检索结果-内蒙古大学图书馆

第三十八届中国控制会议

作者： Al-wesabi Ibrahim Min Ding Xiaoling Jin Xianzhong Dai Mohammad Abu Sarhan Muhammed Badeaa Shafik Hao Zhou School of Automation China University of Geoscience Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex System State Grid Energy Research Institute School of electrical engineering and automation Wuhan university

Nowadays PV systems is suffering from two main problems: high production cost and low efficiency especially under variable weather conditions. Therefore, to reduce such associated problems, PV systems are being connected with various optimization controllers such as maximum power point tracking. In this paper, an artificial neural network maximum power point method has been designed to be linked between a PV system and DC-DC buck converter, and each part of the system is fully explained. The whole system was modeled under MATLAB/Simulink environment, simulation results demonstrated the efficiency of the proposed method. The proposed method has been examined to track the maximum power point under different weather conditions which shows a rapid and accurate tracking of the maximum power point(MPP) of PV system. The whole system which consists of PV arrays, Buck converter, ANN tracker, and load has been modeled using MATLAB/Simulink environment. This Simulink model has been examined using different levels of temperature and irradiation and the output results of both P-V and I-V characteristics, output power, and the system efficiency clearly demonstrate the validation of the modeled system. This demonstration has been done by comparing between the result of experimental platform and the results of simulated model which approves that ANN is highly recommended to be used in the field of maximum power point tracking of PV system.

关键词： Artificial neural network(ANN) Photovoltaic(PV) Maximum power point tracking(MPPT) Buck converter

来源：评论

学校读者我要写书评

暂无评论

Trajectory Planning and Tracking control for Positioning of Planar Three-link Underactuated Manipulator

Trajectory Planning and Tracking Control for Positioning of ...

引用

Asian control Conference

作者： Zixin Huang Xuzhi Lai Pan Zhang Min Wu Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China School of Automation China University of Geosciences Wuhan China

ISBN: (纸本)9781728102634

This paper is concerned with the position control problem of the planar active-passive-active (APA) underactuated manipulator, whose dynamic constraint is mainly caused by the second-order nonholonomic constraint. First, the dynamic model of the system is established and the target angles of the three links are calculated by using differential evolution algorithm. Then, we present a trajectory planning and tracking control strategy to realize the control objective, which is to stabilize the end-point from any initial position to the target position. We plan two stage trajectories, the first of which is planned for the active links. When the the active links track the first stage trajectories, they can reach to their target angles. The second one is planned for the first active link based on the differential evolution algorithm. When the first active link tracks the second stage trajectory, it will back to its target angle eventually. Meantime, the passive link will be controlled to its target angle. Then, we design sliding mode variable structure controllers to make active links track the planned trajectories, which can make the all links reach to the their target angles. Finally, numerical simulation results illuminate the effectiveness of the proposed strategy.

关键词： Trajectory Manipulators Target tracking Position control Planning Heuristic algorithms Optimization

来源：评论

学校读者我要写书评

暂无评论

K-Means Clustering-based Kernel Canonical Correlation Analysis for Multimodal Emotion Recognition ⁎

引用

IFAC-PapersOnLine 2020年第2期53卷 10250-10254页

作者： Luefeng Chen Kuanlin Wang Min Wu Witold Pedrycz Kaoru Hirota School of Automation China University of Geosciences Wuhan 430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan 430074 China Department of Electrical and Computer Engineering University of Alberta Edmonton AB T6R 2G7 Canada Tokyo Institute of Technology Yokohama 226-8502 Japan

Emotion is an important part of human interaction. Emotional recognition can greatly promote human-centered interaction techniques. On this basis, multimodal feature fusion can effectively improve the emotion recognition rate. However, in the multimodal feature fusion at the feature level, most of the methods do not consider the intrinsic relationship between different modes. Only the fusion of analysis and transformation of the feature matrices of different modes does not make better use of modal differences to improve the recognition rate. This problem led us to propose feature fusion method based on K-Means clustering and kernel canonical correlation analysis (KCCA). Clustering makes the classification of features not classified by mode, but by the degree of influence on emotional labels, thus positively affecting the results of KCCA. The experimental results obtained on the Savee database show that the proposed K-Means based KCCA improves overall classification performance and produces higher recognition rate than that of the state of art methods, such as the Informed Segmentation and Labeling Approach.

