检索结果-南通市图书馆

Deep-reinforcement-learning-based UAV autonomous navigation and collision avoidance in unknown environments

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 Aeronautics 2024年第3期37卷 237-257页

作者： Fei WANG Xiaoping ZHU zhou zhou yang TANG School of Astronautics Northwestern Polytechnical UniversityXi’an 710072China School of Aeronautics Northwestern Polytechnical UniversityXi’an 710072China

In some military application scenarios,Unmanned Aerial Vehicles(UAVs)need to perform missions with the assistance of on-board cameras when radar is not available and communication is interrupted,which brings challenges for UAV autonomous navigation and collision *** this paper,an improved deep-reinforcement-learning algorithm,Deep Q-Network with a Faster R-CNN model and a Data Deposit Mechanism(FRDDM-DQN),is proposed.A Faster R-CNN model(FR)is introduced and optimized to obtain the ability to extract obstacle information from images,and a new replay memory Data Deposit Mechanism(DDM)is designed to train an agent with a better *** training,a two-part training approach is used to reduce the time spent on training as we.l as retraining when the scenario *** order to verify the performance of the proposed method,a series of experiments,including training experiments,test experiments,and typical episodes experiments,is conducted in a 3D simulation *** results show that the agent trained by the proposed FRDDM-DQN has the ability to navigate autonomously and avoid collisions,and performs better compared to the FRDQN,FR-DDQN,FR-Dueling DQN,YOLO-based YDDM-DQN,and original FR outputbased FR-ODQN.

关键词： Faster R-CNN model Replay memory Data Deposit Mechanism(DDM) Two-part training approach Image-based Autonomous Navigation and Collision Avoidance(ANCA) Unmanned Aerial Vehicle(UAV)

Phase field modeling of ferroelastic variant switching in yttria-stabilized t'zirconia with strain gradient elasticity and interface tension

在线全文

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2024年第5期67卷 1443-1457页

作者： zhou QianQian we. YueGuang zhou YiChun yang Li College of Engineering BIC-ESATPeking UniversityBeijing100871China School of Advanced Materials and Nanotechnology Xidian UniversityXi’an710126China Frontier Research Center of Thin Films and Coatings for Device Applications Academy of Advanced Interdisciplinary ResearchXidian UniversityXi’an710126China

The 6–8 wt%yttria-stabilized zirconia with a tetragonal structure(t’-YSZ)is extensively employed in thermal barrier *** exceptional fracture toughness of t’-YSZ can be attributed to its distinctive ferroelastic toughening *** and interface tension play a critical role in ferroelastic variant switching at the micro-and *** paper presents an original thermodynamically consistent phase field(PF)theory for analyzing ferroelastic variant switching at the micro-and nano-scale of t’-*** theory incorporates strain gradient elasticity using higher-order elastic energy and interface tension tensor via geometric nonlinearity to represent biaxial tension resulting from interface ***,a mixed-type formulation is employed to implement the higher-order theory through the finite element *** an interface in equilibrium,the effects of strain gradient elasticity result in a more uniform distribution of stresses,whereas the presence of interface tension tensor significantly amplifies the stress magnitude at the *** introduction of an interface tension tensor increases the maximum value of stress at the interface by a factor of 4 to *** nucleation and evolution of variants at a pre-existing crack tip in a mono-phase t’-YSZ have also been *** strain gradient elasticity is capable of capturing the size effect of ferroelastic variant switching associated with microstructures in ***,when the grain size approaches that of the specimen,the critical load required for variant switching at the crack tip increases,resulting in greater dissipation of elastic energy during ferroelastic variant ***,the interface tension accelerates the evolution of *** presented framework exhibits significant potential in modeling ferroelastic variant switching at the micro-and nano-scale.

关键词： thermodynamics strain gradient elasticity interface tension phase field method ferroelastic variant switching

Stabilization/solidification mechanisms of tin tailings and fuming slag-based geopolymers for different heavy metals

在线全文

学校读者我要写书评

暂无评论

Frontiers of Environmental Science & Engineering 2024年第5期18卷 43-55页

作者： Xian zhou Zhengfu Zhang Hui yang School of Materials Science and Engineering Kunming University of Science and TechnologyKunming650093China Kunming Metallurgical Research Institute Co. Ltd.Kunming650031China

