检索结果-内蒙古大学图书馆

19th Chinese Intelligent Systems Conference, CISC 2023

作者： Chen, Tianqi Sun, Liang Li, Peng Jiang, Jingjing Key Laboratory of Intelligent Bionic Unmanned Systems Ministry of Education School of Intelligence Science and Technology Institute of Artificial Intelligence University of Science and Technology Beijing Beijing100083 China Beijing Key Laboratory of Urban Underground Space Engineering University of Science and Technology Beijing Beijing100083 China Department of Aeronautical and Automotive Engineering Loughborough University LeicestershireLE11 3TU United Kingdom

ISBN: (纸本)9789819968855

The stereovision-based visual servo control is designed to enable robotic manipulator to track the target object. A method of target position estimation with existence of measurement noise is achieved through Kalman filter. The adaptive proportional-derivative control is designed to track the desired position and velocity of each joint angle in the joint space. Stability analysis based on the Lyapunov theory is used to prove the rationality and strictness of the designed controllers. Numerical simulations on 2 degree-of-freedom manipulator demonstrate the effectiveness of estimation and control. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Unified numerical predictor-corrector guidance based on characteristic model

引用

中国空间科学技术（中英文） 2024年第4期44卷 40-49页

作者： MENG Bin ZHANG Hangning ZHAO Yunbo Beijing Institute of Control Engineering Beijing 100094China National Key Laboratory of Space Intelligent Control Beijing 100094China University of Science and Technology of China Hefei 230026China

Aerocapture is one of the key technologies for low-cost transportation,with high demands of autonomy,accuracy,and robustness of guidance and control,due to its high reliability requirements for only one chance of trying.A unified numerical predictor-corrector guidance method based on characteristic models for aerocapture is *** numerical predictor-corrector guidance method is used to achieve autonomy and high accuracy,and the characteristic model control method is introduced to achieve *** the same time,by transforming path constraints,characteristic model equations including apogee deviation and altitude differentiation are *** on the characteristic model equations,a unified guidance law which can satisfy path constraints and guidance objectives simultaneously is *** guidance problems,guidance deviation is not directly obtained from the output of the dynamics at present,but is calculated through integral and algebraic ***,the method of directly discretizing differential equations cannot be used to establish characteristic models,which brings great difficulty to characteristic modeling.A method for characteristic modeling of guidance problems is proposed,and convergence analysis of the proposed guidance law is also ***,a joint numerical simulation of guidance and control considering navigation deviation and various uncertainties is conducted to verify the effectiveness of the proposed *** proposed unified method can be extended to general aerodynamic entry guidance designs,providing theoretical and methodological support for them.

关键词： aerocapture path constraint characteristic model unified numerical predictor-corrector guidance convergence

来源：评论

学校读者我要写书评

暂无评论

Adaptive Drag-Free control of Gravity Field Satellites via a Modified Characteristic Model-Based Approach

Adaptive Drag-Free Control of Gravity Field Satellites via a...

引用

International Conference on Guidance, Navigation and control, ICGNC 2020

作者： Wang, Lijiao Gou, Xingyu Liu, Qirui Meng, Bin Science and Technology on Space Intelligent Control Laboratory Beijing Institute of Control Engineering Beijing100190 China Beijing Institute of Control Engineering Beijing100190 China

ISBN: (纸本)9789811581540

In this work, we present a new control scenario for the adaptive drag-free control of gravity field satellites in displacement mode, where the control objective is to lock the position between the test mass and the outer satellite. The un-stability caused by the static electricity, the uncertainty of the sensors and actuators, and the disturbance of the attitude movement propose great challenge for the controller design of the drag-free loop. Characteristic model is introduced to simplify the modeling of the complicated nonlinear dynamics. Then, a novel adaptive control strategy is developed, which is constituted by an extended state-and-parameter estimator and a modified all-coefficient controller. The scheme can not only stabilize the unstable plant, but cope with the uncertainties as well as measurement noises, providing a simple and effective solution for practical applications. Finally, simulations are performed on a gravity field satellite, illustrating that our approach yields good control performance. © 2022, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： controllers

来源：评论

学校读者我要写书评

暂无评论

Distributed Event-Triggered Consensus control for Networked Euler-Lagrange Systems Subject to External Disturbances 37

Distributed Event-Triggered Consensus Control for Networked ...

