检索结果-内蒙古大学图书馆

Interval analysis for neural networks with application to fault detection

Science China(Information Sciences) 2024年第11期67卷 222-237页

作者： Zhenhua WANG Youdao MA Song ZHU Thach Ngoc DINH Yi SHEN Department of Control Science and Engineering Harbin Institute of Technology National Key Laboratory of Complex System Control and Intelligent Agent Cooperation School of Mathematics China University of Mining and Technology The CEDRIC-Lab Conservatoire National des Arts et Métiers (CNAM)

This paper investigates an interval analysis method for neural networks and applies it to fault detection for systems with unknown but bounded measurement noise. First, a novel interval analysis method is presented, which can compute the bounds of the output of a feedforward neural network subject to a bounded input. By applying the proposed interval analysis method to a network trained with fault-free system data, adaptive thresholds for fault detection are computed. Finally, one can acquire fault detection results via a fault detection strategy. The proposed method can achieve tight bounds of the network output and employ simple operations, which leads to accurate fault detection results and a low computational burden.A numerical simulation and an experiment on an AC servo motor are given to illustrate the effectiveness and superiority of the proposed method.

关键词： interval analysis feedforward neural network fault detection adaptive thresholds

来源：评论

学校读者我要写书评

暂无评论

Linear-quadratic and norm-bounded combined differential game guidance scheme with obstacle avoidance for attacking defended aircraft in three-player engagement

引用

Defence Technology（防务技术） 2024年第12期42卷 136-155页

作者： Xintao Wang Ming Yang Songyan Wang Mingzhe Hou Tao Chao Control and Simulation Center Harbin Institute of TechnologyHarbin 150001China National Key Laboratory of Complex System Control and Intelligent Agent Cooperation Harbin 150001China Center for Control Theory and Guidance Technology Harbin Institute of TechnologyHarbin 150001China

A differential game guidance scheme with obstacle avoidance,based on the formulation of a combined linear quadratic and norm-bounded differential game,is designed for a three-player engagement scenario,which includes a pursuer,an interceptor,and an *** confrontation between the players is divided into four phases(P1-P4)by introducing the switching time,and proposing different guidance strategies according to the phase where the static obstacle is located:the linear quadratic game method is employed to devise the guidance scheme for the energy optimization when the obstacle is located in the P1 and P3 stages;the norm-bounded differential game guidance strategy is presented to satisfy the acceleration constraint under the circumstance that the obstacle is located in the P2 and P4 ***,the radii of the static obstacle and the interceptor are taken as the design parameters to derive the combined guidance strategy through the dead-zone function,which guarantees that the pursuer avoids the static obstacle,and the interceptor,and attacks the ***,the nonlinear numerical simulations verify the performance of the game guidance strategy.

关键词： Active defense aircraft Differential game theory Three-player confrontation Energy optimization Acceleration constraint Obstacle avoidance

来源：评论

学校读者我要写书评

暂无评论

Review of Formation control and Cooperative Guidance Technology of Multiple Unmanned Aerial Vehicles

Review of Formation Control and Cooperative Guidance Technol...

引用

International Conference on Guidance, Navigation and control, ICGNC 2022

作者： Liu, Xinyu Hao, Mingrui Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (纸本)9789811966125

Aiming at the research status of formation control and cooperative guidance technology of multi unmanned aircrafts, this paper introduces various methods of formation control technology and cooperative guidance technology. It also expounds the characteristics of formation control methods such as graph theory, leader-follower formation, behavior strategy, virtual structure, artificial potential field mode and consistency mode, as well as independent, centralized and distributed cooperative guidance methods. Then the application status and technical development of intelligent methods in multi vehicles formation control and cooperative guidance are introduced. At the same time, this paper compares the advantages and problems of various methods, and prospects the future development direction of this field. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Collaborative Estimation of Multi-source Heterogeneous Moving Sensors for UAV Cluster 5th

Collaborative Estimation of Multi-source Heterogeneous Movin...

