检索结果-内蒙古大学图书馆

Evolutionary neural architecture search for automatically designing CNN-GRU-Attention neural networks for turntable servo systems

引用

Expert systems with Applications 2025年 283卷

作者： Xie, Cheng Xue, Bing Yang, Mingyi Zhang, Mengjie Xu, Zhigang Wang, Junyi Chen, Songlin Liu, Yang Shenyang Institute of Automation Chinese Academy of Sciences Liaoning Shenyang110169 China Centre for Data Science and Artificial Intelligence & School of Engineering and Computer Science Victoria University of Wellington Wellington6140 New Zealand University of Chinese Academy of Sciences Beijing101408 China National Key Laboratory of Modeling and Simulation for Complex Systems Harbin Institute of Technology Heilongjiang Harbin150001 China

Turntable servo systems are important experimental devices utilized in the semi-physical simulation and testing of aircraft. Building a model for turntable servo systems, which can accurately predict their operating states or behaviors, is important for the development and debugging of the whole servo control system. However, servo systems usually have complex nonlinear characteristics and external disturbances, which brings challenges to the accurate modeling of them. Therefore, this paper develops a modeling method for turntable servo systems by using CNN-GRU-Attention hybrid neural network models. The CNN-GRU-Attention model is used for compensating the nonlinear terms of the known dynamics model, thus effectively improving the modeling accuracy. Considering the complex architectures of the above hybrid model, an evolutionary neural architecture search (ENAS) algorithm is proposed accordingly, which can automatically design the architecture of the CNN-GRU-Attention models. During the designing process, a variable-length encoding strategy is proposed to represent the possible architectures, and novel crossover and mutation operators are proposed accordingly for the evolution of individuals. In addition, the real-time constraints are considered in the design of the search space, so that all the searched models can meet the real-time requirements. The experimental results show the CNN-GRU-Attention models obtained by the proposed ENAS algorithm achieve superior prediction performance over the peer competitors in most tasks. The effectiveness of the proposed method is further verified by analyzing the convergence and the search results. © 2025

关键词： Synchros

来源：评论

学校读者我要写书评

暂无评论

Dynamic analysis of rigid-flexible coupling spacecraft based on Euler parameters

引用

Scientific Reports 2025年第1期15卷 1-12页

作者： Ji, Yi Zhang, Huan School of Astronautics Harbin Institute of Technology Harbin 150001 China Frontier Science Center for Interaction between Space Environment and Matter Harbin 150001 China National Key Laboratory of Modeling and Simulation for Complex Systems Harbin 150001 China MOE Key Laboratory of Dynamics and Control of Flight Vehicle Beijing Institute of Technology Beijing 100081 China

With the development of aerospace technology, rigid-flexible coupling spacecraft with strong nonlinearity dominates, bringing huge challenges for numerical tools. This paper aims to accurately and quickly analyze the dynamic behavior of rigid-flexible coupling spacecraft. In our work, rigid body and flexible body are both described by Euler parameters for avoiding singular angles. Then, for this type of strong nonlinear dynamic system, the BN-stable method that is unconditionally stable for nonlinear initial value problems proposed by the first author is introduced to solve the transient responses. To keep the accuracy of the numerical rotation matrix, the relation between the angular velocity and Euler parameters, and the constraint in the level of velocity, are introduced to reformulate the original BN-stable method. Through the dynamic analysis for rigid satellite bodies and flexible solar wings, we find that the proposed strategy can effectively simulate the dynamic responses of spacecraft, and compared to the currently popular strategy, our strategy enjoys considerable advantages in accuracy, stability, and dissipation. © The Author(s) 2025.

关键词： BN-stability Dynamic analysis Euler parameters Rigid-flexible coupling Rotation matrix

来源：评论

学校读者我要写书评

暂无评论

A constructive method for approximating trigonometric functions and their integrals

引用

Applied Mathematics(A Journal of Chinese Universities) 2020年第3期35卷 293-307页

作者： CHEN Xiao-diao WANG Long-quan WANG Yi-gang Key Laboratory of Complex Systems Modeling and Simulation Hangzhou Dianzi UniversityHangzhou 310027China

This paper presents an interpolation-based method(IBM)for approximating some trigonometric functions or their integrals as *** provides two-sided bounds for each function,which also achieves much better approximation effects than those of prevailing *** principle,the IBM can be applied for bounding more bounded smooth functions and their integrals as well,and its applications include approximating the integral of sin(x)/x function and improving the famous square root inequalities.

