检索结果-内蒙古大学图书馆

Chinese Automation Congress (CAC)

作者： Xiao Han Fang Hu Gang Xiong Xiwei Liu Xiaoyan Gong Xiaojie Niu Wanruo Shi Xinzhu Wang Qingdao Institute of Education Sciences Qingdao China Qingdao No.2 Middle School of Shandong Province Qingdao China The Cloud Computing Center Chinese Academy of Sciences Dongguan China The State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences Beijing China Institute of Smart Education Systems Qingdao Academy of Intelligent Industries Qingdao China Faculty of Education Beijing Normal University Beijing China

We are entering a new AI era, and the development of AI technology and popularization of AI education has become the national strategy of China. The primary and secondary school students are the builder of future society, and have strong curiosity and passion to learn new things; therefore, we should make a good preparation of AI education for them and cultivate their basic AI literacy and computational thinking to adapt to the future. In this paper, from the viewpoint of thinking mode and literacy and skill training, a curriculum including basic, project, and practical types is designed. Integrating with the iSTREAM educational system proposed by Chinese Academy of Sciences, exploratory works were shown with some case studies. The applications show that AI education is helpful to enrich the study of primary and secondary school students and to prompt comprehensive quality.

关键词： Artificial intelligence Education Industries Technological innovation Programming profession Task analysis

来源：评论

学校读者我要写书评

暂无评论

Distributed trajectory tracking control for multiple nonholonomic mobile robots

引用

IFAC-PapersOnLine 2016年第4期49卷 31-36页

作者： Yang, Qingkai Fang, Hao Cao, Ming Chen, Jie School of Automation Beijing Institute of Technology Beijing100081 China Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing100081 China Faculty of Mathematics and Natural Sciences University of Groningen Groningen AG9747 Netherlands

In this paper, the distributed tracking problem for multiple nonholonomic mobile robots is investigated, in which the nonholonomic models are transformed into chained-form systems. By utilizing the dynamic oscillator strategy, the distributed controllers are constructed such that all the mobile robots' trajectories converge to the desired reference asymptotically. One advantage of the chained-form system solution that we propose is that it requires no other variable transformations, which could help reducing the system's complexity and broadening the proposed controller's practical applications. Simulations are presented to show the effectiveness of the proposed control algorithms. © 2016, IFAC (International Federation of Automatic control) Hosting by Elsevier Ltd. All rights reserved.

关键词： Multi agent systems controllers Distributed parameter control systems Mobile robots Navigation Chained form system Distributed control Distributed controller Distributed tracking Non holonomic mobile robots Tracking controls Trajectory tracking control Variable transformation

来源：评论

学校读者我要写书评

暂无评论

Suppressing the pressure fluctuations caused by drill string vibration by SP-EID method

Suppressing the pressure fluctuations caused by drill string...

引用

Asian control Conference

作者： Yang Zhou Xin Chen School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control Intelligent Automation for Complex Systems Wuhan China

ISBN: (纸本)9781509015740;9781509015733

During drilling process, the axial vibration of the drill string always causes the fluctuations of the bottom hole pressure, which may lead to serious accidents. At the same time the bottom hole pressure control system also has the phenomenon of parameter change and the feedback delay, so that the pressure is difficult to control. In view of this situation, we develop a method combining Smith Predictor with equivalent input disturbance(SP-EID) approach to achieve the disturbance suppression and delay compensation. First, considering the changes in the model parameters, we improve the existing hydraulic model to describe the dynamic characteristics of the bottom hole pressure, at same time the mathematical form of the disturbance is given. Then we use the Smith Predictor to compensate the delay of the feedback channel and apply EID method to suppress pressure disturbances. Finally the SP-EID method is used to adjust the mud flow on the ground to control the bottom hole pressure. The simulations are conducted to compare our method with SMC method, in order to show the superiority and effectiveness of our method.

关键词： Mathematical model Delays Matrix decomposition Vibrations State feedback Symmetric matrices

来源：评论

学校读者我要写书评

暂无评论

A GA-SVM and D-S evidence theory based method for shunt-fault diagnosis in power systems

A GA-SVM and D-S evidence theory based method for shunt-faul...

