检索结果-内蒙古大学图书馆

A Transfer Learning Framework for Deep Multi-Agent Reinforcement Learning

IEEE/CAA Journal of Automatica Sinica 2024年第11期11卷 2346-2348页

作者： Yi Liu Xiang Wu Yuming Bo Jiacun Wang Lifeng Ma the School of Automation Nanjing University of Science and Technology the Department of Computer Science and Software Engineering Monmouth University

Dear Editor,This letter presents a new transfer learning framework for the deep multi-agent reinforcement learning(DMARL) to reduce the convergence difficulty and training time when applying DMARL to a new scenario [1... 详细信息

关键词： Deep agent Framework

来源：评论

学校读者我要写书评

暂无评论

Research on simulation of gun muzzle flow field empowered by artificial intelligence

引用

Defence Technology（防务技术） 2024年第2期32卷 196-208页

作者： Mengdi Zhou Linfang Qian Congyong Cao Guangsong Chen Jin Kong Ming-hao Tong School of Mechanical Engineering Nanjing University of Science and TechnologyNanjing210094China Northwest Institute of Mechanical and Electrical Engineering Xianyang712099ShaanxiChina School of Automation Nanjing University of Science and TechnologyNanjing210094China

Artificial intelligence technology is introduced into the simulation of muzzle flow field to improve its simulation efficiency in this paper.A data-physical fusion driven framework is ***,the known flow field data is used to initialize the model parameters,so that the parameters to be trained are close to the optimal *** physical prior knowledge is introduced into the training process so that the prediction results not only meet the known flow field information but also meet the physical conservation *** two examples,it is proved that the model under the fusion driven framework can solve the strongly nonlinear flow field problems,and has stronger generalization and *** proposed model is used to solve a muzzle flow field,and the safety clearance behind the barrel side is *** is pointed out that the shape of the safety clearance under different launch speeds is roughly the same,and the pressure disturbance in the area within 9.2 m behind the muzzle section exceeds the safety threshold,which is a dangerous *** with the CFD results shows that the calculation efficiency of the proposed model is greatly improved under the condition of the same calculation *** proposed model can quickly and accurately simulate the muzzle flow field under various launch conditions.

关键词： Muzzle flow field Artificial intelligence Deep learning Data-physical fusion driven Shock wave

来源：评论

学校读者我要写书评

暂无评论

A review on DFACS(II):Modeling and analysis of disturbances and noises

引用

Chinese Journal of Aeronautics 2024年第5期37卷 120-147页

作者： Chenglei YUE Bohan JIAO Zhaohui DANG Xiaokui YUE Yonghe ZHANG Yuanqing XIA Li DUAN Qinglei HU Qifan LIU Pengcheng WANG Ming GUO Zhansheng DUAN Bing CUI Chu ZHANG Xiaodong SHAO School of Astronautics Northwestern Polytechnical UniversityXi’an 710072China Innovation Academy for Microsatellites Chinese Academy of SciencesShanghai 710699China School of Automation Beijing Institute of TechnologyBeijing 100081China Institute of Mechanics Chinese Academy of SciencesBeijing 710043China School of Automation Science and Electrical Engineering Beihang UniversityBeijing 100191China School of Automation Science and Engineering Xi’an Jiaotong UniversityXi’an 710049China

This paper presents Part II of a review on DFACS,which specifically focuses on the modeling and analysis of disturbances and noises in *** Part I,the system composition and dynamics model of the DFACS were *** this paper,we discuss the effects of disturbance forces and noises on the system,and summarize various analysis and modeling methods for these interferences,including the integral method,frequency domain analysis method,and magnitude evaluation *** analyzing the impact of disturbances and noises on the system,the paper also summarizes the system’s performance under slight ***,we highlight current research difficulties in the field of DFACS noise ***,this paper provides valuable insights into the modeling and analysis of disturbances and noises in DFACSs,and identifies key areas for future research.