关键词： Padéapproximant trigonometric function constructive method interpolation-based method two-sided bounds

来源：评论

学校读者我要写书评

暂无评论

A PARALLEL DOMAIN DECOMPOSITION METHOD FOR SOLVING ELLIPTIC EQUATIONS ON MANIFOLDS

引用

SIAM Journal on Scientific Computing 2025年第2期47卷 A916-A942页

作者： Qin, Lizhen Wang, Feng Wang, Yun School of Mathematics Nanjing University Nanjing210093 China Key Laboratory of Numerical Simulation of Large Scale Complex Systems Nanjing Normal University Ministry of Education Nanjing210023 China Jiangsu International Joint Laboratory of Big Data Modeling Computing and Application Nanjing Normal University Nanjing210023 China School of Mathematical Sciences Nanjing Normal University Nanjing210023 China School of Mathematical Sciences Center for Dynamical Systems and Differential Equations Soochow University Suzhou215006 China

We propose a new numerical domain decomposition method for solving elliptic equations on compact Riemannian manifolds. One advantage of this method is its ability to bypass the need for global triangulations or grids on the manifolds. Additionally, it features a highly parallel iterative scheme. To verify its efficacy, we conduct numerical experiments on some four-dimensional manifolds without and with boundary. © 2025 Society for Industrial and Applied Mathematics Publications. All rights reserved.

关键词： Domain decomposition methods

来源：评论

学校读者我要写书评

暂无评论

Enhancing realism in LiDAR scene generation with CSPA-DFN and linear cross-attention via Diffusion Transformer model

引用

Neural Networks 2025年 189卷 107503页

作者： Ye, Shaoxun Di, Xiaoguang Liao, Ming Li, Ximing Control and Simulation Center Harbin Institute of Technology Harbin150080 China National Key Laboratory of Modeling and Simulation for Complex Systems Harbin150080 China

Point cloud diffusion models have found extensive applications in autonomous driving and robotics. However, there is still a big gap between their generated LiDAR scene samples and real-world data in terms of visual quality. This discrepancy primarily arises from the loss of detailed information during the decoding process from latent space and the lack of guidance from global 3D structural information in the point cloud generation process, leading to distortions and artifacts in LiDAR scene samples. In this paper, we propose a novel LiDAR Diffusion Transformer Model that integrates Channel-Spatial Parallel Attention and Dilation Fusion Network (CSPA-DFN) with a linear cross-attention post-processing module to refine the generated LiDAR scene samples. Specifically, CSPA-DFN is designed to simultaneously emphasize detailed features across different channels and spatial locations in parallel, leveraging multi-scale dilated convolutions and channel grouping to preserve and enhance these detailed features. In order to provide global 3D structural information and balance performance and efficiency, we design a post-processing module that fuses voxelized features and range images using a linear ReLU cross-attention mechanism. Our approach is evaluated on the unconditional generation task using the KITTI-360 and nuScenes datasets, achieving the state-of-the-art results in LiDAR scene's generation quality. Furthermore, by incorporating semantic labels and camera views into the latent space, in addition to enhancing the model's semantic understanding capability for LiDAR scenes, our method also demonstrates additional performance improvements compared to previous works in terms of LiDAR scene's visual quality. The code implementation has been released on https://***/HITysx/LiDAR-Scene-Generation. © 2025 Elsevier Ltd

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

Fermi-Energy-Sensitive Universal Conductance Fluctuations in Anisotropic Materials

arXiv

引用

arXiv 2025年

作者： Yang, Qiang Hu, Yayun Hou, Zhe Tong, Peiqing School of Physics and Technology Nanjing Normal University Nanjing210023 China Zhejiang Lab Hangzhou311100 China Ministry of Education Key Laboratory of Numerical Simulation of Large Scale Complex Systems Nanjing Normal University Nanjing210023 China

Universal conductance fluctuation (UCF) is a hallmark of quantum interference in mesoscopic devices. According to the Altshuler-Lee-Stone theory, the amplitude of UCF remains independent of system parameters such as Fermi energy and disorder strength. However, recent experiments have demonstrated a significant variation in UCF with respect to Fermi energy in the anisotropic Dirac semimetal Cd3As2, suggesting a dependence on band anisotropy. In this work, we reconcile the discrepancy between theoretical predictions and experimental observations through a detailed study of UCF versus Fermi energy using a tight-binding model with tunable anisotropy parameters. Near the band edge, the Hamiltonian is simplified to an anisotropic free electron gas model, recovering the generalized Altshuler-Lee-Stone theory. However, as the Fermi energy shifts toward the band center, where rotational symmetry breaks into C4 (four-fold rotational) symmetry, the UCF amplitude deviates from the standard theory. Our findings reveal that UCF becomes increasingly sensitive to Fermi energy as the anisotropy grows stronger. Furthermore, using realistic parameters for Cd3As2, our calculations demonstrate an increase in UCF away from the Dirac point, in qualitative agreement with experimental results. The enhancement of UCF occurs in two perpendicular transport directions that we have calculated, albeit with quantitative differences in magnitude, which can be tested in future experiments. Given the prevalence of anisotropic materials and technical advances in engineering anisotropy through strain or twist, our results offer a valuable reference for characterizing intrinsic electronic properties via UCF. © 2025, CC BY.