引用

37th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2022

作者： Wei, Minfeng Xu, Min Zang, Yunge Zhang, Fengdi Beijing Institute of Technology Beijing China Beijing Aerospace Automatic Control Institute Beijing China National Key Laboratory of Science and Technology on Aerospace Intelligence Control Beijing China

ISBN: (纸本)9781665465366

Focused on the networked Euler-Lagrange (EL) systems suffering from external disturbances, this study investigates the consensus problem under event-triggered strategies. In this study, a delicate-designed auxiliary variable is introduced, which allows to reduce the system order so as to simplify the controller design. As thus, based on the reduced-order systems, a novel event-triggered consensus (ETC) control protocol is investigated such that the consensus among agents can be achieved in a distributed way with communication resource saved. To further improve the triggering performance, a mixed threshold with state-dependent term and state-independent term is designed based on only local information. Under the proposed ETC control protocol, consensus among EL systems can be achieved in a distributed way with communication overheads reduced. Furthermore, the feasibility of the proposed ETC protocol is ensured by guaranteing the Zeno-freeness. Finally, numerical simulations are shown to illustrate the effectiveness. © 2022 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Two-Archive-Based Competitive Swarm Optimizer for Constrained Multiobjective Optimization 5

Two-Archive-Based Competitive Swarm Optimizer for Constraine...

引用

5th International Conference on Data-Driven Optimization of Complex Systems, DOCS 2023

作者： Li, Lianghao He, Cheng Lin, Jianqing Pan, Linqiang School of Artificial Intelligence and Automation Huazhong University of Science and Technology Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China Wuhan China School of Electrical and Electronic Engineering Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9798350393521

Constrained multiobjective optimization problems (CMOPs) are prevalent in various real-world applications, presenting a formidable challenge to existing evolutionary algorithms when faced with intricate constraints. When solving CMOPs, a crucial concern is achieving a balance between convergence, diversity, and feasibility. To address these challenges, this paper proposes a two-archive-based constrained multiobjective competitive swarm optimizer. The algorithm preserves two collaborative and complementary archives to improve population convergence and feasibility. By implementing a competitive particle swarm mechanism, offspring solutions are generated by drawing upon solutions from both archives, thus capitalizing on their synergistic effect and exceptional information. An adaptive parameter is also used to adjust the bias in choosing the winner in the paired competition during the evolution. The experimental results demonstrate the effectiveness of the proposed algorithm in handling constrained multiobjective optimization problems. © 2023 IEEE.

关键词： Constraint handling

来源：评论

学校读者我要写书评

暂无评论

A Few-shot Fault Diagnosis Method under Target Domain Data Based on Improved Metric space SVM 41

A Few-shot Fault Diagnosis Method under Target Domain Data B...

引用

第41届中国控制会议

作者： Xinyi Xu Qilin Qu Yanwei Wang Ying Zheng Housheng Su China-Belt and Road Joint Laboratory On Measurement and Control Technology School of Artificial Intelligence and AutomationHuazhong University of Science and Technology School of Mechanical & Electrical Engineering Wuhan Institute of Technology

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

The intelligent bearing diagnosis with big data has been widely *** high performance diagnosis models are constantly being proposed,these models are difficult to apply in some practical application with limited collectable *** this paper,an Improved Metric space Support Vector Machine with a two-stage learning strategy is proposed to overcome the challenge of few-shot scenarios under target domain ***,an improved triplet loss is designed in the metric network to select features by utilizing the similarity of ***,kernel method is used to model in few-shot scenarios by maximizing the inter-class *** on CWRU dataset verify the superiority and robustness of IMSSVM comparing with popular baseline ***,the effectiveness of IMSSVM is verified with visualizing the feature embeddings by t-distributed stochastic neighbor embedding.

关键词： fault diagnosis few-shot learning metric learning kernel method

来源：评论

学校读者我要写书评

暂无评论

Variable Selection Method Based on Least Absolute Shrinkage and Selection Operator(LASSO) and kNN for Faults Isolation 41

Variable Selection Method Based on Least Absolute Shrinkage ...

引用

第41届中国控制会议

作者： Yuanle Liu Lang Liu Yanwei Wang Ying Zheng Housheng Su China-Belt and Road Joint Laboratory On Measurement and Control Technology School of Artificial Intelligence and AutomationHuazhong University of Science and Technology School of Mechanical & Eletrical Engineering Wuhan Institute of Technology

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In the multivariable fault isolation of industrial process,the effectiveness of fault isolation is affected by the "smearing" effect because of the correlation between *** order to isolate all the key fault variables correctly,the fault isolation problem is regarded as a variable selection ***,LASSO is applied to the sparse contribution vector based on k-nearest ***,the LASSO-KNN model based on sliding window is established,and the sparse representation of contribution vector is obtained by least angle regression(LAR) algorithm and cumulative weight contribution percent criterion,thus the main fault variables are *** an extended EWMA algorithm combined with sliding window mechanism is introduced to achieve on-line fault ***,the effectiveness of the proposed algorithm is verified by a simulation example of TE process.

