检索结果-内蒙古大学图书馆

Conference Record of the IEEE Industry Applications Society Annual Meeting (IAS)

作者： Ahmad El Khateb M.N. Uddin N. A. Rahim Barry W. Williams Automatic Control and Human-Machine Systems LAMIH UMR/CNRS Valenciennes France Electronic Engineering Department Tsinghua University Tsinghua National Laboratory for Information Science and Technology (TNList) Beijing P. R. China Shenzhen City Key Laboratory of Digital TV System Valeo Powertrain Systems Amiens France National Engineering Lab. for DTV(Beijing) Beijing P. R. China

ISBN: (纸本)9781479983988

This paper presents analysis and control of D converter, which has continuous input and output current to obtain maximum power transfer from a photovoltaic (PV) system. Examining the maximum power involves optimization and control techniques that ensure maximum power extraction enhancement. Traditional converters have rather high input ripple current that originates considerable loss of power extraction when linked to photovoltaic panels. Operating with zero input ripple current enlarges the power obtained from the PV panel without employing electrolytic capacitor. Experiment and simulation of the converter performance support and extol the system concept and establish a balanced view among several types of used controllers as well.

关键词： Inverters Capacitors Photovoltaic systems Radiation effects control systems Fuel cells

来源：评论

学校读者我要写书评

暂无评论

Image recognition based on deep learning

Image recognition based on deep learning

引用

Chinese Automation Congress (CAC)

作者： Meiyin Wu Li Chen College of Computer Science and Technology Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China

Deep learning is a multilayer neural network learning algorithm which emerged in recent years. It has brought a new wave to machine learning, and making artificial intelligence and human-computer interaction advance with big strides. We applied deep learning to handwritten character recognition, and explored the two mainstream algorithm of deep learning: the Convolutional Neural Network (CNN) and the Deep Belief NetWork (DBN). We conduct the performance evaluation for CNN and DBN on the MNIST database and the real-world handwritten character database. The classification accuracy rate of CNN and DBN on the MNIST database is 99.28% and 98.12% respectively, and on the real-world handwritten character database is 92.91% and 91.66% respectively. The experiment results show that deep learning does have an excellent feature learning ability. It don't need to extract features manually. Deep learning can learn more nature features of the data.

关键词： Databases Feature extraction Machine learning Training Convolution Kernel Character recognition

来源：评论

学校读者我要写书评

暂无评论

Distributed simultaneous localization and mapping algorithm based on partition of space-region

引用

Xi Tong Gong Cheng Yu Dian Zi Ji Shu/systems Engineering and Electronics 2015年第3期37卷 639-645页

作者： Pei, Fu-Jun Cheng, Yu-Hang Li, Hao-Yang Ju, He-Hua School of Electronic Information & Control Engineering Beijing University of Technology Beijing100124 China Beijing Key Laboratory of Computational Intelligence and Intelligence System Beijing100124 China

To solve the problem of the simultaneous localization and mapping (SLAM) under the complex circumstance, a distributed algorithm of the SLAM based on partition of space-region is proposed considering the respective advantages of centralized configuration and distributed structure. The region is formed according to the angle between two landmarks and the robot, which is designed in case of the collinearity between two landmarks. The landmarks in each region are combined to establish the corresponding observation model. Besides, the position of the robot is obtained by applying the distributed unscented particle filter and the positions of the landmarks are estimated simultaneously by employing the Kalman filter. Meanwhile, the accuracy and the stability are improved through constructing the adjustment of particle distribution during the dynamic reconfiguration process. Eventually, the better real-time capability and filter accuracy of the proposed SLAM algorithm are proved through simulation experiments which are supported by actual data. ©, 2015, Chinese Institute of Electronics. All right reserved.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Motion Analysis and Experimental Study of A Cable-driven Soft Surgical Robot

Motion Analysis and Experimental Study of A Cable-driven Sof...

