检索结果-南通市图书馆

Joint UAV trajectory and communication design with heterogeneous multi-agent reinforcement learning

science China(Information sciences) 2024年第3期67卷 225-245页

作者： Xuanhan ZHOU Jun XIONG Haitao ZHAO Xiaoran LIU Baoquan REN Xiaochen ZHANG Jibo WEI Hao YIN College of Electronic science and technology National University of Defense Technology Systems Engineering Institute Academy of Military Sciences PLA

Unmanned aerial vehicles(UAVs) are recognized as effective means for delivering emergency communication services when terrestrial infrastructures are unavailable. This paper investigates a multiUAV-assisted communication system, where we jointly optimize UAVs’ trajectories, user association, and ground users(GUs)’ transmit power to maximize a defined fairness-weighted throughput metric. Owing to the dynamic nature of UAVs, this problem has to be solved in real time. However, the problem’s non-convex and combinatorial attributes pose challenges for conventional optimization-based algorithms, particularly in scenarios without central controllers. To address this issue, we propose a multi-agent deep reinforcement learning(MADRL) approach to provide distributed and online solutions. In contrast to previous MADRLbased methods considering only UAV agents, we model UAVs and GUs as heterogeneous agents sharing a common objective. Specifically, UAVs are tasked with optimizing their trajectories, while GUs are responsible for selecting a UAV for association and determining a transmit power level. To learn policies for these heterogeneous agents, we design a heterogeneous coordinated QMIX(HC-QMIX) algorithm to train local Q-networks in a centralized manner. With these well-trained local Q-networks, UAVs and GUs can make individual decisions based on their local observations. Extensive simulation results demonstrate that the proposed algorithm outperforms state-of-the-art benchmarks in terms of total throughput and system fairness.

关键词： unmanned aerial vehicle (UAV) trajectory design resource allocation multi-agent deep reinforcement learning (MADRL) heterogeneous agents

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Anti-explosion performance and dynamic response of an innovative multi-layer composite explosion containment vessel

引用

Defence technology（防务技术） 2024年第6期36卷 105-121页

作者： Zhen Wang Heng Chen Qi Yuan Wenbin Gu Xingbo Xie Hongwei Li College of Field Engineering Army Engineering University of PLANanjing 210007China College of Civil Engineering and Architecture Southwest University of Science and TechnologySichuanMianyang 621010China

An innovative multi-layer composite explosion containment vessel(CECV)utilizing a sliding steel platealuminum honeycomb-fiber cloth sandwich is put forward to improve the anti-explosion capacity of a conventional single-layer explosion containment vessel(SECV).Firstly,a series of experiments and finite element(FE)simulations of internal explosions are implemented to understand the basic anti-explosion characteristics of a SECV and the rationality of the computational models and methods is verified by the comparison between the experimental results and simulation *** on this,the CECV is designed in detail and a variety of FE simulations are carried out to investigate effects of the sandwich structure,the explosive quantity and the laying mode of the fiber cloth on anti-explosion performance and dynamic response of the CECV under internal *** results indicate that the end cover is the critical position for both the SECV and *** maximum pressure of the explosion shock wave and the maximum strain of the CECV can be extremely declined compared to those of the *** a result,the explosive quantity the CECV can sustain is up to 20 times of that the SECV can ***,as the explosive quantity increases,the internal pressure of the CECV keeps growing and the plastic deformation and failure of the sandwich structure become more and more severe,yielding plastic strain of the CECV in addition to elastic *** results also reveal that the laying angles of the fiber cloth's five layers have an impact on the anti-explosion performance of the *** example,the CECV with fiber cloth layered in 0°/45°/90°/45°/0°mode has the optimal anti-capacity,compared to 0°/0°/0°/0°/0°and 0°/30°/60°/30°/0°***,owing to remarkable anti-explosion capacity,this CECV can be regarded as a promising candidate for explosion resistance.

