检索结果-南通市图书馆

ISpliter:an intelligent and automatic surface mesh generator using neural networks and splitting lines

在线全文

学校读者我要写书评

暂无评论

Advances in Aerodynamics 2023年第1期5卷 362-386页

作者： Zengsheng Liu shizhao chen Xiang Gao Xiang Zhang Chunye Gong Chuanfu Xu Jie Liu State Key Laboratory of High Performance Computing National University of Defense TechnologyChangsha 410073China College of Computer National University of Defense TechnologyChangsha 410073China Laboratory of Digitizing Software for Frontier Equipment National University of Defense TechnologyChangsha 410073China

In this paper,we present a novel surface mesh generation approach that splits B-rep geometry models into isotropic triangular meshes based on neural networks and splitting *** the first stage,a recursive method is designed to generate plentiful data to train the neural network model *** the second stage,the implemented mesh generator,ISpliter,maps each surface patch into the parameter plane,and then the trained neural network model is applied to select the optimal splitting line to divide the patch into subdomains continuously until they are all *** the third stage,ISpliter remaps the 2D mesh back to the physical space and further optimizes *** typical cases are evaluated to compare the mesh quality generated by ISpliter and two baselines,Gmsh and *** results show that ISpliter can generate isotropic triangular meshes with high average quality,and the generated meshes are comparable to those generated by the other two software under the same configuration.

关键词： Surface mesh generation Artificial neural network Splitting line Triangular element Feature extraction

Observer-Based Adaptive Robust Precision Motion Control of a Multi-Joint Hydraulic Manipulator

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第5期11卷 1213-1226页

作者： Zheng chen shizhao Zhou Chong Shen Litong Lyu Junhui Zhang Bin Yao State Key Laboratory of Fluid Power and Mechatronic Systems Zhejiang UniversityHangzhou 310027 Ocean College Zhejiang UniversityZhoushan 316021China School of Mechanical Engineering Shijiazhuang Tiedao UniversityShijiazhuang 050000 State Key Laboratory of Fluid Power and Mechatronic Systems Zhejiang UniversityHangzhou 310027China School of Mechanical Engineering Purdue UniversityWest LafayetteIN 47907 USA

Hydraulic manipulators are usually applied in heavy-load and harsh operation ***,when faced with a complex operation,the traditional proportional-integral-derivative(PID)control may not meet requirements for high control ***-based full-state-feedback control is an effective alternative,but the states of a hydraulic manipulator are not always available and reliable in practical applications,particularly the joint angular velocity *** that it is not suitable to obtain the velocity signal directly from differentiating of position measurement,the low-pass filtering is commonly used,but it will definitely restrict the closed-loop bandwidth of the whole *** avoid this problem and realize better control performance,this paper proposes a novel observerbased adaptive robust controller(obARC)for a multi-joint hydraulic manipulator subjected to both parametric uncertainties and the lack of accurate velocity ***,a nonlinear adaptive observer is first designed to handle the lack of velocity measurement with the consideration of parametric ***,the adaptive robust control is developed to compensate for the dynamic uncertainties,and the close-loop system robust stability is theoretically proved under the observation and control ***,comparative experiments are carried out to show that the designed controller can achieve a performance improvement over the traditional methods,specifically yielding better control accuracy owing to the closed-loop bandwidth breakthrough,which is limited by low-pass filtering in fullstate-feedback control.

关键词： handle Observer filtering

Viability of all-solid-state lithium metal battery coupled with oxide solid-state electrolyte and high-capacity cathode

在线全文

学校读者我要写书评

暂无评论

Journal of Energy Chemistry 2024年第4期91卷 122-131页

作者： Xingxing Jiao Xieyu Xu Yongjing Wang Xuyang Wang Yaqi chen shizhao Xiong Weiqing Yang Zhongxiao Song Yangyang Liu Research Institute of Frontier Science Southwest Jiaotong UniversityChengdu 610031SichuanChina State Key Laboratory for Mechanical Behavior of Materials Xi'an Jiaotong UniversityXi'an 710049ShaanxiChina Department of Physics Chalmers University of TechnologyGöteborgSE 41296Sweden

Owing to the utilization of lithium metal as anode with the ultrahigh theoretical capacity density of 3860 mA h g^(-1)and oxide-based ceramic solid-state electrolytes(SE),e.g.,garnet-type Li7La_(3)Zr_(2)O_(12)(LLZO),all-state-state lithium metal batteries(ASLMBs)have been widely accepted as the promising alternatives for providing the satisfactory energy density and ***,its applications are still challenged by plenty of technical and scientific *** this contribution,the co-sintering temperature at 500℃is proved as a compromise method to fabricate the composite cathode with structural integrity and declined capacity fading of LiNi_(0.5)Co_(0.2)Mn_(0.3)O_(2)(NCM).On the other hand,it tends to form weaker grain boundary(GB)inside polycrystalline LLZO at inadequate sintering temperature for LLZO,which can induce the intergranular failure of SE during the growth of Li filament inside the unavoidable defect on the interface of ***,increasing the strength of GB,refining the grain to 0.4μm,and precluding the interfacial defect are suggested to postpone the electro-chemo-mechanical failure of SE with weak ***,the advanced sintering techniques to lower the co-sintering temperature for both NCM-LLZO composite cathode and LLZO SE can be posted out to realize the viability of state-of-the-art ASLMBs with higher energy density as well as the guaranteed safety.