引用

IEEE International Conference on Cyber Technology in Automation, control, and Intelligent systems

作者： Runxi Zhang Hesheng Wang Weidong Chen Xiaozhou Wang Rolf Pfeifer Department of Automation Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Chest Hospital Shanghai Jiao Tong University

ISBN: (纸本)9781479987313

A cable-driven soft robot manipulator is analyzed in this paper. The soft robot manipulator is made of silicon and driven by cables. To improve its flexibility and controllability, the soft robot manipulator is divided into two parts from the middle. Due to infinite degrees of freedom (DOF) and soft materials, the soft robot manipulator is more difficult to model and control. A kinematic model, which takes the two parts into consideration, is established to analyze the motion of the soft robot manipulator. This kinematic model is based on piecewise constant curve. Experiments about motion analysis have been conducted for many times with artificial heart and healthy swine. The experiments demonstrate that the two-part soft robot manipulator is controlled better than one-part and has the ability to reach almost every regions of the heart including the posterior left atrial wall (LAPw).

关键词： Robot Manipulator kinematics artificial heart surgical robots

来源：评论

学校读者我要写书评

暂无评论

A Simulation Platform for Characteristic Model-Based Adaptive control systems

A Simulation Platform for Characteristic Model-Based Adaptiv...

引用

第三十四届中国控制会议

作者： Liangren Shi Zongli Lin Yuanlong Li Department of Automation and Key Laboratory of System Control and Information ProcessingShanghai Jiao Tong University Charles L. Brown Department of Electrical and Computer Engineering University of Virginia

ISBN: (纸本)9781467374439

Characteristic modeling and the adaptive control design based on it have attracted increasing attention from the research community due to their many successful practical applications that have been reported. This paper presents a Matlab simulation platform that has been developed to facilitate the study of characteristic model based adaptive control systems. The simulation platform consists of two interweaving components: for a given continuous-time linear time-invariant plant, represented by a transfer function, and a specified sampling period, the simulation platform calculates a discretized model of the plant, and the corresponding characteristic model, and with a specified set of initial conditions of the characteristic model and its coefficients, along with the specified duration of simulation and reference input, the simulation platform will adaptively tune the coefficients of the characteristic model and calculate the outputs of the plant and the characteristic model. All the data needed for the simulation will be entered through a graphic user interface, which also plots the evolution of the outputs of the plant and the characteristic model as well as the evolution of the coefficients of the characteristic model. The simulation results can also be saved for off line plotting and analysis through the graphic user interface.

关键词： Characteristic model,adaptive control,simulation

来源：评论

学校读者我要写书评

暂无评论

Research for effect of dirt defect of quartz wafer on its electrical parameters

Research for effect of dirt defect of quartz wafer on its el...

引用

2015 IEEE 12th International Conference on Electronic Measurement & Instruments

作者： Li Dong Wang Yanlin Liu Gang Song Peiji Beijing Key Laboratory on Measurement and Control of Mechanical ＆ Electrical System Beijing Information Science and Technology University

research the effect of dirt of quartz wafer on its electrical parameters. Experimental and theoretical analysis results show that the dirt of quartz wafer affects its mass, elastic modulus and vibration damping, and leads to increase of dynamic inductance, decrease of dynamic capacitance, reduction of resonant frequency and increase of resonance resistance. Effect of the dirt on the electrical parameters of quartz wafer is related to not only its magnitude, but also its location, materials and other *** study on quartz wafer appearance defects for improving the quartz wafer automatic sorting technology in our country and setting up the unified and objective testing standards of quartz wafer has important significance.

关键词： quartz wafer appearance defects dirt resonant frequency electrical parameters

来源：评论

学校读者我要写书评

暂无评论

Networked predictive control based on the round-trip delay 34

Networked predictive control based on the round-trip delay

引用

34th Chinese control Conference, CCC 2015

作者： Binglin, Wang Yu, Kang Baoqun, Yin Zhen, Xie Department of Automation University of Science and Technology of China Hefei Anhui China School of Electrical Engineering and Automation Hefei University of Technology Hefei Anhui China State Key Laboratory of Fire Science University of Science and Technology of China Key Laboratory of Technology in Geo-Satial Information Processing and Application System Chinese Academy of Science Hefei Anhui China