Tin mine tailings(TMT)and fuming slag(FS)contain many heavy metals(As,Cr,Cu,Zn and Mn)that cause severe pollution to the ***,geopolymers we.e prepared using TMT,FS and flue gas desulfurization gypsum(FGDG)to immobilize heavy metals,and their compressive strength and heavy metal leaching toxicity we.e *** was first determined that T4F5(TMT:FS=4:5)sample exhibited the highest compressive strength(7.83 MPa).T4F5 achieved 95%immobilization efficiency for As and Cr,and nearly 100%for Cu,Zn and Mn,showing good immobilization performance.A series of characterization analyses showe. that heavy metal cations can balance the charge in the geopolymer and replace Al in the geopolymer structure to form covalent *** addition,about 2%–20%of heavy metal Fe was immobilized in hydration products,heavy metal hydroxides and non-bridging Si–O and Al–O coordination with silica-aluminate ***_(3)^(3−) was oxidized into AsO_(4)^(3−),which may form Ca–As or Fe–As ***_(2)O_(7)^(2−)was converted to CrO_(4)^(2−)under alkaline environment and then combined with OH−to form Cr(OH)3 ***^(2+)may react directly with dissolved silicate to form Mn_(2)SiO_(4) and also form Mn(OH)_(2) *** unstable Mn(OH)_(2) can be further oxidized to MnO_(2).The heavy metal cations we.e immobilized in the silicoaluminate lattice,while the anions tended to form insoluble *** results may benefit the industry and government for better handling of TMT,FS and solid wastes containing the abovementioned five heavy metals.

关键词： Heavy metals Cementitious materials Tin tailings Stabilization/solidification Redox

Intelligent feedforward gust alleviation based on neural network

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 Aeronautics 2024年第3期37卷 116-132页

作者： Yitao zhou Zhigang WU Chao yang School of Aeronautic Science and Engineering Beihang UniversityBeijing 100191China

This paper proposes a neural network-based intelligent feedforward gust alleviation framework,which includes a neural network identification model and a neural network controller.A neural network training dataset is formed by collecting flight data and the gust data encountered during the aircraft flight.A neural network identification model is first trained to accurately predict the aircraft’s ***,based on the output of the identification model and the collected flight data,the parameters of the time-delay neural network controller are obtained through a learning *** simulation results show that the designed intelligent controller has good gust alleviation effects for both continuous turbulence excitation and discrete gust *** example,when the aircraft is 40000 kg and the flight speed is 0.81Ma,the controller achieves a 67.82%reduction in wingtip acceleration and a 35.90%reduction in center of mass acceleration under continuous turbulence *** considering the measurement uncertainties,such as noise existing in the collected data,the trained controller can still achieve an acceptable gust alleviation ***,considering a flight in which the aircraft mass is constantly changing,the intelligent controller,which continuously learns from new flight data,maintains a good gust alleviation effect throughout the flight.

关键词： Gust alleviation Intelligent control Feedforward control Neural networks Time-varying aircraft

Game-theoretical Model for Dynamic Defense Resource Allocation in Cyber-physical Powe. Systems Under Distributed Denial of Service Attacks

在线全文

学校读者我要写书评

暂无评论

Journal of Modern Powe. Systems and Clean Energy 2024年第1期12卷 41-51页

作者： Bingjing Yan Pengchao Yao Tao yang Boyang zhou Qiang yang the College of Electrical Engineering Zhejiang UniversityHangzhou 310027China Zhejiang Lab Hangzhou 311100China

Electric powe. grids are evolving into complex cyber-physical powe. systems(CPPSs)that integrate advanced information and communication technologies(ICTs)but face increasing cyberspace threats and *** study considers CPPS cyberspace security under distributed denial of service(DDoS)attacks and proposes a nonzero-sum game-theoretical model with incomplete information for appropriate allocation of defense resources based on the availability of limited *** time delay is applied to quantify the expected utility as CPPSs have high time requirements and incur massive damage DDoS *** resource allocation strategies are adopted by attackers and defenders under the three cases of attack-free,failed attack,and successful attack,which lead to a corresponding consumption of resources.A multidimensional node value analysis is designed to introduce physical and cybersecurity *** experiments and numerical results demonstrate the effectiveness of the proposed model for the appropriate allocation of defense resources in CPPSs under limited resource availability.

关键词： Game theory complex cyber-physical powe. system(CPPS) multidimensional evaluation distributed denial of service(DDoS)attack

An adaptive energy regulation in a memristive map linearized from a circuit with two memristive channels

在线全文

学校读者我要写书评

暂无评论

Communications in Theoretical Physics 2024年第3期76卷 42-50页

作者： Feifei yang Ping zhou Jun Ma School of Science Chongqing University of Posts and TelecommunicationsChongqing 430065China College of Electrical and Information Engineering Lanzhou University of TechnologyLanzhou 730050China Department of Physics Lanzhou University of TechnologyLanzhou 730050China

Nonlinear circuits can show multistability when a magnetic flux-dependent memristor(MFDM) or a charge-sensitive memristor(CSM) is incorporated into a one branch circuit,which helps estimate magnetic or electric field *** this paper,two different kinds of memristors are incorporated into two branch circuits composed of a capacitor and a nonlinear resistor,thus a memristive circuit with double memristive channels is *** circuit equations are presented,and the dynamics in this oscillator with two memristive terms are ***,the memristive oscillator is converted into a memristive map by applying linear transformation on the sampled time series for the memristive *** Hamilton energy function for the memristive oscillator is obtained by using the Helmholtz theorem,and it can be mapped from the field energy of the memristive *** energy function for the dual memristive map is suggested by imposing suitable we.ghts on the discrete energy *** dynamical behaviors of the new memristive map are investigated,and an adaptive law is proposed to regulate the firing mode in the memristive *** work will provide a theoretical basis and experimental guidance for oscillator-to-map transformation and discrete map energy calculation.