关键词： Explosive container Honeycomb-fiber cloth Anti-explosion Aluminum honeycomb core Composite

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

High Seebeck Coefficient Thermally Chargeable Supercapacitor with Synergistic Effect of Multichannel Ionogel Electrolyte and Ti_(3)C_(2)T_(x)MXene-Based Composite Electrode

引用

Energy & Environmental Materials 2024年第6期7卷 367-377页

作者： Zhongming Chen Zhijian Du La Li Kai Jiang Di Chen Guozhen Shen School of Mathematics and Physics University of Science and Technology BeijingBeijing 100083China School of Integrated Circuits and Electronics Beijing Institute of TechnologyBeijing 100081China Faculty of Hepato-Pancreato-Biliary Surgery Chinese PLA General HospitalInstitute of Hepatobiliary Surgery of Chinese PLA&Key Laboratory of Digital Hepetobiliary SurgeryChinese PLABeijing 100853China

Thermally chargeable supercapacitors can collect low-grade heat generated by the human body and convert it into electricity as a power supply unit for wearable ***,the low Seebeck coefficient and heat-to-electricity conversion efficiency hinder further *** this paper,we designed a high-performance thermally chargeable supercapacitor device composed of ZnMn_(2)O_(4)@Ti_(3)C_(2)T_(x)MXene composites(ZMO@Ti_(3)C_(2)T_(x)MXene)electrode and UIO-66 metal–organic framework doped multichannel polyvinylidene fluoridehexafluoro-propylene ionogel electrolyte,which realized the thermoelectric conversion and electrical energy storage at the same *** thermally chargeable supercapacitor device exhibited a high Seebeck coefficient of 55.4 mV K^(−1),thermal voltage of 243 mV,and outstanding heat-to-electricity conversion efficiency of up to 6.48%at the temperature difference of 4.4 *** addition,this device showed excellent charge–discharge cycling stability at high-temperature differences(3 K)and low-temperature differences(1 K),*** two thermally chargeable supercapacitor units in series,the generated output voltage of 500 mV further confirmed the stability of *** a single device was worn on the arm,a thermal voltage of 208.3 mV was obtained indicating the possibility of application in wearable electronics.

关键词： ionogel electrode Soret effect thermally chargeable supercapacitor Ti_(3)C_(2)T_(x)MXene UIO-66 MOF

来源：

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

Explosion resistance performance of reinforced concrete box girder coated with polyurea:Model test and numerical simulation

引用

Defence technology（防务技术） 2024年第3期33卷 1-18页

作者： Guangpan Zhou Rong Wang Mingyang Wang Jianguo Ding Yuye Zhang School of science Nanjing University of Science and TechnologyNanjing 210094JiangsuChina School of Mechanical Engineering Nanjing University of Science and TechnologyNanjing 210094JiangsuChina State Key Laboratory of Explosion and Impact and Disaster Prevention and Mitigation Army Engineering University of PLANanjing 210007JiangsuChina

To study the anti-explosion protection effect of polyurea coating on reinforced concrete box girder,two segmental girder specimens were made at a scale of 1:3,numbered as G(without polyurea coating)and PCG(with polyurea coating).The failure characteristics and dynamic responses of the specimens were compared through conducting explosion *** reliability of the numerical simulation using LS-DYNA software was verified by the test *** effects of different scaled distances,reinforcement ratios,concrete strengths,coating thicknesses and ranges of polyurea were *** results show that the polyurea coating can effectively enhance the anti-explosion performance of the *** top plate of middle chamber in specimen G forms an elliptical penetrating hole,while that in specimen PCG only shows a very slight local *** peak vertical displacement and residual displacement of PCG decrease by 74.8% and 73.7%,respectively,compared with those of specimen *** the TNT explosion with small equivalent,the polyurea coating has a more significant protective effect on reducing the size of *** the increase of TNT equivalent,the protective effect of polyurea on reducing girder displacement becomes more *** optimal reinforcement ratio,concrete strength,thickness and range of polyurea coating were also drawn.

关键词： Explosive load Explosion resistance performance Model test Polyurea Concrete box girder Numerical simulation

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Optimization of spatial layouts for underground facilities to achieve carbon neutrality in cities:A multi-agent system model

引用

Underground Space 2024年第6期19卷 251-278页

作者： Lingxiang Wei Dongjun Guo Junyuan Ji Zhilong Chen Huapeng Hu Xiaoli Peng Research Center for Underground Space Army Engineering University of PLANanjing 210007China School of Materials science and Engineering Yancheng Institute of TechnologyYancheng 224051China

