检索结果-内蒙古大学图书馆

IEEE/CAA Journal of Automatica Sinica 2017年第1期4卷 1-5页

作者： Fei-Yue Wang Jie Zhang Qinglai Wei Xinhu Zheng Li Li IEEE State Key Laboratory of Management and Control for Complex Systems(SKL-MCCS) Institute of AutomationChinese Academy of Sciences(CASIA) School of Computer and Control Engineering University of Chinese Academy of Sciences Research Center for Military Computational Experiments and Parallel Systems Technology National University of Defense Technology State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences(SKL-MCCSCASIA) Qingdao Academy of Intelligent Industries Department of Computer Science and Engineering University of Minnesota Department of Automation Tsinghua University

Deep reinforcement learning is a focus research area in artificial intelligence. The principle of optimality in dynamic programming is a key to the success of reinforcement learning methods. The principle of adaptive dynamic programming ADP is first presented instead of direct dynamic programming DP , and the inherent relationship between ADP and deep reinforcement learning is developed. Next, analytics intelligence, as the necessary requirement, for the real reinforcement learning, is discussed. Finally, the principle of the parallel dynamic programming, which integrates dynamic programming and analytics intelligence, is presented as the future computational intelligence. © 2014 Chinese Association of Automation.

关键词： Artificial intelligence Neural networks Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Mining Better Samples and Semantic Consistency for Contrast Learning in Forest Semantic Segmentation 41

Mining Better Samples and Semantic Consistency for Contrast ...

引用

第41届中国控制会议

作者： Chongjin Chen Yichao Cao Qingfei Tang Xiaobo Lu School of Software Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing Enbo Technology Co. Ltd.

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Image segmentation has impressive progress in the past several *** good segmentation usually follows pixelwise well-annotated labels which is ***,the robustness would not be guaranteed due to lack-ofdiversity *** work usually focuses on pixels individually and pay less attention to the neighbor *** local context would be scarce and the global context is not utilized following these *** proposal a method,named Forest Semantic Segmentation Network(FSSNet) to address these *** organizes original version and augmented version of images,as two inputs into student branch and teacher branch,and force the two outputs being consistent to strengthen the robustness of our ***,we not only consider pixel itself and also the neighbor pixels because the context of neighbor pixels helps understanding the *** utilizes contrastive loss with memory bank to involve global context in training which will make pixels closer to others in same category and far away from pixels of different categories.A bank filter is suggested to improve the quality of features in the memory *** also proposal a new sample strategy to improve the effect of contrastive loss and reduce the *** method can improve accuracy and strengthen the robustness with affordable extra computation during training process,and no additional computation during inference toward *** to benchmark,the proposed approach can improve the mIoU by 3.1% on our challenging dataset.

关键词： Semantic segmentation Contrastive learning Deep learning

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Robust control Design for Static Synchronous Compensator 29

Nonlinear Robust Control Design for Static Synchronous Compe...

引用

第29届中国控制与决策会议

作者： Xingyu Lv Bangjun Lei Shumin Fei Office of Educational Administration Guizhou Institute of Technology School of Electrical and Information Engineering Guizhou Institute of Technology Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of EducationSchool of AutomationSoutheast University

ISBN: (纸本)9781509046584

This article proposes a nonhnear robust control design for Static Synchronous Compensator(STATCOM) to improve stability and oscillation damping of power *** the parameter deviations,external disturbances and unmodeled dynamics,the nonhnear dynamic model of STATCOM can be translated into a Hamiltonian structure by means of coordinate *** on the Hamiltonian structure of STATCOM,a nonhnear robust(NR) control is designed for *** simulation results on the two-area four-machine power system demonstrate the robustness and effectiveness of the proposed NR control in comparison with the feedback linearization(FL) *** comparative study results indicate that the NR control has better performance than the FL control.

关键词： STATCOM Nonlinear Robust control Hamiltonian Function Method Asymptotic Stability

来源：评论

学校读者我要写书评

暂无评论

A self-learning algorithm based on support vector machine for scheduling a job-shop-like knowledgeable manufacturing cell

A self-learning algorithm based on support vector machine fo...