引用

Asian control Conference

作者： Xiaomin Wu Dianhong Wang Weihua Cao Min Ding School of Automation China University of Geosciences Wuhan China Hubei KEY Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China

ISBN: (纸本)9781509015740;9781509015733

In this paper, a novel genetic algorithm support vector machine (GA-SVM) and Dempster Shafer (D-S) evidence theory based diagnostic method is proposed to improve the efficiency and accuracy for power system fault diagnosis. The fault diagnosis method proposed consists of two steps, first step is the preliminary diagnosis, the second step is the fault fusion. The preliminary diagnosis with two GA-SVM classifiers decreases the information dimension and improve the efficiency. The fault fusion based on D-S evidence theory reduces the conflict of the preliminary diagnosis faults. The voltage phasor and current phasor information are utilized together in the method, the diagnosis accuracy is improved by weakening the detection uncertainties. The method proposed applied in an actual power system in Hubei province in China. The practical results verified the feasibility and effectiveness of the method.

关键词： Support vector machines Genetic algorithms Fault diagnosis Substations Training Uncertainty

来源：评论

学校读者我要写书评

暂无评论

Nesterov Accelerated Gradient Descent-based Convolution Neural Network with Dropout for Facial Expression Recognition

Nesterov Accelerated Gradient Descent-based Convolution Neur...

引用

Asian control Conference

作者： Wanjuan Su Luefeng Chen Min Wu Mengtian Zhou Zhentao Liu Weihua Cao School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China

ISBN: (纸本)9781509015740;9781509015733

Nesterov accelerated gradient descent-based convolution neural network (NAGDCNN) with dropout is proposed for facial expression recognition, which fuses the convolution neural network (CNN) with Softmax regression to construct a deep convolution neural network (DCNN) that can excavate high-level expression features and classify them. The dropout layer is added after the sub-sampling layer which can effectively reduce overfitting and the network's training time, moreover, the Nesterov accelerated gradient descent (NAGD) is used to optimize the network weights that can predictably prevent the algorithm from going too fast or too slow and enhance the response capability of the network. To verify the effectiveness of the proposal, experiments on benchmark database are conducted, and the experimental results show that the proposal outperforms the state-of-the-art methods. Futhermore, the application experiment is also curried out and the results indicate the feasibility of the proposal in practical applications.

关键词： Deep learning Facial expression recognition Nesterov accelerated gradient descent Dropout Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

New constructing method of Lyapunov-Krasovskii functionals for stability of time-varying delay systems

New constructing method of Lyapunov-Krasovskii functionals f...

引用

Annual Conference of Industrial Electronics Society

作者： Gao Zhenman He Yong Wu Min School of Automation China University of Geosciences Wuhan Chian Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China

This paper investigates the stability of linear systems with a time-varying delay. We propose a new approach to construct Lyapunuv-Krasovskii functional (LKF). Compared with other traditional approach, the proposed one can provide a higher time-delay upper bound and lower computation complexity. Six stability criteria by linear matrix inequalities (LMIs) are established by proposed two novel LKFs in this paper. Based on one numerical example, the advantages of the proposed approach are illustrated.

关键词： Stability criteria Symmetric matrices Linear matrix inequalities Numerical stability Delays Linear systems

来源：评论

学校读者我要写书评

暂无评论

A Model Reference Adaptive control with ADP-to-SMC Strategy for Unknown Nonlinear systems

A Model Reference Adaptive Control with ADP-to-SMC Strategy ...

引用

Asian control Conference

作者： Hao Fu Xin Chen Wei Wang School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China

ISBN: (纸本)9781509015740;9781509015733

In this paper, a novel online learning controller based on model reference adaptive control (MRAC) is presented to simplify the complexity of controlling a class of discrete nonlinear systems with a little prior knowledge, using approximate dynamic programming (ADP). Without the identifier and the assumption of a command generator model, the proposed approach employs a modified direct heuristic dynamic programming (HDP) to acquire two types of the bounded tracking errors, which are available to transform the system into a linear system with the uncertain bounded persistent disturbance. In addition, toggling between the learning and the sliding mode control (SMC) flexibly, an ADP-to-SMC strategy is developed to guarantee the better performance in MRAC. Finally, Simulation results demonstrate the effectiveness of the proposed control scheme.

关键词： Mathematical model Nonlinear systems Adaptation models Linear systems Computational modeling Linear programming Generators

来源：评论

学校读者我要写书评

暂无评论

TIEA: A tradeoff-based interactive multiobjective evolutionary algorithm 7

TIEA: A tradeoff-based interactive multiobjective evolutiona...

