检索结果-内蒙古大学图书馆

A Noise-Excitation Generative Adversarial Network for Actuator Fault Diagnosis of Multi-legged Robot

无人系统（英文） 2023年第2期11卷 159-173页

作者： Liling Ma Jian Guo Jiehao Li Junzheng Wang State Key Laboratory of Complex System Intelligent Control and Decision School of Automation Beijing Institute of TechnologyBeijing 100081P.R.China

This research provides a novel approach for detecting multi-legged robot actuator *** most significant concept is to design the Fault Diagnosis Generative Adversarial Network(FD-GAN)to fully adapt to the fault diagnosis problem with insufficient *** found that it is difficult for methods based on classification and prediction to learn failure patterns without enough data.A straightforward solution is to use massive amounts of normal data to drive the diagnostic *** introduce frequency-domain information and fuse multi-sensor data to increase the features and expand the difference between normal data and fault data.A GAN-based framework is designed to calculate the probability that the enhanced data belongs to the normal *** uses a generator network as a feature extractor,and uses a discriminator network as a fault probability evaluator,which creates a new use of GAN in the field of fault *** the many learning strategies of GAN,we find that a key point that can distinguish the two types of data is to use the hidden layer noise with appropriate discrimination as the *** also design a fault location method based on binary search,which greatly improves the search efficiency and engineering value of the entire *** have conducted a lot of experiments to prove the diagnostic effectiveness of our architecture in various road conditions and working *** compared FD-GAN with popular diagnostic *** results show that our method has the highest accuracy and recall rate.

关键词： Actuator fault diagnosis multi-legged robot generative adversarial network attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Relative Navigation of Unmanned Aerial Vehicles Based on Data Link Ranging and Partial Guidance Information 1

引用

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

作者： Wang, Ziwen Song, Chuang Hao, Mingrui Liang, Xinkai Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (数字)9789819733323

ISBN: (纸本)9789819733316

In GNSS-denied environments, precise relative navigation between unmanned aerial vehicles (UAVs) is a key technology for achieving cooperative tasks. The relative navigation method based on data link ranging information combines altitude, airspeed measurements, and attitude information to ensure the observability of UAVs’ relative states. However, due to the significant constraints imposed by observability conditions, a novel approach is proposed that utilizes partial guidance information from the UAV swarm towards the target as additional measurements. This approach enhances the observability capability of relative navigation and alleviates the constraints imposed by the observability conditions. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Observability

来源：评论

学校读者我要写书评

暂无评论

Combat Intention Recognition of Aerial Battlefield Targets Based on LSTM 3rd

Combat Intention Recognition of Aerial Battlefield Targets B...

引用

3rd International Conference on Autonomous Unmanned systems, ICAUS 2023

作者： Xu, Hongfeng Zhao, Jiajia Zhang, Hang Jiang, Jixiang Chen, Linxiu Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (纸本)9789819710867

In the course of military operations, the battlefield situation changes rapidly, and the combat time is fleeting. How to quickly and accurately identify the enemy’s combat intention is one of the important preconditions to ensure the commander’s correct command decision and obtain the initiative in the battlefield. In this paper, aiming at the problems of low accuracy and insufficient algorithm robustness of traditional target combat intention recognition methods in air battlefield, a combat intention recognition method based on LSTM is proposed according to the characteristics of sequence and multi-dimension of target characteristic data. Based on the historical and current state characteristics, electromagnetic characteristics and action characteristics of the target obtained by the sensor, the method uses the LSTM network to build the target combat intention recognition model, and learns the changes of the target characteristics through the network model to realize the target combat intention recognition. Simulation results show that the proposed method can effectively improve the accuracy of target combat intention recognition. © Beijing HIWING Scientific and Technological Information Institute 2024.

关键词： Military operations

来源：评论

学校读者我要写书评

暂无评论

Low-Light Image Enhancement Method for Consistency Judgment of Multi-view Multi-target for UAV Swarm 7th

Low-Light Image Enhancement Method for Consistency Judgment ...

引用

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

作者： Li, WeiXue Song, Chuang Hao, MingRui Zhang, Hang Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (纸本)9789819733392

To address the challenges posed by low-light images in multi-drone detection tasks, which lead to significant differences in target image features across different perspectives and poor accuracy in target association under multiple viewpoints, this paper proposes an enhanced network architecture based on MIRNet for low-light image enhancement. The goal is to improve the stability of target features in multi-view scenarios. By incorporating Sobel convolution to capture target edges and texture features, and by designing a residual contextual block combined with an attention mechanism and a pixel loss function that emphasizes the central region, the model not only acquires richer features but also focuses more on the central region's target characteristics. Experimental results demonstrate that the proposed approach effectively enhances image brightness, contrast, and target texture, exhibiting substantial advantages in both objective and subjective evaluation metrics. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Target Tracking Method Based on LSTM-EKF 1

引用

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

作者： Xu, Hongfeng Zhao, Jiajia Zhang, Hang Jiang, Jixiang Chen, Linxiu Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (数字)9789819733323

ISBN: (纸本)9789819733316

With the development of science and technology, target tracking technology has been widely used in many fields. Through target tracking technology, the accurate estimation of target state can be obtained, and the perception ability can be effectively improved. However, due to the increasing maneuvering ability of the target, the traditional target tracking algorithm is more and more difficult to meet the requirements of maneuvering target tracking. This article in view of the traditional filtering algorithm based on bayesian theory problems of nonlinear error model, in combination with the advantages of EKF and deep learning, introducing the idea of hybrid data model, puts forward the algorithm of target tracking based on LSTM - EKF, and design a mathematical simulation experiment on the performance of the algorithm is verified. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Cooperative Formation Control of Fixed-Wing UAV Based on L1 Guidance Law Considering Collision Avoidance 7th

Cooperative Formation Control of Fixed-Wing UAV Based on L1 ...