关键词： Fermions

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Point Cloud Super Resolution with Local Interpolation and Readjustment via Outer-Product Neural Network

引用

Journal of systems Science & complexity 2021年第1期34卷 68-82页

作者： WANG Guangyu XU Gang WU Qing WU Xundong School of Computer Science and Technology Hangzhou Dianzi UniversityHangzhou 310018China Key Laboratory of Complex Systems Modeling and Simulation Ministry of EducationHangzhou 310018China

This paper proposes a two-stage point cloud super resolution framework that combines local interpolation and deep neural network based readjustment. For the first stage, the authors apply a local interpolation method to increase the density and uniformity of the target point cloud. For the second stage, the authors employ an outer-product neural network to readjust the position of points that are inserted at the first stage. Comparison examples are given to demonstrate that the proposed framework achieves a better accuracy than existing state-of-art approaches, such as PU-Net, Point Net and DGCNN(Source code is available at https://***/qwerty1319/PC-SR).

关键词： Neural network outer-product network point cloud super resolution

来源：评论

学校读者我要写书评

暂无评论

Interfacial Thermal Transport and Energy Dissipation in Multilayer PdSe2 Field Effect Transistors

引用

Advanced Materials 2025年第0期 e2503264页

作者： Xie, Jiaqiu Yu, Zehao Sun, Yuanchen Gan, Qikang Liu, Chenhan Wang, Lei Zhang, Lifa Zhao, Yunshan Phonon Engineering Research Center of Jiangsu Province Ministry of Education Key Laboratory of NSLSCS Center for Quantum Transport and Thermal Energy Science Institute of Physics Frontiers and Interdisciplinary Sciences School of Physics and Technology Nanjing Normal University Nanjing210023 China National Laboratory of Solid-State Microstructures School of Physics Collaborative Innovation Center of Advanced Microstructures Nanjing University Nanjing210093 China Micro- and Nano-scale Thermal Measurement and Thermal Management Laboratory Jiangsu Key Laboratory for Numerical Simulation of Large-Scale Complex Systems School of Energy and Mechanical Engineering Nanjing Normal University Nanjing210046 China

The continuous miniaturization of 2D electronic circuits results in increased power density during device operation, leading to heat localization and placing higher demands on their performance thresholds. The risk to thermal breakdown and subsequent damage, due to the energy dissipation in the 2D semiconductor field-effect transistors (FETs) supported on the bulk substrates, represents a significant challenge in maintaining their optimal performance. Herein, this study investigates energy dissipation behavior in multilayer PdSe2 FETs for the first time. The high-field breakdown behavior is firstly studied in multilayer PdSe2 FETs on SiO2/Si substrates, where a maximum current density of ≈2.74 MA cm−2 is observed, which is comparable to that of multilayer black phosphorus FET and significantly higher—by about five times—than that of multilayer MoS2 FET. Additionally, the thermal boundary conductance (TBC) of PdSe2/SiO2 interface is measured at room temperature using Raman thermometry. The TBC is found to be ≈12–13 MW m−2 K−1, which is relatively low compared to the other known solid–solid interfaces, indicating that enhancing the performance of PdSe2 FETs can be possible by optimizing the TBC at the PdSe2/SiO2 interface. These findings provide valuable insights for design of high-quality and high-performance PdSe2 electronic and optoelectronic devices. © 2025 Wiley-VCH GmbH.

关键词： Multilayers

来源：评论

学校读者我要写书评

暂无评论

A new general formulation of a transfer-function matrices of 2D digital systems

引用

Australian Journal of Electrical and Electronics Engineering 2019年第2期16卷 81-85页

作者： Bouhamla, Lakhdar Adamou-Mitiche, Amel Baha Houda Mitiche, Lahcène Laboratory of Research Modeling Simulation and Optimization of Real Complex Systems University Ziane Achour Djelfa Algeria

The contribution of our paper is a new simple method for transfer-function matrices derivation in two-dimensional digital systems from Roesser’s model is given. The main idea of this method is changing the form of the transfer-function, from state space to a fraction with a polynomial numerator and denominator. Then by identity, we can derive matrices of numerator and denominator. Numerical examples are given to prove the effectiveness and the simplicity of the proposed method. © 2019, © 2019 Engineers Australia.

关键词： Transfer functions

来源：评论

学校读者我要写书评

暂无评论

O(1/t) complexity analysis of the generalized alternating direction method of multipliers

引用

Science China Mathematics 2019年第4期62卷 795-808页

作者： Xingju Cai Deren Han School of Mathematical Sciences and Key Laboratory for Numerical Simulation of Large Scale Complex Systems of Jiangsu Province Nanjing Normal University

Owing to its efficiency in solving some types of large-scale separable optimization problems with linear constraints, the convergence rate of the alternating direction method of multipliers(ADMM for short) has recently attracted significant attention. In this paper, we consider the generalized ADMM(G-ADMM), which incorporates an acceleration factor and is more efficient. Instead of using a solution measure that depends on a bounded set and cannot be easily estimated, we propose using the original ?-optimal solution measure, under which we prove that the G-ADMM converges at a rate of O(1/t). The new bound depends on the penalty parameter and the distance between the initial point and the solution set, which is more reasonable than the previous bound.

关键词： generalized alternating direction method of multipliers separable convex optimization iteration complexity sublinear convergence rate

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：