检索结果-内蒙古大学图书馆

Chinese Automation Congress (CAC)

作者： Zeng-Jie Liu Huai-Ning Wu The Science and Technology on Aircraft Control Laboratory School of Automation Science and Electrical Engineering Beihang University Beijing China

ISBN: (数字)9781728176871

ISBN: (纸本)9781728176888

In this paper, an inverse reinforcement learning method based on particle swarm optimization (PSO) is proposed to model driver's steering behavior. Initially, the vehicle dynamics is represented by a Takagi-Sugeno (T-S) fuzzy model which provides a method of approximating Q-function. Then the driver behavior model is described as an optimal control policy with decision-making model which illustrates the driving style. Subsequently, the Q-function is approximated by a quadratic polynomial-in-memberships form and the PSO algorithm is used to obtain the decision-making model from the driving data. And the corresponding optimal control policy is obtained by using the Q-learning policy iteration method. Finally, a numerical simulation is carried to show the effectiveness of the proposed method.

关键词： Vehicles Cost function Vehicle dynamics Optimal control Mathematical model TV Safety

来源：评论

学校读者我要写书评

暂无评论

Multi-sensor Measurement Information Fusion for Maneuvering Target Recognition and Tracking

Multi-sensor Measurement Information Fusion for Maneuvering ...

引用

第40届中国控制会议

作者： Zheng Zhang Liang Han Xiwang Dong Qingdong Li Zhang Ren School of Automation Science and Electrical Engineering Science and Technology on Aircraft Control Laboratory Beihang University School of Sino-French Engineer Beihang University Key Laboratory of Dependable Service Computing in Cyber Physical Society (Chongqing University) Ministry of Education of ChinaChongqing University

This paper proposes multi-sensor information fusion algorithm for maneuvering target recognition and tracking based on mobile sensor networks（MSNs）. In order to improve target recognition accuracy, the modified evidence combination rule is designed to obtain the identity information of target based on the Dempster-Shafer（DS） algorithm. The target recognition process is designed by two stages, namely, sensing stage and fusion stage. During the first stage, each sensor node in the MSNs can obtain the feature information of the target, which makes up the measurement information. In the information fusion stage,each sensor combine the information exchanged from neighboring nodes with local measurement information to obtain the highprecise identity information of the maneuvering target based on the improved DS algorithm. Then, the identity information can be used to obtain the accurate state estimation of the maneuvering target. For the purpose of obtaining the accurate state estimation of target, the target tracking process is designed by local filtering stage and fusion stage. Finally, a numerical simulation is designed to illustrate the effectiveness of the algorithm.

关键词： Information Fusion Target Recognition and Tracking Mobile Sensor Network

来源：评论

学校读者我要写书评

暂无评论

Battlefield Situation Deduction and Maneuver Decision Using Deep Q-Learning

Battlefield Situation Deduction and Maneuver Decision Using ...

引用

第40届中国控制会议

作者： Minghui Shi Xiwang Dong Liang Han Qingdong Li Zhang Ren School of Automation Science and Electrical Engineering Science and Technology on Aircraft Control Laboratory Beihang University Key Laboratory of Dependable Service Computing in Cyber Physical Society (Chongqing University) Ministry of Education of ChinaChongqing University School of Sino-French Engineer Beihang University

As the pace and complexity of modern warfare accelerates, it is of great significance to apply intelligent technology to defense decision-making. Due to the high dynamics and randomness of the aircraft, traditional methods are difficult to solve the optimal control strategy. The characteristics of reinforcement learning match the difficulty of the problem. In this paper, the situation of hypersonic aircraft is deduced, and the deep reinforcement learning method is used to make autonomous penetration decisions in the reentry phase. The model of aircraft and environment is established, and the maneuvering decision-making model is established based on deep Q-learning and its optimization algorithm. Through a large number of simulation training,this method can effectively give the real-time decision output of the agent and make a good prediction of the situation. It has the ability of short-range accurate operation and long-term planning and prediction. This method can improve the probability of successful penetration, and can be used as the decision-making basis of glider penetration.

关键词： Hypersonic aircraft situational deduction maneuver decision-making reinforcement learning deep Q-learning

来源：评论

学校读者我要写书评

暂无评论

Research on Multi-UAVs Formation Flight control Based on Fuzzy PID 19

Research on Multi-UAVs Formation Flight Control Based on Fuz...