引用

5th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2021

作者： Yang, Xiangyu Song, Chuang Chen, Linxiu Hao, Mingrui Zhang, Hang Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (纸本)9789811939976

In the cooperative combat mission of UAV cluster, the collaborative estimation of targets by airborne multi-source heterogeneous sensors can make the utmost of the multivariate detection performance of moving sensors placed in multiple spatial positions in complex confrontation environments, in order to deal with the problem of independent estimation failure of sensors carried by single aircraft under the multiple compound interference of non-cooperative targets. In this paper, the typical target motion model, estimation model and interference model are established, then a collaborative estimation method of airborne target detection sensors with different detection accuracy and different interference countermeasure capability is designed for each aircraft in the UAV cluster, based on spatial allocation strategy, nonlinear filtering, interference detection, consistency correlation and information fusion. It is verified by Monte Carlo simulation study that this method can guarantee the obtainment of continuous and accurate guidance information for each aircraft in the cluster, so as to improve the strike accuracy of each UAV and complete the strike mission. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Cooperative Search Strategy of Multi-UAVs Based on Hexagonal Grid 7th

Cooperative Search Strategy of Multi-UAVs Based on Hexagonal...

引用

7th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2023

作者： Zhao, Hongyin Hao, Mingrui Zhang, Hang Dong, Xiaofei Liu, Yuting Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (纸本)9789819733316

Aiming at the cooperative search problem in a wide-area unknown region, a cooperative search strategy of multi-UAVs based on hexagonal grid is proposed for the fairness of decision-making, This strategy is trained by reinforcement learning method, and adopts centralized training and distributed execution, and deals with the dynamic environment problem by fusing pheromone models. Simulation shows that the cooperative search algorithm has the functions of unknown region cooperative search and online threat avoidance replanning. Compared with the square grid training method, the reinforcement learning search algorithm based on the hexagonal grid after training expands the feasible directions in each decision planning cycle, which is more suitable for low-slow-small UAVs, and the performance is more stable after convergence. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Multiple UAVs Time-Cooperative Guidance Law Under Directed Communication Topologies

Multiple UAVs Time-Cooperative Guidance Law Under Directed C...

引用

International Conference on Guidance, Navigation and control, ICGNC 2020

作者： Lyu, Teng Xu, Cheng Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (纸本)9789811581540

Collaborative guidance of multiple UAVs with directional communication topologies for directional targets is being researched. First, a new multi-UAV time-cooperative guidance model is established based on the relative motion equation of the UAV target. Next, based on the cooperative control theory of multi-agent systems, a rigorously proven distributed time cooperative guidance method is designed. This ensures that the impact times of multiple UAVs in a directional topology reach asymptotic consistency. After reaching the impact time consensus, all unmanned aerial vehicles use traditional PN guidance techniques to ensure that the UAV accurately hits the target without impacting the impact time consensus. Finally, the simulation results prove the effectiveness of the designed collaborative guidance method. © 2022, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Static Unstable STT Overload control on High-order Fully Actuated system Theory 6

Static Unstable STT Overload Control on High-order Fully Act...

引用

6th International Symposium on Autonomous systems, ISAS 2023

作者： Liu, Xinyu Hao, Mingrui Zhen, Yan Fan, Yu Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (纸本)9798350316155

This article proposes a joint overload controller for pitch and yaw channels on the high-order fully actuated system theory for a nonlinear lateral and longitudinal static unstable STT aircraft model. Firstly, a second-order fully actuated system model for aircraft overload was derived, and an optimal control method for lateral and longitudinal overload was designed. Through mathematical simulation verification of this controller and traditional PID controller, it is shown that the PID control method has significant shortcomings in nonlinear aircraft with coupling. However, high-order fully actuated system theory control method can better adapt to nonlinear and static instability problems, achieve stable tracking of aircraft overload commands, and have better rapidity. © 2023 IEEE.