关键词： Drag-free DFACS Disturbance Analysis Noise Analysis Frequency Domain Analysis Performance Evaluation

来源：评论

学校读者我要写书评

暂无评论

NPE-DRL: Enhancing Perception Constrained Obstacle Avoidance With Nonexpert Policy Guided Reinforcement Learning

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第1期6卷 184-198页

作者： Zhang, Yuhang Yan, Chao Xiao, Jiaping Feroskhan, Mir Nanyang Technological University School of Mechanical and Aerospace Engineering 639798 Singapore Nanjing University of Aeronautics and Astronautics College of Automation Engineering Nanjing211106 China

Obstacle avoidance under constrained visual perception presents a significant challenge, requiring rapid detection and decision-making within partially observable environments, particularly for unmanned aerial vehicles (UAVs) maneuvering agilely in 3-D space. Compared with traditional methods, obstacle avoidance algorithms based on deep reinforcement learning (DRL) offer a better comprehension of the uncertain operational environment in an end-to-end manner, reducing computational complexity, and enhancing flexibility and scalability. However, the inherent trial-and-error learning mechanism of DRL necessitates numerous iterations for policy convergence, leading to sample inefficiency issues. Meanwhile, existing sample-efficient obstacle avoidance approaches that leverage imitation learning often heavily rely on offline expert demonstrations, which are not always feasible in hazardous environments. To address these challenges, we propose a novel obstacle avoidance approach based on nonexpert policy enhanced DRL (NPE-DRL). This approach integrates a fundamental DRL framework with prior knowledge derived from a nonexpert policy-guided imitation learning. During the training phase, the agent starts by online imitating the actions generated by the nonexpert policy during interactions and progressively shifts toward autonomously exploring the environment to generate the optimal policy. Both simulation and physical experiments validate that our approach improves sample efficiency and achieves a better exploration-exploitation balance in both virtual and real-world flights. Additionally, our NPE-DRL-based obstacle avoidance approach shows better adaptability in complex environments characterized by larger scales and denser obstacle configurations, demonstrating a significant improvement in UAVs' obstacle avoidance capability. Code available at https://***/zzzzzyh111/NonExpert-Guided-Visual-UAV-Navigation-Gazebo. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Learning Empirical Inherited Intelligent MPC for Switched Systems With Network Security Communication

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6342-6355页

作者： Qi, Yiwen Tang, Yiwen Yu, Wenke Fuzhou University College of Electrical Engineering and Automation Fuzhou350108 China Shenyang Aerospace University School of Automation Shenyang110136 China

This article studies learning empirical inherited intelligent model predictive control (LEII-MPC) for switched systems. For complex environments and systems, an intelligent control method design with learning ability is necessary and meaningful. First, a switching law that coordinates the iterative learning control action is devised according to the average dwell time approach. Second, an intelligent MPC mechanism with the iteration learning experience is designed to optimize the control action. With the designed LEII-MPC, sufficient conditions for the switched systems stability equipped with the event-triggering schemes (ETSs) in both the time domain and the iterative domain are presented. The ETS in the iterative domain is to solve unnecessary iterative updates. The ETS in the time domain is to deal with potential denial of service (DoS) attacks, which includes two parts: 1) for detection, an attack-dependent event-triggering method is presented to determine attack sequence and reduce lost packets;and 2) for compensation, a buffer is used to ensure system performance during the attack period. Last, a numerical example shows the effectiveness of the proposed method. © 2020 IEEE.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

Information mining and mechanical analysis of new-generation aero-engine turbine discs with industrial computed laminography reverse engineering

引用

Chinese Journal of Aeronautics 2025年第4期38卷 361-377页

作者： Yenan GAO School of Mechanical Engineering and Automation Beihang UniversityBeijing 100191China China North Industries Group Corporation Limited Beijing 100089China