关键词： Fault diagnosis Fault isolation Variable selection k-Nearest neighbour

来源：评论

学校读者我要写书评

暂无评论

Online learning control law design based on policy gradient reinforcement learning

Online learning control law design based on policy gradient ...

引用

Chinese control and Decision Conference, CCDC

作者： Zhaolei Wang Kunfeng Lu Xiaomin Li Chunmei Yu Chenhui Jia Xu Huang National Key Laboratory of Science and Technology on Aerospace Intelligence Control Beijing Aerospace Automatic Control Institute Beijing China

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

Morphing aircraft exhibit agile maneuverability within an extensive flight envelope, which imposes heightened requirements on the online adaptation capabilities of control laws and necessitates enhanced dynamic flight control performance. The coefficient freezing method frequently used in engineering applications entails individualized design procedures for each distinct operating point, a process that is both intricate and heavily reliant on human expertise. Moreover, once deployed, conventional flight control laws generally exhibit static performance with limited potential for online optimization and adjustment. This work presents an offline strategy gradient deep reinforcement learning approach to devise a self-learning architecture for the parameters of PI state feedback control laws. This architecture is trained automatically by traversing across multiple operational points of the morphing aircraft under control, thereby yielding a set of control laws adaptable to various operational conditions. Concurrently, the action network from this framework is extracted and implemented as an online learning module, enabling real-time adjustments to control law parameters during flight based on the observed control performance, thus augmenting the aircraft’s inherent online adaptive capabilities. The validity and effectiveness of the proposed methodology are substantiated through a case study focusing on tracking control in the pitch channel of a representative morphing aircraft.

关键词： Training State feedback Adaptive systems Neural networks Focusing control systems Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Diving into Underwater: Segment Anything Model Guided Underwater Salient Instance Segmentation and A Large-scale Dataset 41

Diving into Underwater: Segment Anything Model Guided Underw...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Lian, Shijie Zhang, Ziyi Li, Hua Li, Wenjie Yang, Laurence Tianruo Kwong, Sam Cong, Runmin Hainan University China China Ministry of Education China Huazhong University of Science and Technology China St. Francis Xavier University Canada LIngnan University School of Data Science Hong Kong Shandong University School of Control Science and Engineering China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China

With the breakthrough of large models, Segment Anything Model (SAM) and its extensions have been attempted to apply in diverse tasks of computer vision. Underwater salient instance segmentation is a foundational and vital step for various underwater vision tasks, which often suffer from low segmentation accuracy due to the complex underwater circumstances and the adaptive ability of models. Moreover, the lack of large-scale datasets with pixel-level salient instance annotations has impeded the development of machine learning techniques in this field. To address these issues, we construct the first large-scale underwater salient instance segmentation dataset (USIS10K), which contains 10,632 underwater images with pixel-level annotations in 7 categories from various underwater scenes. Then, we propose an Underwater Salient Instance Segmentation architecture based on Segment Anything Model (USIS-SAM) specifically for the underwater domain. We devise an Underwater Adaptive Visual Transformer (UA-ViT) encoder to incorporate underwater domain visual prompts into the segmentation network. We further design an out-of-the-box underwater Salient Feature Prompter Generator (SFPG) to automatically generate salient prompters instead of explicitly providing foreground points or boxes as prompts in SAM. Comprehensive experimental results show that our USIS-SAM method can achieve superior performance on USIS10K datasets compared to the state-of-the-art methods. Datasets and codes are released on Github. Copyright 2024 by the author(s)

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

An estimation algorithm of population feature distribution for the imaging constellation task planning problem

An estimation algorithm of population feature distribution f...

引用

第42届中国控制会议

作者： Yinan Ding Yongjun Lei Shuyi Wang Beijing Institute of Control Engineering Science and Technology on Space Intelligent Control Laboratory

An estimation algorithm of population feature distribution(EPFD) is proposed to improve the completion and imaging quality of imaging constellation observation tasks. Firstly, the observation task constraints and on-board resource constraints of agile imaging satellites are analyzed, the objective function of evaluating task completion and imaging quality is constructed, and the task planning model of agile imaging constellation is established. Then, the coding and decoding strategy with imaging time as the optimization object is designed. The concepts of global heuristic information and local heuristic information are given. A method for establishing the probability distribution model of imaging time based on heuristic information and a population evolution method are proposed. The directional search of imaging time is realized, and the completion of observation tasks and imaging quality are improved. Finally, the algorithm and particle swarm optimization algorithm are compared and analyzed through engineering examples. The results show that the algorithm has a fast convergence speed and a good optimization effect.

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：