引用

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

作者： Yue, keyuan Hao, Mingrui Zhen, Yan Liu, Xinyu Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (纸本)9789819733392

This article proposes a formation control scheme based on L1 guidance law for fixed wing unmanned aerial vehicle clusters while considering collision avoidance issues between them. The fixed wing aircraft cluster adopts L1 guidance and tracking method to track their respective desired waypoints. By controlling the speed of the fixed-wing UAVs, the entire cluster forms a formation configuration on their individual desired trajectories. During the formation and transformation processes, an improved artificial potential field method is proposed based on the characteristics of fixed-wing UAVs to achieve collision avoidance between clusters. The effectiveness of the proposed approach is validated through numerical simulations based on a six-degree-of-freedom nonlinear UAV model, providing a reference for practical engineering applications. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Fixed wings

来源：评论

学校读者我要写书评

暂无评论

Cluster Collaborative Search Method Based on Dynamic Adjustment of Parameters 1

引用

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

作者： Si, JiaShuai Hao, MingRui Liu, ZhenChang Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (数字)9789819733361

ISBN: (纸本)9789819733354

In order to improve the ability of unmanned aerial vehicle(UAV) cluster collaborative search and obstacle avoidance, a multi-UAV collaborative search method based on dynamic parameter adjustment is proposed. Firstly, based on the distributed model predictive control (DMPC) model, a collaborative search problem model is designed considering the rapidity of target discovery, the rapidity of covering the task area and the obstacle avoidance between drones. Secondly, the jump grid decision method not only expands the feasible solution of the search decision, but also ensures that the UAV can track the navigation point of the decision smoothly. At last, a dynamic adjustment method of search parameters is proposed, which realizes threat avoidance in collaborative search process by adjusting search parameters online. The simulation results show that the cluster cooperative search method based on dynamic parameter adjustment can fully consider the maneuverability of UAVs and realize threat avoidance during cooperative search, and improve the robustness of the algorithm after some nodes are damaged. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Maneuverability

来源：评论

学校读者我要写书评

暂无评论

EPM-Net: A better way for optical and infrared scene matching via edge point 12

EPM-Net: A better way for optical and infrared scene matchin...

引用

SPIE 12th International Symposium on Multispectral Image Processing and Pattern Recognition, MIPPR 2023

作者： Huang, Shixiang Chi, Longyun Fu, Wenxing Tian, Jinwen National Key Laboratory of Multispectral Information Intelligent Processing Technology Huazhong University of Science and Technology Wuhan China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (数字)9781510674943

ISBN: (纸本)9781510674936

As a crucial auxiliary technique in inertial navigation, scene matching has been widely applied in aircraft navigation and guidance. To enhance the adaptability and efficiency of scene matching algorithms in complex environments, existing approaches have gradually shifted towards heterogeneous scene matching, such as optical/ infrared scene matching based on deep learning features, with a focus on point features. However, due to the complex and diverse nonlinear distortions between optical and infrared images, the matching accuracy often fails to meet the practical requirements of navigation and positioning. In view of this problem, an EPM-Net algorithm based on edge features is proposed to improve matching performance by extracting more stable and discriminative edge point descriptors. Experimental results on infrared datasets demonstrate that this method achieves an average matching accuracy improvement of more than four times compared to traditional and existing deep learning methods. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Review of Target Association Methods 1

引用

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

作者： Xu, Hongfeng Zhao, Jiajia Zhang, Hang Jiang, Jixiang Chen, Linxiu Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing100074 China

ISBN: (数字)9789819733361

ISBN: (纸本)9789819733354

With the continuous development of information technology, target association technology has been more and more widely used in military and civilian fields. How to achieve effective and reliable target data association has always been a difficult and hot spot in the field of target tracking. In this paper, the research status of target association technology is summarized, the existing target association algorithm is sorted and summarized according to the method principle, and the existing problems in the research of target association technology are analyzed, and the further research direction is prospected. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

A Formation Control Method for Leader-Follower Aircraft Based on Particle Swarm Optimization 3rd

A Formation Control Method for Leader-Follower Aircraft Base...

引用

3rd International Conference on Autonomous Unmanned systems, ICAUS 2023

作者： Zhao, Yuxia Quan, Yanli Science and Technology on Complex System Control and Intelligent Agent Cooperative Laboratory Beijing100074 China

ISBN: (纸本)9789819710829

As the defense system of military powers is becoming more and more complete, improving the aircraft’s penetration capabilities is particularly critical. Formation control is an effective way to improve the ability of penetration. Based on an uncontrollable situation, this paper proposes an angle-based formation control strategy for multiple aircraft. The leader’s trajectory inclination angle and trajectory deflection angle are used as the states of consistency, and the tilt angle is used as the control volume, to design the PI controller of the follower. The parameter optimization design is performed through the particle swarm optimization (PSO) algorithm. The simulation results show that the proposed angle-based formation control method can be well achieved and maintain the formation. © Beijing HIWING Scientific and Technological Information Institute 2024.

关键词： Aircraft

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：