引用

Proceedings of the 2019 8th International Conference on Computing and Pattern Recognition

作者： Xiangwei Jiang Boxin Zhao Boyang Zhang Xiaolong Chen Xiongwei Wang Air force engineering university Xi'an China Science and Technology on Aircraft Control Laboratory Xi'an China

ISBN: (纸本)9781450376570

Small Unmanned Aerial Vehicle (UAV for short) has advantages of low cost, light and flexible. But single UAV also has disadvantages of lack of sight distance, sole access to information, limited airborne computing resources, etc. In order to overcome those weaknesses, UAV is undergoing a change for formation cluster. Moreover, UAV formation control is a key technology to ensure effective cooperative formation flight of UAV. [1] Therefore the paper studied the fuzzy PID controller for formation control of mini quad-rotor UAV through MATLAB simulation and contrast with the typical PID controller.

关键词： fuzzy PID control UAVs formation flight

来源：评论

学校读者我要写书评

暂无评论

Neural network-based fully distributed dynamic event-triggered formation-containment control for nonlinear multi-agent systems

引用

Neurocomputing 2025年 642卷

作者： You, Long Qin, Kaiyu Yue, Jiangfeng Li, Weihao Lin, Boxian Shi, Mengji School of Aeronautics and Astronautics University of Electronic Science and Technology of China Chengdu611731 China Aircraft Swarm Intelligent Sensing and Cooperative Control Key Laboratory of Sichuan Province Chengdu611731 China National Laboratory on Adaptive Optics Chengdu610209 China

Achieving robust and fully distributed time-varying formation-containment control for multi-agent systems (MASs) necessitates a trade-off among control accuracy, communication efficiency, and fully distributed implementation, particularly in the presence of unknown system dynamics. To address this issue, this paper proposes a novel adaptive neural network (NN)-based fully distributed dynamic event-triggered control scheme, which ensures robust formation-containment while minimizing communication and computational overhead. Theoretically, a fully distributed event-triggering condition is developed, which eliminates the need for global knowledge and continuous monitoring. Moreover, an aperiodic NN-based approximator is designed to compensate for unknown dynamics, updating NN weights only when triggered, significantly reducing computational load. To sum up, the proposed time-varying formation-containment controller governs both control inputs and NN weights to ensure convergence of approximation and formation errors, achieving practical distributed control. Unlike conventional continuous mechanisms, the proposed scheme triggers controller updates and state transmissions only when a dynamic condition is satisfied, avoiding Zeno behavior and reducing unnecessary resource consumption. Finally, simulation results confirm the effectiveness of the scheme, demonstrating precise control and reduced resource utilization. © 2025 Elsevier B.V.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Neural network-based adaptive prescribed-time bipartite flocking for uncertain networked multi-agent systems

引用

Neurocomputing 2025年 646卷

作者： Qing, Xian Li, Weihao Chen, Bowen Lin, Boxian Shi, Mengji Qin, Kaiyu School of Aeronautics and Astronautics University of Electronic Science and Technology of China Chengdu 611731 China Aircraft Swarm Intelligent Sensing and Cooperative Control Key Laboratory of Sichuan Province Chengdu 611731 China National Laboratory on Adaptive Optics Chengdu 610209 China

Flocking is a fundamental self-organizing behavior observed in networked agent systems (NASs), wherein agents achieve coordinated group dynamics through mutual interactions. While in dynamic environmental contexts, the demand for flocking behavior to demonstrate rapid responsiveness and robust stability becomes more critical. With this in mind, this paper addresses the adaptive bipartite flocking control problem for NASs, particularly in the presence of compound uncertainties and convergence time constraints. A robust adaptive neural network-based prescribed-time bipartite flocking controller is developed to ensure that, despite uncertainties, all agents achieve flocking behavior within a predefined time. Notably, the settling time can be predefined and remains independent of system parameters such as controller gain, initial agent states, and the communication topology among agents. Additionally, by analyzing the stability conditions of the closed-loop error system, an adaptive weight update law for the neural network estimator is formulated. This updated law allows for effective uncertainty estimation through backpropagation of the flocking control error. Finally, the effectiveness and superiority of the proposed prescribed-time bipartite flocking control scheme are validated through numerical simulations. © 2025 Elsevier B.V.

关键词： Bipartite flocking Compound uncertainties Networked multi-agent systems Neural networks Prescribed-time control

来源：评论

学校读者我要写书评

暂无评论

Limit Cycle Oscillation Suppression controller Design and Stability Analysis of the Periodically Time-varying Flapping Flight Dynamics in Hover

Research Square

引用

Research Square 2021年

作者： Wang, Liang Jiang, Wuyao Jiao, Zongxia Zhao, Longfei School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Science and Technology on Aircraft Control Laboratory Beihang University Beijing100191 China Ningbo Institute of Technology Beihang University Ningbo315800 China Research Institute for Frontier Science Beihang University Beijing100191 China