关键词： Emotion Recognition K-Means Clustering Kernel Canonical Correlation Analysis Feature Fusion

来源：评论

学校读者我要写书评

暂无评论

Robust disturbance rejection for a fractional-order system based on equivalent-input-disturbance approach

引用

Science China(Information Sciences) 2018年第7期61卷 200-211页

作者： Ruijuan LIU Jinhua SHE Min WU Fenfang ZHU Zhuoyun NIE School of Applied Mathematics Xiamen University of Technology School of Automation China University of Geosciences School of Engineering Tokyo University of Technology Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems School of Information Science and Engineering National Huaqiao University

This paper presents a disturbance rejection method that is based on the equivalent-inputdisturbance approach for uncertain fractional-order(FO) systems. An FO observer is used to reconstruct the plant states and estimate the disturbances. A disturbance estimator is incorporated in the construction of the FO control system to actively compensate for the entire disturbance. A robust stability condition for the control system and the parameters of the controller are derived using an indirect Lyapunov *** presented method effectively rejects disturbances and handles modeling uncertainties without requiring prior knowledge of the disturbance. Comparison simulations on both numerical and practical examples demonstrate the effectiveness of the proposed method.

关键词： fractional-order system disturbance rejection equivalent-input-disturbance uncertain system Lyapunov method state observer stability

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Protein complex Discovery based on Graph Wavelet

Multi-scale Protein Complex Discovery based on Graph Wavelet

引用

第三十九届中国控制会议

作者： Wang Yue Ran Xu Peng Xiao-yu Yi Ming Zhu Yuan School of Science Huazhong Agricultural University School of Mathematics and Statistics Huazhong University of Science and Technology School of Mechanical Engineering Wuhan Institute of Shipbuilding Technology School of Mathematics and Physics China University of Geosciences School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems

Identifying protein complexes from protein interaction networks is an important task in the post-genomic era. With the development of high-throughput sequencing technology, the acquisition of protein interaction network data is becoming more and more convenient. The current protein complex recognition algorithms cannot well balance the hierarchical and overlapping properties of protein networks. In order to overcome these limitations, this paper proposes a Graph Wavelet based Protein complex Discovery algorithm, GW-PCD. The method exploits the clustering analysis of protein interaction networks to find a modular mechanism by characterizing the distance between graph wavelet coefficients of protein pairs. Comparative experimental results show that GW-PCD enhances the performance of identifying protein complexes, which will provide valuable clues for further exploration of the unknown functions of proteins at the multiscale perspective.

关键词： Graph wavelet Protein-protein interaction network Multiresolution analysis Protein complex Community discovery

来源：评论

学校读者我要写书评

暂无评论

D-S Data Fusion and Efficiency Evaluation for Drilling Process

D-S Data Fusion and Efficiency Evaluation for Drilling Proce...

引用

第37届中国控制会议

作者： Haipeng Fan Xuzhi Lai Min Wu School of Automation China University of Geosciences Hubei Key Labortory of Advanced Control and Intelligent Automation for Complex System

Due to the unknown complexity of geological conditions, drilling operations are difficult to carry out. It is of great value to implement drilling measurement while drilling. However, due to the poor working conditions underground, information transmission for the drilling process may be affected, which leads to the loss and conflicts of the data. It is necessary to use effective method to deal with the data and to make evaluation for the drilling process. In this paper, we present a D-S data fusion method and use fused data to form a framework to evaluate efficiency for the drilling process. We can efficiently analyze the entire drilling process and optimize the drilling parameters based on this framework.

关键词： State Monitoring Wireless Sensor Network Data fusion Efficiency evaluation Drilling process

来源：评论

学校读者我要写书评

暂无评论

Dissipativity Analysis for Markovian Jump Neural Networks with Time-Varying Delay via An Extended Relaxed Integral Inequality 37

Dissipativity Analysis for Markovian Jump Neural Networks wi...