引用

7th International Symposium on Computational Intelligence and Industrial Applications, ISCIIA 2016

作者： Chen, Lu Xin, Bin Chen, Jie School of Automation Beijing Institute of Technology Key Laboratory of Intelligent Control and Decision of Complex System Beijing China

ISBN: (纸本)9784990534349

This paper proposes a tradeoff based interactive multiobjective evolutionary algorithm (TIEA). It can support the decision maker (DM) to guide the search towards the DM's most preferred solution by combing evolutionary algorithms with the framework of gradient projection. At each iteration, an evolutionary algorithm is used to generate an approximate Pareto optimal solution. Then, the DM is asked to provide preferences in terms of indifference tradeoffs, the projection of which onto the tangent hyperplane of the Pareto front provides a tradeoff direction. To calculate the projection, an approach to approximate the normal vector of the tangent hyperplane of the Pareto front is developed. Results on nine numerical examples by using TIEA show that TIEA is able to solve multiobjective optimization problems with more than three objectives. Moreover, it can find the Pareto optimal solution that the DM prefers most. © 2016, Fuji Technology Press. All rights reserved.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Maximum power point tracking control of direct-drive permanent magnet wind turbine based on adaptive neuro-fuzzy inference system 5

Maximum power point tracking control of direct-drive permane...

引用

5th International Workshop on Advanced Computational Intelligence and intelligent Informatics, IWACIII 2017

作者： Ding, Min Ou, Yingxiong Hu, Bo She, Jinhua Wu, Min School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China State Grid Energy Research Institute Beijing102200 China School of Engineering Tokyo University of Technology Tokyo192-0982 Japan

The power from wind varies depending on the environmental factors. Because of the randomness and intermittent of wind, it is difficult for the wind energy conversion system to locate and track the maximum power point (MPP) with fast speed and high accuracy under the condition of variable wind speed. In this paper, a variable-speed wind-generator maximum power point tracking (MPPT) control method based on adaptative neuro-fuzzy inference system (ANFIS) is presented. It is designed as a combination of the Sugeno fuzzy model and neural network. The ANFIS based controller predicts the optimum speed with the inputs as the speed change and power change, and controls the speed with PI controllers. The performance of the proposed controller is tested for direct-drive permanent magnet wind turbine based wind energy conversion system under fast wind speed variation in MATLAB/Simulink. The simulation results show that the designed control method has good dynamic characteristics and steady-state accuracy in wind power MPPT and improves the working efficiency.

关键词： Wind turbines

来源：评论

学校读者我要写书评

暂无评论

Spike-burst chimera states in an adaptive exponential integrate-and-fire neuronal network

arXiv

引用

arXiv 2019年

作者： Santos, Moises S. Protachevicz, Paulo R. Iarosz, Kelly C. Caldas, Iberê L. Viana, Ricardo L. Borges, Fernando S. Ren, Hai-Peng Szezech, José D. Batista, Antonio M. Grebogi, Celso Department of Physics Federal University of Paraná CuritibaPR80060-000 Brazil Graduate in Science Program - Physics State University of Ponta Grossa Ponta Grossa PR84030-900 Brazil Institute of Physics University of São Paulo São PauloSP05508-900 Brazil Center for Mathematics Computation and Cognition Federal University of ABC São Bernardo do CampoSP09606-045 Brazil Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xian University of Technology Xi'an710048 China Xian Technological University Xi'an710021 China Graduate in Science Program - Physics State University of Ponta Grossa Ponta Grossa PR84030-900 Brazil Institute for Complex Systems and Mathematical Biology King's College University of Aberdeen AberdeenAB24 3UE United Kingdom

Chimera states are spatiotemporal patterns in which coherence and incoherence coexist. We observe the coexistence of synchronous (coherent) and desynchronous (incoherent) domains in a neuronal network. The network is composed of coupled adaptive exponential integrate-and-fire neurons that are connected by means of chemical synapses. In our neuronal network, the chimera states exhibit spatial structures both with spikes and bursts activities. Furthermore, those desynchronised domains not only have either spike or burst activity, but we show that the structures switch between spikes and bursts as the time evolves. Moreover, we verify the existence of multicluster chimera states. Copyright © 2019, The Authors. All rights reserved.

关键词： Neural networks

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：