引用

2011 International Conference on Mechanical engineering, Materials and Energy, ICMEME 2011

作者： Li, Wen-Chao Yan, Hong-Sen Key Laboratory of Measurement and Control of Complex Systems Engineering Southeast University Ministry of Education Nanjing 210096 China Department of Transportation Jiangsu University Zhenjiang 212013 China

ISBN: (纸本)9783037853405

The job-shop-like knowledgeable manufacturing cell scheduling is a NP-complete problem and there has not been a completely valid algorithm for it until now. An algorithm with self -learning ability is proposed through the addition of precedence constraint of operations on the basis of directed graph. A method based on support vector machine is constructed to choose accurately interchangeable operations by small samples earning to obtain the better scheduling. The classification accuracy can be improved by the continuous addition of new instances to the sample library. The results of simulation show that the algorithm performs well for the job-shop-like knowledgeable manufacturing cell. © (2012) Trans Tech Publications, Switzerland.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

A Hierarchical Formation-Containment control Scheme for Second-Order Multi-agent systems 7th

A Hierarchical Formation-Containment Control Scheme for Sec...

引用

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

作者： Cao, Yue Wang, Xiangyu Chen, Yangyang School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China

ISBN: (纸本)9789819733231

In this paper, a hierarchical formation-containment control scheme is proposed for second-order multi-agent systems. The proposed hierarchical scheme decouples the control task into two layers, i.e., reference signal generator and agents’ tracking controllers. First, a reference signal generator is designed in Layer 1 for leader agents and follower agents, respectively, to produce the formation reference signals and containment reference signals, whose outputs "achieve" formation-containment asymptotically. Second, tracking controllers are designed in Layer 2 for each agent to track the reference signal. The proposed hierarchical formation-containment scheme realizes formation-containment asymptotically. The simulations are performed to validate the effectiveness and practicality of the scheme. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Adaptive Augmented Kalman Filter-Based control for Electronic Throttle systems with Disturbances and Noises 42

Adaptive Augmented Kalman Filter-Based Control for Electroni...

引用

42nd Chinese control Conference, CCC 2023

作者： Li, Wen Su, Jinya Li, Shihua School of Automation Southeast University Nanjing210096 China Ministry of Education Key Laboratory of Measurement and Control of Complex Systems of Engineering Southeast University Nanjing210096 China

ISBN: (纸本)9789887581543

In this study, we investigate the control problem of electronic throttle systems in the presence of practical challenges such as disturbances and measurement noises. To address these challenges, we propose an adaptive augmented Kalman filter (AAKF) based control approach that combines the strengths of extended state observer in disturbance estimation and adaptive Kalman fil-ter in adaptive noise filtering. The outputs of AAKF are integrated into the Backstepping control design, resulting in a composite control that concurrently achieves fast disturbance rejection and noise suppression. We conduct a comparative simulation study against conventional methods without adaptive filtering to validate the effectiveness of the proposed AAKF-based control strat-egy, which exhibits superior position control accuracy and disturbance attenuation performance. We envision that our proposed control strategy will contribute to improving vehicle power, fuel economy, and emission performance. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Adaptive filtering

来源：评论

学校读者我要写书评

暂无评论

Flight control Using only Synthetic Jet Actuators in High-Angle-of-Attack 35

Flight Control Using only Synthetic Jet Actuators in High-An...

引用

第35届中国控制会议

作者： LI Chunzhi Yang Jianying State Key Laboratory for Turbulence and Complex Systems Department of Mechanics and Engineering Science College of Engineering Peking University National Key Laboratory of Science and Technology on Aerospace Intelligence Control

ISBN: (纸本)9781509009107

This paper proposes a novel airfoil active flow control method using only synthetic jet to achieve triple-channel flight attitude control at high angle of attack. It's a feasible and effective control method to solve the difficult problem of flight control at high attack angle when stall occurs. As a first step, we build a model of the aircraft, and derive the relationship between the synthetic-jet peak velocity and moments. Under these conditions, we design a controller to the system. A nonlinear integrated flight control and flow control system was developed and tested in simulations. Simulation results showed that the proposed control method, can effectively control the aircraft at high angle of attack.