Aero engines are key power components that provide thrust for the *** cerme turbine disc allows the new-generation domestic fighter aircraft to increase the overall thrust of the aero *** coatings and analyzing the stress on the teeth play critical roles in improving the turbine disc’s performance,which are two issues must be solved ***,this work pro poses a quantitative analysis algorithm to conduct the Three-Dimensional(3D)distribution informa tion mining of the extracted ***,it proposes an Industrial Computed Laminography(ICL)reconstruction algorithm for non-destructively reconstructing the turbine disc’s high-quality3D morphological actual ***,a Finite Element Analysis(FEA)under the ultimate thrus is conducted on ICL reconstruction to verify the working status of the new-generation aero-engine turbine *** results show that the proposed quantitative analysis algorithm digitizes the aggre gated conditions of the coating with a statistically normalized Z_(1)value of–2.15 and a confidence leve higher than 95%.Three image-quality quantitative indicators:Peak Signal-to-Noise Ratio(PSNR)Structural Similarity Index Measure(SSIM),and Normalized Mean Square Distance(NMSD)of the proposed ICL reconstruction algorithm on turbine disc laminographic image are 26.45,0.88,and 0.73respectively,which are better than other *** mechanical analysis of ICL more realisti cally reflects the stress and deformation than that of 3D *** work provides new ideas for the iterative research of new-generation aero-engine turbine discs.

关键词： Aero engines Quantitative analysis algorithm Information mining Industrial computed laminography reconstruction algorithm Finite element analysis

来源：评论

学校读者我要写书评

暂无评论

Model for atomization droplet size and energy distribution ratio at the distal end of an electrostatic nozzle

引用

Frontiers of Mechanical engineering 2024年第5期19卷 33-58页

作者： Dongzhou JIA Keke JIANG Yanbin ZHANG Zhenlin LV Changhe LI College of Mechanical Engineering and Automation Liaoning University of TechnologyJinzhou 121001China School of Materials Science and Engineering Xi’an University of TechnologyXi’an 710048China School of Mechanical and Automotive Engineering Qingdao University of TechnologyQingdao 266520China

Electrostatic atomization minimum quantity lubrication(EMQL)employs the synergistic effect of multiple physical fields to atomize minute quantities of *** innovative methodology is distinguished by its capacity to ameliorate the atomization attributes of the lubricant substantially,which subsequently augments the migratory and infiltration proficiency of the droplets within the complex and demanding milieu of the cutting *** with the traditional minimum quantity lubrication(MQL),the EMQL process is further complicated by the multiphysical field *** presence of multiple physical fields not only increases the complexity of the forces acting on the liquid film but also induces changes in the physical properties of the lubricant itself,thus making the analysis of atomization characteristics and energy distribution particularly *** address this objective reality,the current study has conducted a meticulous measurement of the volume average diameter,size distribution span,and the percentage concentration of inhalable particles of the charged droplets at various intercept positions of the EMQL nozzle.A predictive model for the volume-averaged droplet size at the far end of the EMQL nozzle was established with the observed statistical value F of 825.2125,which indicates a high regression accuracy of the ***,based on the changes in the potential energy of surface tension,the loss of kinetic energy of gas,and the electric field work at different nozzle orifice positions in the EMQL system,an energy distribution ratio model for EMQL was *** energy distribution ratio coefficients under operating conditions of 0.1 MPa air pressure and 0 to 40 kV voltage on the 20 mm cross-section ranged from 3.094‰to 3.458‰,while all other operating conditions and cross-sections had energy distribution ratios below 2.06‰.This research is expected to act as a catalyst for the progression of EMQL by stimulating innovation in the sp

关键词： atomization performance EMQL energy distribution PIV observation sustainable manufacturing

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Excitation Variable-Leakage-Flux Machine with Magnetic-Bridge for Electric Vehicle

引用

Progress In Electromagnetics Research C 2024年 145卷 35-43页

作者： Lu, Ruipan Huang, Xinlong Liu, Zhangqi Liu, Xiping School of Electrical Engineering and Automation Jiangxi University of Science and Technology Jiangxi Ganzhou341000 China

