检索结果-南通市图书馆

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

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

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

Optical detection method of discharge mode transition of inductively coupled plasma in an atmosphere-breathing electric propulsion system

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2024年第10期37卷 172-183页

作者： Yuxuan ZHONG Yu ZHANG Jianjun WU Peng ZHENG college of Aerospace Science and engineering National University of Defense TechnologyChangsha 410073China

Plasma discharge stability is an important problem in atmosphere-breathing electric propulsion system when maintaining long-term missions at ultra-low earth *** paper designed an inductively coupled plasma source to imitate the ionization *** effect of inflow rate and Radio Frequency(RF)power on the plasma discharge mode transition is experimentally studied.A discharge mode detection method is proposed,which determines the discharge mode by identifying the morphology of the plasma *** using the method,the discharge mode transition is quantified and a control model based on the parameter sensitivity is *** verify the method,the spectra are measured and the electron temperature spatial distribution is *** the method has been proven *** results show that the inductively coupled discharge contains capacitive components affected by the mass flow rate and the radio frequency *** plasma characteristics can be maintained stably by controlling the radio frequency power when the mass flow rate randomly changes in a certain *** is demonstrated that the application of detection method effectively identifies the discharge mode,which is a promising active control method for the plasma discharge mode.

关键词： Atmosphere-breathing electric propulsion Inductively coupled plasma Discharge mode transition Optical diagnosis Ultra-low earth orbit

Thermogalvanic hydrogel-based e-skin for self-powered on-body dual-modal temperature and strain sensing

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Microsystems & Nanoengineering 2024年第2期10卷 293-302页

作者： Zhaosu Wang Ning Li Xinru Yang Zhiyi Zhang Hulin Zhang Xiaojing Cui college of Electronic Information and Optical engineering Taiyuan University of TechnologyTaiyuan030024China college of Materials Science and engineering Taiyuan University of TechnologyTaiyuan030024China School of Physics and Information engineering Shanxi Normal UniversityTaiyuan030031China

Sensing of both temperature and strain is crucial for various diagnostic and therapeutic ***,we present a novel hydrogel-based electronic skin(e-skin)capable of dual-mode sensing of temperature and *** thermocouple ion selected for this study is the iodine/triiodide(I−/I3−)redox couple,which is a common component in everyday *** leveraging the thermoelectric conversion in conjunction with the inherent piezoresistive effect of a gel electrolyte,self-powered sensing is achieved by utilizing the temperature difference between the human body and the external *** composite hydrogels synthesized from polyvinyl alcohol(PVA)monomers using a simple freeze‒thaw method exhibit remarkable flexibility,extensibility,and adaptability to human *** incorporation of zwitterions further augments the resistance of the hydrogel to dehydration and low temperatures,allowing maintenance of more than 90%of its weight after 48 h in the *** its robust thermal current response,the hydrogel was encapsulated and then integrated onto various areas of the human body,including the cheeks,fingers,and ***,the detection of the head-down state and the monitoring of foot movements demonstrate the promising application of the hydrogel in supervising the neck posture of sedentary office workers and the activity *** successful demonstration of self-powered on-body temperature and strain sensing opens up new possibilities for wearable intelligent electronics and robotics.

关键词： hydrogel modal utilizing

Accurately tracking hypersonic gliding vehicles via an LEO mega-constellation in relay tracking mode

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1期35卷 211-221页

作者： LI Zhao WANG Yidi ZHENG Wei college of Aerospace Science and engineering National University of Defense TechnologyChangsha 410073China

In order to effectively defend against the threats of the hypersonic gliding vehicles(HGVs),HGVs should be tracked as early as possible,which is beyond the capability of the ground-based *** benefited by the developing megaconstellations in low-Earth orbit,this paper proposes a relay tracking mode to track HGVs to overcome the above *** whole tracking mission is composed of several tracking intervals with the same *** each tracking interval,several appropriate satellites are dispatched to track the *** that are planned to take part in the tracking mission are selected by a new derived observability *** tracking performances of the proposed tracking mode and the other two traditional tracking modes,including the stare and track-rate modes,are compared by *** results show that the relay tracking mode can track the whole trajectory of a HGV,while the stare mode can only provide a very short tracking ***,the relay tracking mode achieve higher tracking accuracy with fewer attitude controls than the track-rate mode.