关键词： synthetic jet flight control high angle of attack

来源：评论

学校读者我要写书评

暂无评论

Smoke vehicle detection based on multi-feature fusion and hidden Markov model

Smoke vehicle detection based on multi-feature fusion and hi...

引用

作者： Tao, Huanjie Lu, Xiaobo School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China

Existing smoke vehicle detection methods and vision-based smoke detection methods are vulnerable to false alarms. This paper presents an automatic smoke vehicle detection method based on multi-feature fusion and hidden Markov model (HMM). In this method, we first detect moving objects using an improved visual background extractor (ViBe) algorithm and obtain smoke-colored blocks using color histogram features in the HSI (hue, saturation, and intensity) color space. The adaptive scale local binary pattern (AS-LBP) and the discriminative edge orientation histogram (disEOH) are proposed and combined to characterize the smoke-colored blocks. More specifically, the proposed AS-LBP, a texture feature descriptor, is based on the quadratic fitting of our labelled data to obtain the best scale. The proposed disEOH, a gradient-based feature descriptor, is robust to noise by extracting discriminative edge information using Gaussian filters and principal component analysis (PCA). The discrete cosine transform (DCT) is employed to extract frequency domain information from the region fused by smoke blocks. To utilize the dynamic features, the HMMs are employed to analyze and classify the smoke-colored block sequences and region sequences in continuous frames. The experimental results show that the proposed method achieves better performances than existing smoke detection methods, especially achieves lower false alarms. © 2019, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Smoke

来源：评论

学校读者我要写书评

暂无评论

Integrated Missile Guidance and control Design with Smooth Adaptive Sliding Mode control 34

Integrated Missile Guidance and Control Design with Smooth A...

引用

第三十四届中国控制会议

作者： Zhou Jialing Yang Jianying State Key Laboratory for Turbulence and Complex Systems Department of Mechanics and Engineering Science College of Engineering Peking University National Key Laboratory of Science and Technology on Aerospace Intelligence Control

ISBN: (纸本)9781467374439

This paper considers the problem of a missile intercepting a maneuvering target with demand for fast finite-time convergence and anti-chattering. Based on the widely used proportional navigation strategy, a novel integrated guidance and control(IGC) scheme is proposed, which is formulated as a second-order affine nonlinear system with uncertainties. Then the smooth adaptive nonsingular terminal sliding mode control(SANTSMC) method which is proposed in our pervious work is applied to this IGC scheme. By virtue of the SANTSMC method, the uncertainties with unknown bounds can be addressed, fast finite-time convergence can be achieved, and the chattering problem can be well solved.

关键词： Missile Interception,Integrated Guidance and control,Anti-chattering,Adaptive Sliding Mode control

来源：评论

学校读者我要写书评

暂无评论

Time-varying Terminal Sliding Mode Based on Salvo Attack Cooperative Guidance Law for Unknown Uncertainty Upper Bounds 35

Time-varying Terminal Sliding Mode Based on Salvo Attack Coo...

引用

第35届中国控制会议

作者： WEI Xiaoqian YANG Jianying State Key Laboratory for Turbulence and Complex Systems Department of Mechanics and Engineering ScienceCollege of EngineeringPeking University National Key Laboratory of Science and Technology on Aerospace Intelligence Control

ISBN: (纸本)9781509009107

In this paper,a new time-varying terminal sliding mode with unknown uncertainty bounds is designed to make multiple missiles-attack against the maneuvering target *** new method in this paper can guarantee accurate time-to-go by distributed ***,a new cooperative guidance law is designed for the nonlinear system based on the known uncertainty ***,it is extended to unknown uncertainty bound using the disturbance observer and the composite cooperative guidance *** desired salvo attack time is achieved by selecting the parameter variables of sliding model and the adjacency matrix in the *** simulations with the comparisons demonstrate the effectiveness and the superiority of the proposed method.

关键词： Terminal Sliding Mode Salvo Attack Unknown Uncertainty Upper Bounds

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：