检索结果-南通市图书馆

Structure-Preserving Recurrent neural networks for a Class of Birkhoffian Systems

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 Science & Complexity 2024年第2期37卷 441-462页

作者： XIAO Shanshan CHEn Mengyi ZHAnG Ruili tang Yifa LSEC ICMSECAcademy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China School of Mathematical Sciences University of Chinese Academy of SciencesBeijing 100049China School of Mathematics and Statistics Beijing Jiaotong UniversityBeijing 100044China

In this paper,the authors propose a neural network architecture designed specifically for a class of Birkhoffian systems—The newtonian *** proposed model utilizes recurrent neural networks(Rnns)and is based on a mathematical framework that ensures the preservation of the Birkhoffian *** authors demonstrate the effectiveness of the proposed model on a variety of problems for which preserving the Birkhoffian structure is important,including the linear damped oscillator,the Van der Pol equation,and a high-dimensional *** with the unstructured baseline models,the newtonian neural network(nnn)is more data efficient,and exhibits superior generalization ability.

关键词： Birkhoffian system k(z,t)-symplectic neural networks recurrent neural network

The Investigation of Data Voting Algorithm for Train Air-Braking System Based on Multi-Classification SVM and AnFIS

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2024年第1期33卷 274-281页

作者： Juhan wAnG Ying GAO Yuan CAO Tao tang School of Electronics and Information Engineering Beijing Jiaotong University Graduate Department China Academy of Railway Science national Engineering Research Center of Rail Transportation Operation and Control System Beijing Jiaotong University

The pressure data of the train air braking system is of great significance to accurately evaluate its operation state. In order to overcome the influence of sensor fault on the pressure data of train air braking system, it is necessary to design a set of sensor fault-tolerant voting mechanism to ensure that in the case of a pressure sensor fault, the system can accurately identify and locate the position of the faulty sensor, and estimate the fault data according to other normal data. A fault-tolerant mechanism based on multi-classification support vector machine(SVM) and adaptive network-based fuzzy inference system(AnFIS) is introduced. Multi-classification SVM is used to identify and locate the system fault state, and AnFIS is used to estimate the real data of the fault sensor. After estimation, the system will compare the real data of the fault sensor with the AnFIS estimated data. If it is similar,the system will recognize that there is a false alarm and record it. Then the paper tests the whole mechanism based on the real data. The test shows that the system can identify the fault samples and reduce the occurrence of false alarms.

关键词： Support vector machines Fault diagnosis Pressure sensors Fuzzy logic Fault tolerance Adaptive systems Fault tolerant systems

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

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 well 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)

A physics-informed neural network for simulation of finite deformation in hyperelastic-magnetic coupling problems

在线全文

学校读者我要写书评

暂无评论

Applied Mathematics and Mechanics(English Edition) 2024年第10期45卷 1717-1732页

作者： wAnG Lei LUO Zikun LU Mengkai tang Minghai Department of Engineering Mechanics College of Mechanics and Engineering SciencesHohai UniversityNanjing 211100China School of Mechanical Engineering and Mechanics Ningbo UniversityNingbo 315211Zhejiang ProvinceChina

Recently,numerous studies have demonstrated that the physics-informed neural network(PInn)can effectively and accurately resolve hyperelastic finite deformation *** this paper,a PInn framework for tackling hyperelastic-magnetic coupling problems is *** the solution space consists of two-phase domains,two separate networks are constructed to independently predict the solution for each phase *** addition,a conscious point allocation strategy is incorporated to enhance the prediction precision of the PInn in regions characterized by sharp *** the developed framework,the magnetic fields and deformation fields of magnetorheological elastomers(MREs)are solved under the control of hyperelastic-magnetic coupling *** examples are provided and contrasted with the reference results to validate the predictive accuracy of the proposed ***,the advantages of the proposed framework in solving hyperelastic-magnetic coupling problems are validated,particularly in handling small data sets,as well as its ability in swiftly and precisely forecasting magnetostrictive motion.

关键词： physics-informed neural network(PInn) deep learning hyperelastic-magnetic coupling finite deformation small data set

Research on modeling and self-excited vibration mechanism in magnetic levitation-collision interface coupling system

在线全文

学校读者我要写书评

暂无评论

Applied Mathematics and Mechanics(English Edition) 2024年第5期45卷 873-890页

作者： Jinghu tang Chaofeng LI Jin ZHOU Zhiwei wU School of Mechanical Engineering&Automation Northeastern UniversityShenyang 110819China Key Laboratory of Vibration and Control of Aero-Propulsion Systems of Ministry of Education of China Northeastern UniversityShenyang 110819China School of Mechanical and Electrical Engineering Nanjing University of Aeronautics and AstronauticsNanjing 210016China

The modeling and self-excited vibration mechanism in the magnetic levitation-collision interface coupling system are *** effects of the control and interface parameters on the system's stability are *** frequency range of self-excited vibrations is investigated from the energy point of *** phenomenon of self-excited vibrations is elaborated with the phase *** corresponding control strategies are briefly analyzed with respect to the vibration *** results show that when the levitation objects collide with the mechanical interface,the system's vibration frequency becomes larger with the decrease in the collision gap;when the vibration frequency exceeds the critical frequency,the electromagnetic system continues to provide energy to the system,and the collision interface continuously dissipates energy so that the system enters the self-excited vibration state.