Subways,underground logistics systems and underground parking,as the primary facilities types of underground,contribute significantly to the achievement of carbon–neutral cities by moving surface transportation to underground,thereby releasing surface space for the creation of more urban blue-green space for carbon ***,in-depth studies on carbon neutrality strategies as well as reliable layout optimization solutions of these three types of underground facilities are *** study proposes a spatial layout optimization strategy for carbon neutrality using underground hydrogen storage and geothermal energy for these three types of underground facilities employing a multi-agent system ***,three spatial layout relationships,competition,coordination,and followership,between five underground facilities that contribute to emission reduction were ***,the implementation steps for optimizing the spatial layout of underground facilities were determined by defining the behavioral guidelines for spatial environment,underground facility,and synergistic ***,using the Tianfu New District in Chengdu City,China,as a case study,layouts of underground facilities under three different underground space development scenarios were simulated to verify the *** findings of this study address the gap in the research on underground spatial facilities and their layout optimization in response to emission *** study provided a significant reference for the study of underground space and underground resources at the planning level to aid in achieving carbon–neutral cities.

关键词： Urban underground space(UUS) Carbon-neutral city Multi-agent system model Underground facility Spatial layouts

来源：

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

Power-Domain Collision-Tolerant Random Access Method with Auxiliary Beam for Satellite Internet of Things:A New Solution

引用

China Communications 2024年第8期21卷 236-248页

作者： Xu Yuanyuan Liu Ziwei Bian Dongming Zhang Gengxin School of Communications and Information Engineering Nanjing University of Posts and TelecommunicationsNanjing 210003China Institute of Communications Engineering PLA University of Science and TechnologyNanjing 210007China

There are numerous terminals in the satellite Internet of Things(IoT).To save cost and reduce power consumption,the system needs terminals to catch the characteristics of low power consumption and light *** regular random access(RA)protocols may generate large amounts of collisions,which degrade the system throughout *** near-far effect and power control technologies are not applicable in capture effect to obtain power difference,resulting in the collisions that cannot be *** fact,the optimal design at the receiving end can also realize the condition of packet power domain separation,but there are few relevant *** this paper,an auxiliary beamforming scheme is proposed for power domain signal *** adds an auxiliary reception beam based on the conventional beam,utilizing the correlation of packets in time-frequency domain between the main and auxiliary beam to complete signal *** roll-off belt of auxiliary beam is used to create the carrier-to-noise ratio(CNR)*** paper uses the genetic algorithm to optimize the auxiliary beam *** results show that the proposed scheme outperforms slotted ALOHA(SA)in terms of system throughput per-formance and without bringing terminals additional control burden.

关键词： beamforming non-orthogonal multiple access random access satellite Internet of Things

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Comparative study on pump frequency tuning and self-injection locking in Kerr microcomb generation

引用

Chinese Optics Letters 2024年第8期22卷 58-63页

作者： Zhuopei Yu Weihong Hua Chenxi Zhang Runlin Miao Ke Yin Tian Jiang College of Advanced Interdisciplinary Studies National University of Defense TechnologyChangsha 410073China National Innovation Institute of Defense technology Academy of Military Sciences PLA ChinaBeijing 100071China Institute for Quantum science and technology National University of Defense TechnologyChangsha 410073China

The optical frequency comb has attracted considerable interest due to its diverse applications in optical atomic clocks,ultra-low-noise microwave generation,dual-comb spectroscopy,and optical *** merits of large frequency spacing,high integration,and low power consumption have shown that microresonator-based Kerr optical frequency combs will become mainstream in the *** methods of pump frequency tuning and self-injection locking were used to obtain Kerr combs in the same silicon nitride microresonators with free spectral ranges of 50 GHz and 100 *** combs are realized with both ***,pump power,spectrum bandwidth,conversion efficiency,and linewidth are compared and *** results show that the advantages of pump frequency tuning are a wider spectrum and higher soliton power while the advantages of self-injection locking are simplicity,compactness,low cost,significant linewidth narrowing,and high conversion efficiency.

关键词： Kerr frequency comb silicon nitride frequency tuning self-injection locking soliton comb

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Microscopic defects formation and dynamic mechanical response analysis of Q345 steel plate subjected to explosive load

引用

Defence technology（防务技术） 2024年第2期32卷 430-442页

作者： Zhengqing Zhou Zechen Du Yulong Zhang Guili Yang Ruixiang Wang Yuzhe Liu Peize Zhang Yaxin Zhang Xiao Wang Research Institute of Macro-Safety science University of Science and TechnologyBeijing100083China School of Civil and Resource Engineering University of Science and TechnologyBeijing100083China China North Industry Advanced technology Generalization Institute Beijing100089China College of Field Engineering PLA Army Engineering UniversityNanjing210007China School of Mechanical Engineering Nantong UniversityNantong226019China