关键词： target tracking mega-constellation hypersonic gliding vehicle(HGV) sensor selection observability analysis

Semi-supervised remote sensing image scene classification with prototype-based consistency

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2024年第2期37卷 459-470页

作者： Yang LI Zhang LI Zi WANG Kun WANG Qifeng YU college of Aerospace Science and engineering National University of Defense TechnologyChangsha 410073China

Deep learning significantly improves the accuracy of remote sensing image scene classification,benefiting from the large-scale ***,annotating the remote sensing images is time-consuming and even tough for *** neural networks trained using a few labeled samples usually generalize less to new unseen *** this paper,we propose a semi-supervised approach for remote sensing image scene classification based on the prototype-based consistency,by exploring massive unlabeled *** this end,we,first,propose a feature enhancement module to extract discriminative *** is achieved by focusing the model on the foreground ***,the prototype-based classifier is introduced to the framework,which is used to acquire consistent feature *** conduct a series of experiments on NWPU-RESISC45 and Aerial Image Dataset(AID).Our method improves the State-Of-The-Art(SOTA)method on NWPU-RESISC45 from 92.03%to 93.08%and on AID from 94.25%to 95.24%in terms of accuracy.

关键词： Semi-supervised learning Remote sensing Scene classification Prototype network Deep learning

Hydrogen evolution reaction activity enhancement from active site turnover mechanism

在线全文

学校读者我要写书评

暂无评论

Journal of Energy Chemistry 2024年第5期92卷 629-638页

作者： Jiacheng Wang Tongqing Yang Xiyue Li Haiqin Zhang Yixue Zhang Yan He Hongyao Xue college of Electromechanical engineering Qingdao University of Science and TechnologyQingdao 266061ShandongChina

Although heteroatom doping is an effective way to improve the catalytic activity of transition metal phosphides(TMPs),the mechanism of activity enhancement needs to be further *** this end,we synthesized a Co-doped Ni_(2)P catalyst as a research model and found that the introduction of heterogeneous Co reconstructed the charge distribution around the P site,which effectively enhanced the hydrogen evolution reaction(HER)activity of the pure Ni_(2)*** on in-situ Raman real-time monitoring technology,we monitored for the first time that Co doping triggered a switch of the active site(from the original Co-active site to the P-active site),which promoted the adsorption of H_(2)O to enhance the HER *** density functional theory(DFT)calculations indicated that the P site of Co-Ni_(2)P expressed the highest activity and the Ni site of pure Ni_(2)P expressed the highest activity,which further confirms the in-situ Raman monitoring *** active site turnover mechanism discovered in this study will undoubtedly provide more rational and targeted ideas for future catalyst design.

关键词： In-situ Raman observation Heteroatom doping Activesites turnover Hydrogen production

Gas film/regenerative composite cooling characteristics of the liquid oxygen/liquid methane (LOX/LCH4) rocket engine

在线全文

学校读者我要写书评

暂无评论

Journal of Zhejiang University-Science A(Applied Physics & engineering) 2024年第8期25卷 631-649页

作者： Xinlin LIU Jun SUN Zhuohang JIANG Qinglian LI Peng CHENG Jie SONG Science and technology on Scramjet Laboratory College of Aerospace Science and EngineeringNational University of Defense TechnologyChangsha 410073China

The thermal protection of rocket engines is a crucial aspect of rocket engine *** this paper,the gas film/regenerative composite cooling of the liquid oxygen/liquid methane(LOX/LCH4)rocket engine thrust chamber was investigated.A gas film/regenerative composite cooling model was developed based on the Grisson gas film cooling efficiency formula and the one-dimensional regenerative cooling *** accuracy of the model was validated through experiments conducted on a 6 kg/s level gas film/regenerative composite cooling thrust ***,key parameters related to heat transfer performance were *** results demonstrate that the model is sufficiently accurate to be used as a preliminary design *** temperature rise error of the coolant,when compared with the experimental results,was found to be less than 10%.Although the pressure drop error is relatively large,the calculated results still provide valuable guidance for heat transfer *** addition,the performance of composite cooling is observed to be superior to regenerative *** the gas film flow rate results in higher cooling efficiency and a lower gas-side wall ***,the position at which the gas film is introduced greatly impacts the cooling *** optimal introduction position for the gas film is determined when the film is introduced from a single row of *** optimal introduction position results in a more uniform wall temperature distribution and reduces the peak ***,it is observed that a double row of holes,when compared to a single row of holes,enhances the cooling effect in the superposition area of the gas film and further lowers the gas-side wall *** results provide a basis for the design of gas film/regenerative composite cooling systems.