关键词： magnetic levitation coupling system self-excited vibration mechanical interface vibration frequency

Microstructure and mechanical properties stability of pre-hardening treatment in Al-Cu alloys for pre-hardening forming process

在线全文

学校读者我要写书评

暂无评论

International Journal of Minerals,Metallurgy and Materials 2024年第3期31卷 539-551页

作者： Liping tang Pengfei wei Zhili Hu Qiu Pang Hubei Longzhong laboratory Xiangyang 441000China Hubei Key Laboratory of Advanced Technology for Automotive Components School of Automotive EngineeringWuhan University of TechnologyWuhan 430070China Hubei Engineering Research Center for Green&Precision Material Forming Wuhan University of TechnologyWuhan 430070China Key Laboratory of Metallurgical Equipment and Control Technology of Ministry of Education School of Machinery and AutomationWuhan University of Science and TechnologyWuhan 430081China

The stability of the microstructure and mechanical properties of the pre-hardened sheets during the pre-hardening forming(PHF)process directly determines the quality of the formed *** microstructure stability of the pre-hardened sheets was in-vestigated by differential scanning calorimetry(DSC),transmission electron microscopy(TEM),and small angle X-ray scattering(SAXS),while the mechanical properties and formability were analyzed through uniaxial tensile tests and formability *** results in-dicate that the mechanical properties of the pre-hardened alloys exhibited negligible changes after experiencing 1-month natural aging(nA).The deviations of ultimate tensile strength(UTS),yield strength(YS),and sheet formability(Erichsen value)are all less than 2%.Also,after different nA time(from 48 h to 1 month)is applied to alloys before pre-hardening treatment,the pre-hardened alloys possess stable microstructure and mechanical properties as ***,with the extension of nA time before pre-hardening treatment from 48 h to 1 month,the contribution of nA to the pre-hardening treatment is *** a yield strength increment of 20 MPa is achieved,with no loss in *** limited enhancement is mainly attributed to the fact that only a limited number of clusters are transformed into Guinier-Preston(GP)zones at the early stage of pre-hardening treatment,and the formation ofθ''phase inhibits the nucleation and growth of GP zones as the precipitated phase evolves.

关键词： Al-Cu alloy pre-hardened alloy natural aging mechanical properties microstructure

The Structure Entropy of Social networks

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Science & Complexity 2024年第3期37卷 1147-1162页

作者： LI Zhenpeng YAn Zhihua YAnG Jian tang Xijin School of Electronics and Information Engineering Taizhou UniversityLinhai 317000China Academy of Mathematics and Systems Science Chinese Academy of SciencesBeijing 100190China Yunnan Key Laboratory of Smart City in Cyberspace Security Yuxi Normal UniversityYuci 653100China University of Chinese Academy of Sciences Beijing 100039China

Micro triadic structure is an important motif and serves the building block of complex *** this paper,the authors define structure entropy for a social network and explain this concept by using the coded triads proposed by Davis and Leinhardt in *** proposed structure entropy serves as a new macro-evolution index to measure the network’s stability at a given *** analysis of real-world network structure entropy discloses rich information on the mechanism that yields given triadic motifs frequency *** paper illustrates the intrinsic link between the micro dyadic/triadic motifs and network structure ***,the authors find that the high proportion of reciprocity and transitivity results in the emergence of hierarchy,order,and cooperation of online social networks.

关键词： Dyadic and triadic motifs network structure entropy reciprocity and transitivity

Macro Meso Response and Stress wave Propagation Characteristics of MCT High-Voltage Switch Under Shock load

在线全文

学校读者我要写书评

暂无评论

Defence Technology（防务技术） 2024年第2期32卷 317-335页

作者： Yuyang Guo Chuang Chen Ruizhi wang Enling tang Key Laboratory of Transient Physical Mechanics and Energy Conversion Materials of Liaoning Province Shenyang Ligong UniversityShenyang110159LiaoningChina

In order to study the dynamic and electrical coupling response characteristics of Metal Oxide Semiconductor Controlled Thyristor(MCT)high-voltage switch under the synergic action of mechanical load and high voltage,the separated Hopkinson pressure bar(SHPB)test system was used to simulate different impact load environments,and combined with the multi-layer high-voltage ceramic capacitor charging and discharging system,the instantaneous electrical signals of MCT high-voltage switch were *** with numerical simulation and theoretical analysis,the failure mode and stress wave propagation characteristics of MCT high voltage switch were *** mechanical and electrical coupling response characteristics and failure mechanism of MCT high voltage switch under dynamic load were revealed from macroscopic and microscopic *** results show that the damage modes of MCT high-voltage switches can be divided into non-functional damage,recoverable functional damage,non-recoverable damage and structural *** to the gap between the metal gate and the oxide layer,the insulating oxide layer was *** placing for a period of time,the elastic deformation of the metal gate partially recovered and the accumulated charge disappeared,which induced the recoverable functional damage failure of the *** addition,obvious cracks appeared on both sides of the monocrystalline silicon inside the MCT high-voltage switch,leading to unrecoverable damage of the device.

关键词： MCT Impact load Failure analysis Stress wave numerical simulation

Civil Ambassador Enriches Peru-China Relations

在线全文

学校读者我要写书评

暂无评论

China news Release 2024年第2期 54-57页

作者： Rubén tang the Pontificia Catholic University of Peruand Asian Academic Institutions

Peru and China are both ancient countries with rich histories and *** immigration to Peru is the most significant in Latin *** first Chinese immigrants arrived in Peru in 1849 to seek a new future in these distant *** initially worked in the fields and later established successful businesses,making important contributions to the country's development across various sectors.

关键词： initially Latin Per