ISBN: (纸本)9789881563897

Network predictive control is effectively in dealing with time-delay, data dropouts, packets disorders of Network control system. This paper studies the stochastic stability of a affine nonlinear system within random time delay. The system controller is consist of a control prediction generator (CPG) at the controller side and a network delay compensator (NDC) at the plant side. Different from the previous literatures that model the random delay of the feedback channel and the forward channel as Markov chain respectively, the model in this paper is based on the round-trip delay, which making the predictive control process more concise but without losing generality. Then, this paper gives the necessary and sufficient conditions for stochastic stability of the closed-loop system. Finally, a numerical example is given to demonstrate the effectiveness of the proposed method. © 2015 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Affine system Markov Process Predictive control Stochastic Stability

来源：评论

学校读者我要写书评

暂无评论

Adaptive Image-Based Leader-Follower Approach of Mobile Robot with Omnidirectional Camera

引用

Journal of Applied Mathematics 2015年第1期2015卷

作者： Guo, Dejun Wang, Hesheng Chen, Weidong Liang, Xinwu Department of Automation Shanghai Jiao Tong University and Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai 200240 China

This paper focuses on the problem of the adaptive image-based leader-follower formation control of mobile robot with on-board omnidirectional camera. A calibrated omnidirectional camera is fixed on the follower in any position, and a feature point representing the leader can be chosen in any position. An adaptive image-based controller without depending on the velocity of the leader is proposed based on a filter technology. In other words, only by relying on the projection of the feature on the image plane, can the follower track the leader and achieve the formation control. Moreover, an observer is introduced to estimate the unknown camera extrinsic parameters and the unknown parameters of plane, where the feature point moves, relative to omnidirectional camera frame. At last, the lyapunov method is applied to prove the uniform semiglobal practical asymptotic stability (USPAS) for the closed-loop system. Simulation results are presented to validate the algorithm. © 2015 Dejun Guo et al.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of NARX-DNN Model for Coal-fired Boiler Using Real Plant Data

Development of NARX-DNN Model for Coal-fired Boiler Using Re...

引用

第26届中国过程控制会议（CPCC2015）

作者： LIU Jingwei CHENG Yin ZHANG Xi PAN Fengping ZHANG Weidong Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education Electric Power Research Institute of Guangdong Power Grid Corporation

In this paper,a deep learning model referred as NARX-DNN based on Deep Neural Network(DNN)and Nonlinear Auto Regressive with Extension X input(NARX)neural network is developed to model the coal-fired ***,the distributed control system(DCS)data is trained by DNN to extract highly abstract features for *** the NARX neural network is trained to predict parameters for coal-fired boiler with the output of ***,with the powerful learning ability of NARX-DNN model to deal with the time delay problem,the long-time predicting of operation status can be *** to the feature learning ability of DNN,the overwhelmingly complex property of coal-fired boiler can be represented more reasonable and *** are provided to illustrate the effectiveness of the proposed design *** with traditional TDNN and ARNN model,our approach achieves the lowest error rate.

关键词： Deep Learning Coal-fired Boiler Stacked De-noising Auto-Encoders

来源：评论

学校读者我要写书评

暂无评论

A selection method of frequency combination in MF-InSAR system

A selection method of frequency combination in MF-InSAR syst...

引用

IET International Radar Conference 2015

作者： Qi, Yalin Zhang, Qi Yang, Wenfu Yang, Shuangjing Liu, Tiandong Beijing Key Laboratory of Embedded Real-Time Information Processing Technology Radar Research Lab. School of Information and Electronics Beijing Institute of Technology Beijing100081 China China Academy of Launch Vehicle Technology Beijing100076 China Beijing Institute of Spacecraft System Engineering CAST Beijing100094 China

ISBN: (纸本)9781849199940

As an extension of the Interferometric Synthetic aperture radar (InSAR), the multi-frequency InSAR can realize high-accuracy elevation extraction of the steep terrain. Though the maximum likelihood estimation (MLE) is widely used in the signal processing of multi-frequency InSAR, the performance of this method can be influenced by the selection of frequency combination. At the beginning, this paper analyses the elevation estimated effectiveness of different frequency combinations from the aspect of Cramer-Rao Lower Bound (CRLB). Then, it calculates the ambiguity cycle as a further filter for the optimal frequency combination. Finally, this paper discusses the adaptability to the phase noise with the help of Monte Carlo simulation strategy. In consideration of these three aspects, a selection method of frequency combination is proposed, and further simulation results are provided in quantity. Relevant researches can be used in the design of multi-frequency InSAR system.

关键词： Phase noise

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：