关键词： All-solid-state lithium metal battery LiNi_(0.5C)o_(0.2)Mn_(0.3)O_(2)-Li7La_(3)Zr_(2)O_(12)composite cathode Co-sintering Lithium metal anode Electro-chemo-mechanical failure

在线全文

学校读者我要写书评

暂无评论

MEC计算卸载与资源分配联合智能优化方案

北京邮电大学学报 2022年第2期45卷 65-71页

作者：杜梅周军华李敦桥陈士钊魏翼飞北京邮电大学电子工程学院北京100876 北京市复杂产品先进制造工程研究中心北京市仿真中心北京100854 贵州航天控制技术有限公司贵阳550009 宁波中湾科技有限公司宁波315400

移动边缘计算(MEC)中的分布式基站部署、有限的服务器资源和动态变化的终端用户使得计算卸载方案的设计极具挑战。鉴于深度强化学习在处理动态复杂问题方面的优势,设计了最优的计算卸载和资源分配策略,目的是最小化系统能耗。首先考虑... 详细信息

移动边缘计算(MEC)中的分布式基站部署、有限的服务器资源和动态变化的终端用户使得计算卸载方案的设计极具挑战。鉴于深度强化学习在处理动态复杂问题方面的优势,设计了最优的计算卸载和资源分配策略,目的是最小化系统能耗。首先考虑了云边端协同的网络框架;然后将联合计算卸载和资源分配问题定义为一个马尔可夫决策过程,提出一种基于多智能体深度确定性策略梯度的学习算法,以最小化系统能耗。仿真结果表明,该算法在降低系统能耗方面的表现明显优于深度确定性策略梯度算法和全部卸载策略。

关键词：移动边缘计算计算卸载资源分配多智能体强化学习

Meridional deflection of global eddy propagation derived from tandem altimetry: Mechanism and implication

在线全文

学校读者我要写书评

暂无评论

Science China Earth Sciences 2024年第3期67卷 811-825页

作者： Ge chen Xiaoyan chen Frontiers Science Center for Deep Ocean Multispheres and Earth System School of Marine TechnologyOcean University of ChinaQindao 266100China Laboratory for Regional Oceanography and Numerical Modeling Laoshan LaboratoryQindao 266237China

A common view on meridional deflection of eddy propagation is poleward for cyclones and equatorward for anticyclones. This widely accepted polarity-sensitive pattern has been increasingly undermined given that it is systematically violated on both zonal and regional scales as recently reported. Here, we approach the problem by exploring these violations in terms of eddy effects of spatiotemporal geostrophy, thermal fading, and flow dragging, yielding the following main conclusions.(1) The polarity-dependent deflection discrepancy is a pseudo feature resulting from a biased fit to the normalized eddy tracks which are spatially asymmetric(though azimuthally symmetric) between the two signs;Instead, the primary pattern of eddy deflection appears to be geographically correlated and polarity independent.(2) Geostrophic adjustment plays a critical role in defining the meridional movement of an eddy. Specifically, a consistent poleward(equatorward) trajectory bending of spatially(temporally) ageostrophic eddies is observed irrespective of their polarity.(3) The mechanism of eddy deflection is also determined by its zonal propagation direction. Westward propagating eddies are substantially affected by thermal fading, while opposite ones by flow dragging. A realistic and comprehensive understanding of eddy deflection mechanisms serves as a significant contribution to the prediction of eddy trajectory, and the protection of ocean environment.

关键词： Mesoscale eddies Eddy propagation Eddy meridional deflection Satellite observation Geostrophic adjustment

同方期刊数据库

A refined representation method of the particle size distribution curve based on grading entropy

在线全文

学校读者我要写书评

暂无评论

Particuology 2024年第5期88卷 302-311页

作者： Xing Li Qun chen Zhaozhao Liu cheng Zhou chen Wang chen chen State Key Laboratory of Hydraulics and Mountain River Engineering College of Water Resource and HydropowerSichuan UniversityChengdu610065China

The particle size distribution(PSD)curve is an important expression of the basic properties of the *** characteristic parameters such as median particle size D_(50),effective particle size D_(10),and some combinations of characteristic parameters can only represent some points of the PSD curve,failing to represent all information of the PSD *** this paper,a fraction characteristic parameter F that could reflect the fraction size variation of the PSD curve was introduced based on grading *** a new presentation method of the A-B-F three parameters was proposed for a refined representation of the PSD *** was found that the newly constructed model not only better represents the differences in the width of PSD curves but also has a higher sensitivity than the A-B two-parameter model proposed by Lő*** PSD curves with similar distributions,the new presentation method has a higher degree of discrimination than that of the D_(50)-C_(u)-C_(c) three-parameter or the four-parameter combination G_(c) proposed by ***,the application of this new method in describing the spatial nonuniformity distribution of depositions and predicting the soil hydraulic conductivity was *** research results can provide a reference for the refined representation of PSD curves.