关键词： Liquid oxygen/liquid methane(LOX/LCH4)rocket engine Gas film cooling Regenerative cooling Heat transfer characteristics

Experimental Study on Wire Melting Control Ability of Twin-Body Plasma Arc

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Mechanical engineering 2024年第2期37卷 184-194页

作者： Ruiying Zhang Fan Jiang Long Xue School of Mechanical engineering Beijing Institute of Petrochemical TechnologyBeijing 102617China Beijing Academy of Safety engineering and technology Beijing 102617China college of Mechanical and Energy engineering Beijing University of TechnologyBeijing 100124China

The twin-body plasma arc has the decoupling control ability of heat transfer and mass transfer,which is beneficial to shape and property control in wire arc additive *** this paper,with the wire feeding speed as a characteristic quantity,the wire melting control ability of twin-body plasma arc was studied by adjusting the current separation ratio(under the condition of a constant total current),the wire current/main current and the position of the wire in the arc axial *** results showed that under the premise that the total current remains unchanged(100 A),as the current separation ratio increased,the middle and minimum melting amounts increased approximately synchronously under the effect of anode effect power,the first melting mass range remained constant;the maximum melting amount increased twice as fast as the middle melting amount under the effect of the wire feeding speed,and the second melting mass range was *** the wire current increased,the anode effect power and the plasma arc power were both factors causing the increase in the wire melting amount;however,when the main current increased,the plasma arc power was the only factor causing the increase in the wire melting *** average wire melting increment caused by the anode effect power was approximately 2.7 times that caused by the plasma arc *** minimum melting amount was not affected by the wire-torch distance under any current separation ratio *** the current separation ratio increased and reached a threshold,the middle melting amount remained constant with increasing wire-torch *** the current separation ratio continued to increase and reached the next threshold,the maximum melting amount remained constant with the increasing wire-torch *** effect of the wire-torch distance on the wire melting amount reduced with the increase in the current separation *** this study,the decoupling mechanism and ability of this innovative

关键词： Twin-body plasma arc Melting control ability Melting amount Current separation ratio

Traffic-Aware Fuzzy Classification Model to Perform IoT Data Traffic Sourcing with the Edge Computing

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第2期78卷 2309-2335页

作者： Huixiang Xu college of Information engineering Zhengzhou University of TechnologyZhengzhou450044China

The Internet of Things(IoT)has revolutionized how we interact with and gather data from our surrounding *** devices with various sensors and actuators generate vast amounts of data that can be harnessed to derive valuable *** rapid proliferation of Internet of Things(IoT)devices has ushered in an era of unprecedented data generation and *** IoT devices,equipped with many sensors and actuators,continuously produce vast volumes of ***,the conventional approach of transmitting all this data to centralized cloud infrastructures for processing and analysis poses significant ***,transmitting all this data to a centralized cloud infrastructure for processing and analysis can be inefficient and impractical due to bandwidth limitations,network latency,and scalability *** paper proposed a Self-Learning Internet Traffic Fuzzy Classifier(SLItFC)for traffic data *** proposed techniques effectively utilize clustering and classification procedures to improve classification accuracy in analyzing network traffic *** addresses the intricate task of efficiently managing and analyzing IoT data traffic at the *** employs a sophisticated combination of fuzzy clustering and self-learning techniques,allowing it to adapt and improve its classification accuracy over *** adaptability is a crucial feature,given the dynamic nature of IoT environments where data patterns and traffic characteristics can evolve *** the implementation of the fuzzy classifier,the accuracy of the clustering process is improvised with the reduction of the computational *** can reduce computational time while maintaining high classification *** efficiency is paramount in edge computing,where resource constraints demand streamlined data ***,SLItFC’s performance advantages make it a compelling choice for organizations seeking to harness the potential of IoT data for real-time insig

关键词： Internet of Things(IoT) edge computing traffic data self-learning fuzzy-learning