关键词： Hamilton energy dual memristive map adaptive energy regulation

Image-Based Flow Prediction of Vocal Folds Using 3D Convolutional Neural Networks

在线全文

学校读者我要写书评

暂无评论

Journal of Bionic Engineering 2024年第2期21卷 991-1002页

作者： yang Zhang Tianmei Pu Jiasen Xu Chunhua zhou College of Astronautics Nanjing University of Aeronautics and AstronauticsNanjing210016China College of Electrical Energy and Power EngineeringYangzhou UniversityYangzhou225127China College of Aeronautics Nanjing University of Aeronautics and AstronauticsNanjing210016China

In this work,a three dimensional(3D)convolutional neural network(CNN)model based on image slices of various normal and pathological vocal folds is proposed for accurate and efficient prediction of glottal *** 3D CNN model is composed of the feature extraction block and regression *** feature extraction block is capable of learning low dimensional features from the high dimensional image data of the glottal shape,and the regression block is employed to flatten the output from the feature extraction block and obtain the desired glottal flow *** input image data is the condensed set of 2D image slices captured in the axial plane of the 3D vocal folds,where these glottal shapes are synthesized based on the equations of normal vibration *** output flow data is the corresponding flow rate,averaged glottal pressure and nodal pressure distributions over the glottal *** 3D CNN model is built to establish the mapping betwe.n the input image data and output flow *** ground-truth flow variables of each glottal shape in the training and test datasets are obtained by a high-fidelity sharp-interface immersed-boundary *** proposed model is trained to predict the concerned flow variables for glottal shapes in the test *** present 3D CNN model is more efficient than traditional Computational Fluid Dynamics(CFD)models while the accuracy can still be retained,and more powe.ful than previous data-driven prediction models because more details of the glottal flow can be *** prediction performance of the trained 3D CNN model in accuracy and efficiency indicates that this model could be promising for future clinical applications.

关键词： Vocal folds Computational fluid dynamics Machine learning 3D convolutional neural network

Maximizing Submodular+Supermodular Functions Subject to a Fairness Constraint

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2024年第1期29卷 46-55页

作者： Zhenning Zhang Kaiqiao Meng Donglei Du yang zhou Beijing Institute for Scientific and Engineering Computing Beijing University of TechnologyBeijing 100124China Faculty of Management University of New BrunswickFredericton E3B 5A3Canada School of Mathematics and Statistics Shandong Normal UniversityJinan 250014China

we.investigate the problem of maximizing the sum of submodular and supermodular functions under a fairness *** sum function is non-submodular in *** an offline model,we.introduce two approximation algorithms:A greedy algorithm and a threshold greedy *** a streaming model,we.propose a one-pass streaming *** also analyze the approximation ratios of these algorithms,which all depend on the total curvature of the supermodular *** total curvature is computable in polynomial time and widely utilized in the literature.

关键词： submodular function supermodular function fairness constraint greedy algorithm threshold greedy algorithm streaming algorithm

An initial investigation of the non-isotropic feature of GNSS tropospheric delay

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Satellite Navigation 2024年第1期5卷 155-167页

作者： Ying Xu Zaozao yang Hongzhan zhou Fangzhao Zhang College of Geodesy and Geomatics Shandong University of Science and Technology579 Qianwangang RoadQingdao266590ShandongChina

Tropospheric delay is a significant error source in Global Navigation Satellite Systems(GNSS)*** Path Delay(SPD)is commonly derived by multiplying Zenith Tropospheric Delay(ZTD)with a mapping ***,mapping functions,assuming atmospheric isotropy,restrict the accuracy of derived *** improve the accuracy,a horizontal gradient correction is introduced to account for azimuth-dependent SPD variations,treating the atmosphere as *** study uncovers that,amidst atmospheric dynamics and spatiotemporal changes in moisture content,the SPD deviates from that based on traditional isotropy or anisotropy *** innovatively introduces the concept that SPD exhibits non-isotropy with respect to azimuth *** validation involves assessing SPD accuracy using three mapping functions at five International GNSS Service(IGS)stations,referencing the SPD with the ray-tracing *** subsequently evaluates the SPD accuracy with horizontal gradient correction based on Vienna Mapping Function 3(VMF3)***,the non-isotropic of SPD is analyzed through the ray-tracing *** results indicate the smallest residual(1.1–82.7 mm)betwe.n the SPDs with VMF3 and those with the ***,introducing horizontal gradient correction yields no significant improvement of SPD *** potential decimeter-level differences in SPD due to non-isotropic tropospheric delay across azimuth angles,a precise grasp and summary of these variations is pivotal for accurate tropospheric delay *** finding provides vital support for future high-precision tropospheric delay modeling.

关键词： Tropospheric delay GNSS Non-isotropy Mapping function Ray-tracing Horizontal gradient ERA5