As the basic protective element, steel plate had attracted world-wide attention because of frequent threats of explosive loads. This paper reports the relationships between microscopic defects of Q345 steel plate under the explosive load and its macroscopic dynamics simulation. Firstly, the defect characteristics of the steel plate were investigated by stereoscopic microscope(SM) and scanning electron microscope(SEM). At the macroscopic level, the defect was the formation of cave which was concentrated in the range of 0-3.0 cm from the explosion center, while at the microscopic level, the cavity and void formation were the typical damage characteristics. It also explains that the difference in defect morphology at different positions was the combining results of high temperature and high pressure. Secondly, the variation rules of mechanical properties of steel plate under explosive load were studied. The Arbitrary Lagrange-Euler(ALE) algorithm and multi-material fluid-structure coupling method were used to simulate the explosion process of steel plate. The accuracy of the method was verified by comparing the deformation of the simulation results with the experimental results, the pressure and stress at different positions on the surface of the steel plate were obtained. The simulation results indicated that the critical pressure causing the plate defects may be approximately 2.01 GPa. On this basis, it was found that the variation rules of surface pressure and microscopic defect area of the Q345 steel plate were strikingly similar, and the corresponding mathematical relationship between them was established. Compared with Monomolecular growth fitting models(MGFM) and Logistic fitting models(LFM), the relationship can be better expressed by cubic polynomial fitting model(CPFM). This paper illustrated that the explosive defect characteristics of metal plate at the microscopic level can be explored by analyzing its macroscopic dynamic mechanical response.

关键词： Explosive load Q345 steel Micro defect Finite element simulation Dynamic response Data fitting

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Robustness of interdependent networks with weak dependency links and reinforced nodes

引用

science China(Information sciences) 2024年第2期67卷 329-330页

作者： Qian LI Hongtao YU Weitao HAN Ruiyang HUANG Shaomei LI Jianpeng ZHANG Institute of Information technology PLA Strategic Support Force Information Engineering University

Interdependent networks are more vulnerable than single,non-interacting networks under cascading failure [1–3]. Percolation theory provides a quantifiable theoretical framework to quantify and evaluate the robustness of networked systems. Most existing models [1–3] on the robustness of interdependent networks mainly focused on the giant connected component(GCC) to explore the structural robustness from the macro perspective,

关键词：

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Robust video question answering via contrastive cross-modality representation learning

引用

science China(Information sciences) 2024年第10期67卷 211-226页

作者： Xun YANG Jianming ZENG Dan GUO Shanshan WANG Jianfeng DONG Meng WANG School of Information science and technology University of Science and Technology of China Institute of Artificial Intelligence Hefei Comprehensive National Science Center School of Computer science and Information Engineering Hefei University of Technology Institutes of Physical science and Information technology Anhui University School of Computer science and technology Zhejiang Gongshang University

Video question answering(VideoQA) is a challenging yet important task that requires a joint understanding of low-level video content and high-level textual semantics. Despite the promising progress of existing efforts, recent studies revealed that current VideoQA models mostly tend to over-rely on the superficial correlations rooted in the dataset bias while overlooking the key video content, thus leading to unreliable results. Effectively understanding and modeling the temporal and semantic characteristics of a given video for robust VideoQA is crucial but, to our knowledge, has not been well investigated. To fill the research gap, we propose a robust VideoQA framework that can effectively model the cross-modality fusion and enforce the model to focus on the temporal and global content of videos when making a QA decision instead of exploiting the shortcuts in datasets. Specifically, we design a self-supervised contrastive learning objective to contrast the positive and negative pairs of multimodal input, where the fused representation of the original multimodal input is enforced to be closer to that of the intervened input based on video perturbation. We expect the fused representation to focus more on the global context of videos rather than some static keyframes. Moreover, we introduce an effective temporal order regularization to enforce the inherent sequential structure of videos for video representation. We also design a Kullback-Leibler divergence-based perturbation invariance regularization of the predicted answer distribution to improve the robustness of the model against temporal content perturbation of videos. Our method is model-agnostic and can be easily compatible with various VideoQA backbones. Extensive experimental results and analyses on several public datasets show the advantage of our method over the state-of-the-art methods in terms of both accuracy and robustness.

关键词： video question answering cross-modality fusion contrastive learning cross-media reasoning

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：