引用

37th Chinese control Conference, CCC 2018

作者： Wen-Juan, Lin Yong, He Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems China University of Geosciences School of Automation Wuhan430074 China

ISBN: (纸本)9789881563941

This paper investigates the problem of the strictly (\mathcal{Q}, \mathcal{S}, \mathcal{R})-\gamma -dissipativity analysis for Markovian jump neural networks with a time-varying delay. By employing an appropriate Lyapunov-Krasovskii functional and using the extended relaxed integral inequality to estimate its derivative, a delay-dependent and mode-dependent condition that guarantee the considered Markovian jump neural networks strictly (\mathcal{Q}, \mathcal{S}, \mathcal{R})-\gamma -dissipative is derived. Finally, a numerical example is provided to illustrate the effectiveness of the proposed method. © 2018 Technical Committee on control Theory, Chinese Association of automation.

关键词： Lyapunov functions

来源：评论

学校读者我要写书评

暂无评论

Convex Relaxation with Log-Determinant Divergence-L1 Regularization for 3D Shape Reconstruction

Convex Relaxation with Log-Determinant Divergence-L1 Regular...

引用

第三十八届中国控制会议

作者： Wei Cao Luefeng Chen Min Wu Witold Pedrycz School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Department of Electrical and Computer Engineering University of Alberta

Investigated is the problem of estimating the 3 D shape of an object defined by a set of 3 D landmarks with their 2 D correspondences in a single image. To solve this problem, we use a dictionary of the basic shape with LDD-L1 regularization,which is the construction of the shape space model. Based on the proposed convex optimization method, 3 D human pose reconstruction by shape space model and 3 D variable shape model was carried out on the mocap database. To improve accuracy and reduce the number of iterations, we use PSO algorithm to optimize initial value of the key parameter. The experimental results show that the improved algorithm exhibits less iterations but higher accuracy, which can be much helpful in practical applications.

关键词： LDD-L1 regularization 3D reconstruction PSO

来源：评论

学校读者我要写书评

暂无评论

Visual enhancement by spectral optimization of light sources 8

Visual enhancement by spectral optimization of light sources

引用

8th International Symposium on Computational Intelligence and Industrial Applications and 12th China-Japan International Workshop on Information Technology and control Applications, ISCIIA and ITCA 2018

作者： Jin, Xing Cheng, Xianghui Yang, Xiang Zhang, Jinjin School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China

The visualization of an object image is directly affected by the spectral power distribution of the illuminated light source. In addition, the quality and the clarity of an object image can be evaluated by the color entropy value. Therefore, in order to obtain higher color entropy value of the target object image, a visual enhancement method is proposed by optimizing the spectral of the illumination. The optimal light source spectrum of the target image is obtained by the maximum color entropy, and the spectral reflectance of the object is obtained by the reconstruction method of the RBF neural network. The images under the optimal illumination source were compared with those of other commercial white light sources (6774K, 5000K, 2700K, 3000K,). The result shows that the optimized light source has a better visual effect and the lines in the image are more apparent. © ISCIIA and ITCA 2018 - 8th International Symposium on Computational Intelligence and Industrial Applications and 12th China-Japan International Workshop on Information Technology and control Application.

关键词： Light sources

来源：评论

学校读者我要写书评

暂无评论

Real-world Robot Reaching Skill Learning Based on Deep Reinforcement Learning

Real-world Robot Reaching Skill Learning Based on Deep Reinf...

引用

第32届中国控制与决策会议

作者： Naijun Liu Tao Lu Yinghao Cai Rui Wang Shuo Wang State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced TechnologyChinese Academy of Sciences Center for Excellence in Brain Science and Intelligence Technology of the Chinese Academy of Sciences

Traditional programming method can achieve certain manipulation tasks with the assumption that robot environment is known and ***,with robots gradually applied in more domains,robots often encounter working scenes which are complicated,unpredictable,and *** overcome the limitation of traditional programming method,in this paper,we apply deep reinforcement learning(DRL) method to train robot agent to obtain skill *** policy trained with DRL on real-world robot is time-consuming and costly,we propose a novel and simple learning paradigm with the aim of training physical robot ***,our method train a virtual agent in an simulated environment to reach random target position from random initial ***,virtual agent trajectory sequence obtained with the trained policy,is transformed to real-world robot command with coordinate transformation to control robot performing reaching *** show that the proposed method can obtain self-adaptive reaching policy with low training cost,which is of great benefits for developing intelligent and robust robot manipulation skill system.

关键词： Robot reaching skill learning deep reinforcement learning

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：