A hybrid excitation variable-leakage-flux machine (HE-VLFM) for electric vehicles is presented in this paper, which places the excitation windings on the outer side of the stator and provides an axial magnetic field through the magnetic-conducting ring and magnetic-conducting bridge. The HE-VLFM proposed in this paper has a rotor permanent magnet to provide the main magnetic field and an excitation winding to provide a variable auxiliary magnetic field, which can fulfill the requirements of the electric vehicle drive system with large torque at low-speed and wide speed regulation range. The electromagnetic performance of the proposed HE-VLFM is evaluated using the equivalent magnetic circuit method and three-dimensional finite element analysis, and the results show that the HE-VLFM has a well-developed regulating flux capability. © 2024, Electromagnetics Academy. All rights reserved.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

A Current Sensorless Interval Torque Ripple Suppression Method for Permanent Magnet assisted-Switched Reluctance Motor

引用

Progress in Electromagnetics Research C 2024年 150卷 69-80页

作者： Gong, Chengyi Xu, Junxin Xiao, Renquan Huang, Chaozhi Liu, Xiaobo Xiao, Yong School of Electrical Engineering and Automation Jiangxi University of Science and Technology Jiangxi Ganzhou341000 China

The conventional DITC strategy for switched reluctance motor relies on current for control, while the use of current sensors increases the complexity of the system, and the torque ripple in the two-phase exchange region of the conventional DITC strategy is too large. To solve the above problems, a current sensorless interval torque control (CSITC) method is proposed. Initially, the equivalence between torque and acceleration control is established, replacing the torque loop with an acceleration loop. This forms a dual closed-loop system with the speed control loop, enhancing system stability. Subsequently, the variation of the output torque capacity of phase winding of the motor in each conduction region is analyzed, and combined with the inductive characteristics of the motor windings, the two-phase exchange region is divided into two subregions. Different acceleration hysteresis loop control strategies are adopted for the phase windings in each region, so as to realize the stable output of the motor torque. Finally, a three-phase 6/20 permanent magnet assisted-switched reluctance motor (PMa-SRM) is used for simulation and physical verification. The results show that the method can still achieve the steady state of the motor when only the position sensor is used and effectively reduces the torque ripple in the exchange region. © 2024, Electromagnetics Academy. All rights reserved.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

Multi-step state-based opacity for unambiguous weighted machines

引用

Science China(Information Sciences) 2024年第11期67卷 211-221页

作者： Zhipeng ZHANG Chengyi XIA Guoyuan QI Jun FU School of Artificial Intelligence Tiangong University School of Control Science and Engineering Tiangong University State Key Laboratory of Synthetical Automation for Process Industries Northeastern University

Opacity is a central concept in the issue of privacy security and has been studied extensively in fields such as finite automata, probabilistic automata, and stochastic automata. Here, we investigate the problem of validating multi-step opaque properties through unambiguous weighted machines from the perspective of cyber-physical systems. First, the notion of multi-step state-based opacity for unambiguous weighted machines is presented and defined. It includes two variants of delays with a finite K and infinite steps. Subsequently, the weighted state estimate with K(infinite)-step delay is established by abstracting the possible state set that the system could have through these weighted observations. Meanwhile, to keep the observable weighted sequence consistent between the bidirectional observers, the unobserved weights of the reverse weighted machine are assumed to be reserved. Subsequently, the existence conditions are developed, and the corresponding algorithms, termed the weighted bidirectional observer, are generalized to verify these properties. Finally, several numerical examples are illustrated to demonstrate the effectiveness of the proposed method. Taken together, the current approach will be conducive to a deep understanding of the security and privacy of cyber-physical systems.

关键词： logical dynamical systems weighted state machine state estimation opacity cyber physical systems

来源：评论

学校读者我要写书评

暂无评论

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

请选择保存的检索档案：

请选择收藏分类：

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

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

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：