China,by using machine learning *** total,133 historical debris flow records and 16 related factors were *** support vector machine(SVM)was first used as the base classifier,and then a hybrid model was introduced by a two-step ***,the particle swarm optimization(PSO)algorithm was employed to select the SVM model ***,two feature selection algorithms,namely principal component analysis(PCA)and PSO,were integrated into the PSO-based SVM model,which generated the PCA-PSO-SVM and FS-PSO-SVM models,*** statistical metrics(accuracy,recall,and specificity)and the area under the receiver operating characteristic curve(AUC)were employed to evaluate and validate the performance of the *** results indicated that the feature selection-based models exhibited the best performance,followed by the PSO-based SVM and SVM ***,the performance of the FS-PSO-SVM model was better than that of the PCA-PSO-SVM model,showing the highest AUC,accuracy,recall,and specificity values in both the training and testing *** was found that the selection of optimal features is crucial to improving the reliability of debris flow susceptibility assessment ***,the PSO algorithm was found to be not only an effective tool for hyperparameter optimization,but also a useful feature selection algorithm to improve prediction accuracies of debris flow susceptibility by using machine learning *** high and very high debris flow susceptibility zone appropriately covers 38.01%of the study area,where debris flow may occur under intens

关键词： Chengde Feature selection Support vector machine Particle swarm optimization Principal component analysis Debris flow susceptibility

来源：评论

学校读者我要写书评

暂无评论

An intelligent mesh-smoothing method with graph neural networks

引用

Frontiers of Information Technology & Electronic Engineering 2025年第3期26卷 367-384页

作者： Zhichao WANG Xinhai CHEN Junjun YAN Jie LIU Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense TechnologyChangsha 410073China Laboratory of Digitizing Software for Frontier Equipment National University of Defense TechnologyChangsha 410073China

In computational fluid dynamics(CFD),mesh-smoothing methods are widely used to refine the mesh quality for achieving high-precision numerical ***,optimization-based smoothing is used for high-quality mesh smoothing,but it incurs significant computational *** works have improved its smoothing efficiency by adopting supervised learning to learn smoothing methods from high-quality ***,they pose difficulties in smoothing the mesh nodes with varying degrees and require data augmentation to address the node input sequence ***,the required labeled high-quality meshes further limit the applicability of the proposed *** this paper,we present graph-based smoothing mesh net(GMSNet),a lightweight neural network model for intelligent mesh *** adopts graph neural networks(GNNs)to extract features of the node’s neighbors and outputs the optimal node *** smoothing,we also introduce a fault-tolerance mechanism to prevent GMSNet from generating negative volume *** a lightweight model,GMSNet can effectively smooth mesh nodes with varying degrees and remain unaffected by the order of input data.A novel loss function,MetricLoss,is developed to eliminate the need for high-quality meshes,which provides stable and rapid convergence during *** compare GMSNet with commonly used mesh-smoothing methods on two-dimensional(2D)triangle *** results show that GMSNet achieves outstanding mesh-smoothing performances with 5%of the model parameters compared to the previous model,but offers a speedup of 13.56 times over the optimization-based smoothing.

关键词： Unstructured mesh Mesh smoothing Graph neural network optimization-based smoothing

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-based Multi-Scenario Multi-Scale Economic Scheduling for Integrated Energy systems 6

Deep Reinforcement Learning-based Multi-Scenario Multi-Scale...

引用

6th International Conference on Energy systems and Electrical Power, ICESEP 2024

作者： Li, Guangxi Zhao, Qingsheng Han, Xiaoqing Li, Tingjun Taiyuan University of Technology Shanxi Key Laboratory of Power System Operation and Control Taiyuan China

ISBN: (纸本)9798350353563

The integrated energy system (IES) with multi-energy coupling and gradient utilization has become an important means to help realize the goal of 'double carbon'. The optimal operation of IES is a nonlinear, nonconvex and complex problem. With the gradual increase of intermittent energy and load uncertainty, traditional scheduling methods are limited to fixed physical models and parameter settings, which make it difficult to quickly and accurately obtain optimal scheduling strategies. In this paper, we propose a distributed proximal policy optimization (DPPO) algorithm to train the IES optimal scheduling model offline and solve the optimization online, which transforms the physical scheduling problem into a reinforcement learning sequential decision-making problem, and adaptively learns the scheduling policy through continuous interaction between the agent and the integrated energy system environment, and the multi-threaded structure enhances the exploration ability of the reinforcement learning agent in the complex environment. Example simulations show that online applications do not need to rely on accurate modeling of the physical model of the IES to achieve fast scheduling decisions in multiple scenarios and scales. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

An Innovative optimization Framework for Aerodynamic Shape optimization Using Deep Neural Network 3

An Innovative Optimization Framework for Aerodynamic Shape O...

引用

3rd International Symposium on Aerospace Engineering and systems, ISAES 2024

作者： Wu, Pin Zhou, Zhu Liu, Zhitao Song, Chao School of Computer Engineering and Science Shanghai University Shanghai200444 China China Aerodynamics Research And Development Center State Key Laboratory of Aerodynamics Sichuan Mianyang621000 China

ISBN: (纸本)9798350350418

It is necessary to optimize the design method of the airfoil aerodynamic shape for better performance while meeting the design requirements. However, current mainstream design methods for aerodynamic shape are based on CFD model simulations and rely heavily on manual experience design, which are very time-consuming. Therefore, we propose an innovative optimization framework based on multi-task learning for Aerodynamic Shape optimization. Firstly, Bezier-ACGAN is used to intelligently parametrize the airfoil shape. Secondly, the MMOE-MF surrogate model is used to predict different-fidelity of aerodynamic data. Finally, GA optimizer selects the optimal shape that satisfies the optimization objective by adjusting the latent variables of Bezier-ACGAN. The performance of the proposed optimization framework is verified by two optimization design cases and results show that the predicted results of the optimal airfoils agree with the results of high-fidelity simulation well. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Machine-Learning modelling of a Fluid Flow in a Two-Dimensional Channel 15

Machine-Learning Modelling of a Fluid Flow in a Two-Dimensio...

引用

15th International Conference on Information, Intelligence, systems and Applications, IISA 2024

作者： Aravanis, Theofanis Chrimatopoulos, Grigorios Xenos, Michalis Tzirtzilakis, Efstratios E. University of the Peloponnese Fluid Mechanics and Turbomachinery Laboratory Department of Mechanical Engineering Patras Greece University of Ioannina Department of Mathematics Ioannina Greece

ISBN: (纸本)9798350368833

Over the past decade, the integration of Artificial Neural Networks (ANNs) has garnered significant interest, capitalizing on their ability to discern intricate patterns within data. Focused on enhancing computational efficiency, this article explores the application of ANNs in fluid-dynamics simulations, particularly in modelling a benchmark problem of fluid flow in a two-dimensional (2D) channel. Leveraging a Multilayer Perceptron trained on Finite Volume Method numerical data, for both interpolation and extrapolation estimations and various grid resolutions, our findings demonstrate the ANN's prowess as a swift and accurate surrogate for traditional numerical methods. Overall, the results of this work mark a pioneering step towards leveraging Machine Learning for modelling complex relationships in fluids phenomena, promising transformative advancements in Computational Fluid Dynamics. © 2024 IEEE.

关键词： Computational fluid dynamics

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：