关键词： system theory

来源：评论

学校读者我要写书评

暂无评论

The Research on Simulation Technology for multi-aircraft cooperative guidance

The Research on Simulation Technology for multi-aircraft coo...

引用

2019 IEEE International Conference on Unmanned systems, ICUS 2019

作者： Jing, Li Chao, Shen Jiahui, Tong Beijing Electro-Mechanical Engineering Institute Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (纸本)9781728137926

In this paper, the composition and operation mechanism of a multi-aircraft cooperative simulation system is analyzed, with its formal architecture identified as a discrete event system differential equation system specifications (DEVDESS). Then, the operation and control problem of the cooperative simulation system is converted into the simulation control problem of a specific DEVDESS system. A coordinator-based test method for cooperative simulation is proposed and validated by tests of real-time mathematical simulation. © 2019 IEEE.

关键词： Hardware-in-the-loop simulation

来源：评论

学校读者我要写书评

暂无评论

Lightweight hybrid visual-inertial odometry with closed-form zero velocity update

引用

Chinese Journal of Aeronautics 2020年第12期33卷 3344-3359页

作者： QIU Xiaochen ZHANG Hai FU Wenxing School of Automation Science and Electrical Engineering Beihang UniversityBeijing 100191China Science and Technology on Aircraft Control Laboratory Beijing 100191China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing 100074China

Visual-Inertial Odometry(VIO) fuses measurements from camera and Inertial Measurement Unit(IMU) to achieve accumulative performance that is better than using individual *** VIO is an extended Kalman filter-based solution which augments features with long tracking length into the state vector of Multi-State Constraint Kalman Filter(MSCKF). In this paper, a novel hybrid VIO is proposed, which focuses on utilizing low-cost sensors while also considering both the computational efficiency and positioning precision. The proposed algorithm introduces several novel contributions. Firstly, by deducing an analytical error transition equation, onedimensional inverse depth parametrization is utilized to parametrize the augmented feature *** modification is shown to significantly improve the computational efficiency and numerical robustness, as a result achieving higher precision. Secondly, for better handling of the static scene,a novel closed-form Zero velocity UPda Te(ZUPT) method is proposed. ZUPT is modeled as a measurement update for the filter rather than forbidding propagation roughly, which has the advantage of correcting the overall state through correlation in the filter covariance matrix. Furthermore, online spatial and temporal calibration is also incorporated. Experiments are conducted on both public dataset and real data. The results demonstrate the effectiveness of the proposed solution by showing that its performance is better than the baseline and the state-of-the-art algorithms in terms of both efficiency and precision. A related software is open-sourced to benefit the community.

关键词： Inverse depth parametrization Kalman filter Online calibration Visual-inertial odometry Zero velocity update

来源：评论

学校读者我要写书评

暂无评论

Dual and reduced-order observer based attack-free protocols for consensus of multi-agent systems with Markovian switching topologies

引用

systems & control Letters 2025年 202卷

作者： Tian-Yu Gao Zhao-Yan Li Bin Zhou Center for Control Theory and Guidance Technology Harbin Institute of Technology Harbin 150001 China School of Mathematics Harbin Institute of Technology Harbin 150001 China Zhengzhou Research Institute of HIT Zhengzhou 450000 China National Key Laboratory of Complex System Control and Intelligent Agent Cooperation Harbin 150001 China

This paper studies the output feedback consensus problem of linear multi-agent systems with Markovian switching topologies. To avoid reconstructing the Markovian switching topologies during designing the observers or adding the state of the observers to the information exchange loop, dual and reduced-order observer based attack-free consensus protocols are proposed, which only utilizes the relative outputs of neighboring agents. It is shown that, under certain mild conditions, a necessary and sufficient condition for the solvability of the mean square consensus problem is that the union of switching topologies has a spanning tree. Finally, numerical examples are given to illustrate the effectiveness of the proposed approaches.

关键词：

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：