关键词： Grading entropy Particle size distribution curve Refined representation

Track correlation algorithm based on CNN-LSTM for swarm targets

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2024年第2期35卷 417-429页

作者： chen Jinyang WANG Xuhua chen Xian Research Institute for National Defense Engineering Academy of Military SciencesLuoyang 471023China Information Engineering University Zhengzhou 450001China School of Computer Science and Technology Xidian UniversityXi’an 710071China

The rapid development of unmanned aerial vehicle(UAV) swarm, a new type of aerial threat target, has brought great pressure to the air defense early warning system. At present, most of the track correlation algorithms only use part of the target location, speed, and other information for *** this paper, the artificial neural network method is used to establish the corresponding intelligent track correlation model and method according to the characteristics of swarm ***, a route correlation method based on convolutional neural networks (CNN) and long short-term memory (LSTM)Neural network is designed. In this model, the CNN is used to extract the formation characteristics of UAV swarm and the spatial position characteristics of single UAV track in the formation,while the LSTM is used to extract the time characteristics of UAV swarm. Experimental results show that compared with the traditional algorithms, the algorithm based on CNN-LSTM neural network can make full use of multiple feature information of the target, and has better robustness and accuracy for swarm targets.

关键词： track correlation correlation accuracy rate swarm target convolutional neural network(CNN) long short-term memory(LSTM)neural network

Two-stage Planning Method for Energy Router Considering Its Optimal Operation in Distribution Networks

在线全文

学校读者我要写书评

暂无评论

CSEE Journal of Power and Energy Systems 2024年第2期10卷 605-616页

作者： Meifu chen Mingchao Xia Qifang chen School of Electrical Engineering Beijing Jiaotong UniversityBeijing 100044China

An energy router can effectively optimize the network loss and power quality of distribution networks. The optimal configuration of the energy router is relatively complex because issues dynamically influence each other, such as the location of the energy router, optimal number and capacity of its ports, and building new distribution lines for the ports. Presently, there has been very few research studies on the practical problems for the energy router. In this paper, a planning model of an energy router combined with the distribution network is established, which fully exploits the active and reactive power control abilities of the energy router to optimize the operation of the grid. The configuration problem is decoupled into two stages. The upper layer determines the location of the energy router and the parameters of the candidate new distribution lines for the ports. The lower layer calculates the optimal configuration of the energy router by minimizing the total annual cost. Because of the same rated bus voltage in the distribution network, the existing structure of the energy router is changed to be more applicable for the distribution network, and then the power flow model of the energy router is also modified. Due to the nonlinearity of the model, the planning model is converted into a mixed-integer second-order cone model to solve efficiently. In addition, some core factors influencing the optimal scheme of the energy router are also analyzed in this paper. Simulation results show that the optimal scheme of the energy router can significantly improve the economic deployment of the energy router, and optimize the network loss and power quality of the distribution network.

关键词： Capacity allocation distribution network energy router optimal operation

Aerial target threat assessment based on gated recurrent unit and self-attention mechanism

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2024年第2期35卷 361-373页

作者： chen chen QUAN Wei SHAO Zhuang School of Automation Beijing Institute of TechnologyBeijing 100081China State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing 100081China

Aerial threat assessment is a crucial link in modern air combat, whose result counts a great deal for commanders to make decisions. With the consideration that the existing threat assessment methods have difficulties in dealing with high dimensional time series target data, a threat assessment method based on self-attention mechanism and gated recurrent unit(SAGRU) is proposed. Firstly, a threat feature system including air combat situations and capability features is established. Moreover, a data augmentation process based on fractional Fourier transform(FRFT) is applied to extract more valuable information from time series situation features. Furthermore, aiming to capture key characteristics of battlefield evolution, a bidirectional GRU and SA mechanisms are designed for enhanced ***, after the concatenation of the processed air combat situation and capability features, the target threat level will be predicted by fully connected neural layers and the softmax classifier. Finally, in order to validate this model, an air combat dataset generated by a combat simulation system is introduced for model training and testing. The comparison experiments show the proposed model has structural rationality and can perform threat assessment faster and more accurately than the other existing models based on deep learning.

关键词： target threat assessment gated recurrent unit(GRU) self-attention(SA) fractional Fourier transform(FRFT)