The periodically time-varying forces make the equilibrium state of Beihawk, an X-shaped flapping-wing aircraft, to be a periodic limit cycle oscillation. However, traditional controllers based on averaging theory fail to suppress this oscillation and the derived stability result may be inaccurate. In this study, a period-based method is proposed to design the oscillation suppression controller, locate the corresponding cycle and analyze its stability. A periodically time-varying wing–tail interaction model is built and Discrete Fourier Transform is applied to adapt the model for controller design. The harmonics less than quintuple flapping frequency account for more than 96 percent of the total harmonics and are reserved to present a concise model. Based on this model, Active Disturbance Rejection controller (ADRC) is designed and its Extended State Observer can observe the disturbance to suppress the oscillation. Poincaré map is introduced to convert the stability analysis of the cycle to a fixed point. A multiple shooting method is adopted to locate several points on the cycle and © 2021, CC BY.

关键词： controllers

来源：评论

学校读者我要写书评

暂无评论

A densely connected feature pyramid network for object detection

A densely connected feature pyramid network for object detec...

引用

CSAA/IET International Conference on aircraft Utility Systems 2020, AUS 2020

作者： Zhang, Xiongjie Yan, Liang Gerada, Chris School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Science and Technology on Aircraft Control Laboratory Beihang University Beijing100191 China Ningbo Institute of Technology Beihang University Ningbo315800 China University of Nottingham NottinghamNG7 2RD United Kingdom

ISBN: (纸本)9781839535635

Feature pyramid plays an important role in object detection. Feature Pyramid Network(FPN)[1] looks perfect, but still has some short-comings: Rough coarsest nearest neighbor interpolation is used, so that the high-level feature information may not be effectively propagated. In the paper, we propose more efficient dense feature pyramid network structure, which call Dense-FPN. Our architecture essentially adds a series of dense skip pathways for FPN. Dense-FPN is essentially different from feature pyramid network (FPN)[1]: 1) has a dense skip connection on the skip pathways, which improves the gradient flow and enhances the semantic information;2) uses a dense skip connection to enhance the transfer of features, the semantic information between the down-sampling and up-sampling maps is bridged. Extensive evaluation of multiple data sets shows that under different evaluation indicators, the performance of the model has achieved good performance. © 2020 Institution of Engineering and technology. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Source Term Estimation with Unknown Number of Sources using Improved Cuckoo Search Algorithm

Source Term Estimation with Unknown Number of Sources using ...

引用

第三十九届中国控制会议

作者： Zhi-Pu Wang Huai-Ning Wu Science and Technology on Aircraft Control Laboratory School of Automation Science and Electrical Engineering Beihang University（Beijing University of Aeronautics and Astronautics）

This paper is focused on the source term estimation（STE） with unknown number of sources. The dispersion model of multiple point sources is constructed firstly. Then the cost function is established by using the outputs of dispersion model and the fixed sensor network’s measurements. To ensure finding the global minimum of the cost function, the Improved Cuckoo Search（ICS） algorithm is applied. Simulations with different sensor and noise modes are designed to evaluate the estimating performance. Finally, comparison of ICS, Particle Swarm Optimization（PSO） and Genetic Algorithm（GA） proves the superiority of ICS in this problem.

关键词： Source term estimation unknown number of sources dispersion model Improved Cuckoo Search Algorithm

来源：评论

学校读者我要写书评

暂无评论

Study on life prediction method of mosfet thermal environment experiments based on extended kalman filter 20th

Study on life prediction method of mosfet thermal environmen...

引用

20th International Conference on Man-Machine-Environment System Engineering, MMESE 2020

作者： Li, Ke Zhang, Yuxiang Song, Shimin Zhao, Zhijian Wang, Lijing Fundamental Science on Ergonomics and Environment Control Laboratory School of Aeronautics Science and Engineering & Beijing Advanced Discipline Center for Unmanned Aircraft System Beihang University Beijing100191 China China Academy of Space Technology Beijing100094 China Naval Aeronautical University Yantai264000 China

ISBN: (纸本)9789811569777

The prediction method of the residual service life of power MOSFET is studied in this paper. By analyzing the data collected under the existing thermal overload accelerated aging experiment, after processing the data, the failure threshold was set by using the prediction algorithm based on data drive and model to predict the residual life of power MOSFET. The traditional SVR algorithm requires a lot of parameter selection and only a few parameter convergence. The prediction algorithm model is based on Extended Kalman Filter, the extended Kalman filter is relative to the advantage of support vector machine (SVM) regression is used to predict the variance is small, and can be found in a wide range of required to predict the sample interval and the predicted results are more accurate, the test results verify the feasibility of this method. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2020.

关键词： Extended Kalman filters

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：