检索结果-内蒙古大学图书馆

Chinese control Conference (CCC)

作者： Wei Wang Xin Chen Fang Wang Hao Fu Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan P. R. China School of Electrical and Information Engineering Zhengzhou University of Light Industry Wuhan P. R. China

In engineering applications, it is very useful to make a nonlinear system behave like a linear stable system. However, how to design a model reference adaptive control (MRAC) as the nonlinear dynamics is unknown is the key problem. In this study, an MRAC with adaptive dynamic programming (ADP) algorithm is presented for discrete-time nonlinear unknown dynamic systems, in which a multi-layer neural network (NN) model is utilized to describe the nonlinear system's dynamics. Then based on this approximate model, a feedforward neuro-controller is developed as the desired control corresponding to the reference input. Third, the iterative ADP algorithm, in the form of actor-critic framework, employs two NNs to estimate the action value function, and generates the feedback control which, together with the feedforward neuro-controller, makes the state of the system track the reference model. Finally the feasibility of the new approach is verified by two numerical experiments.

关键词： Artificial neural networks Nonlinear systems Feedforward systems Optimal control Adaptation models Feedback control Mathematical model

来源：评论

学校读者我要写书评

暂无评论

Estimation of image Jacobian Matrix with time-delay compensation based on Kalman filtering with colored noise 5

Estimation of image Jacobian Matrix with time-delay compensa...

引用

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

作者： Wang, Xinmei Liu, Zhenzhu Wei, Wu Liu, Feng School of Automation China University of Geosciences Hubei430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan Hubei430074 China College of Automation Science and Engineering South China University of Technology Guangzhou Guangdong510640 China

In order to compensate for the impact of time delay on the estimation of object feature point image and image Jacobian matrix and improve the control precision of image-based visual servo system, a Kalman filtering algorithm with colored noise is proposed to obtained the current motion state estimation of the feature point with time-delay compensation in the image space, then the accurate image Jacobian matrix under time delay can be obtained. For the above, the following work will be done in this paper: (1) the current motion state estimation of the feature point in the image space is predicted by Kalman filtering algorithm, combined with practical applications, measurement noise is usually as colored noise and can be regarded as a one-order Markov sequence excited by Gauss white noise, then a Kalman filtering recursive model can be derived according to the variance minimization principle of the estimation error;(2) to obtain the measurement vectors estimation which cannot be acquired in the Kalman filtering model owing to the existence of time delay, the relationship between the motion state of the feature point at the prior and later point is established, and a polynomial is fitted by using some of the observed data under the relationship to realize the measurement vectors estimation in the time-delay period. Thus the estimation of the motion state of the feature point at the current time in the image space can be obtained, and the estimation of image Jacobian matrix with time-delay compensation can be obtained. Experimental results validate the feasibility and superiority of this method.

关键词： Time delay

来源：评论

学校读者我要写书评

暂无评论

Distributed dynamic modeling and monitoring for large-scale industrial processes under closed-loop control

arXiv

引用

arXiv 2018年

作者： Li, Wenqing Zhao, Chunhui Huang, Biao State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou310027 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Department of Chemical and Materials Engineering University of Alberta EdmontonABT6G-2V4 Canada

For large-scale industrial processes under closed-loop control, process dynamics directly resulting from control action are typical characteristics and may show different behaviors between real faults and normal changes of operating conditions. However, conventional distributed monitoring approaches do not consider the closed-loop control mechanism and only explore static characteristics, which thus are incapable of distinguishing between real process faults and nominal changes of operating conditions, leading to unnecessary alarms. In this regard, this paper proposes a distributed monitoring method for closed-loop industrial processes by concurrently exploring static and dynamic characteristics. First, the large-scale closed-loop process is decomposed into several subsystems by developing a sparse slow feature analysis (SSFA) algorithm which capture changes of both static and dynamic information. Second, distributed models are developed to separately capture static and dynamic characteristics from the local and global aspects. Based on the distributed monitoring system, a two-level monitoring strategy is proposed to check different influences on process characteristics resulting from changes of the operating conditions and control action, and thus the two changes can be well distinguished from each other. Case studies are conducted based on both benchmark data and real industrial process data to illustrate the effectiveness of the proposed method. Copyright © 2018, The Authors. All rights reserved.

关键词： Process monitoring

来源：评论

学校读者我要写书评

暂无评论

An Improved-WM Method Based on Optimization of Centers of Output Fuzzy Subsets for Fuzzy Rules

引用

IFAC-PapersOnLine 2017年第1期50卷 7369-7374页

作者： Jin Y. Cao W. Wu M. She J. Yuan Y. 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 School of Engineering Tokyo University of Technology Hachioji Tokyo 192-0982 Japan

The generation of fuzzy rules from samples is significant for fuzzy modelling. To improve the robustness of Wang-Mendel (WM) method, an improved WM method to extract fuzzy rules from all the regularized sample data was proposed. However, the accuracy of the model with this method is degraded for the conflicting rules with small difference between support degrees. And the output subsets can only be chosen from the pre-defined ones. To solve these problems, we develop an improved-WM method based on optimization of centers of output fuzzy subsets for fuzzy rules (COiWM). This method adopts the fuzzy c-means (FCM) clustering algorithm to divide the input and output spaces, and the improved WM method which replaces the original data by regularized data is used to calculate the support degrees. Then the support degrees are used as weights to optimize the centers of output fuzzy subsets with a method of weighted averages, so as to enhance the accuracy of a fuzzy model. Experimental results of a case study on short term daily maximum electric load forecasting prove that our proposed method enhances the accuracy of a fuzzy model. © 2017

关键词： Accuracy Conflicting rules Fuzzy c-means clustering algorithm Fuzzy rules Wang-Mendel method

来源：评论

学校读者我要写书评

暂无评论

A four-stage localization method for epileptic seizure onset zones

引用

IFAC-PapersOnLine 2017年第1期50卷 4412-4417页

作者： Wan T. Wu M. Lai X. Wan X. She J. Du Y. School of Automation China University of Geosciences Wuhan Hubei 430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan Hubei 430074 China School of Engineering Tokyo University of Technology Hachioji Tokyo 192-0982 Japan School of Automation Guangdong University of Technology Guangzhou Guangdong 510006 China

This paper presents a four-stage localization method for epileptic seizure onset zones (SOZs). This method combines the advantages of both the Shannon-entropy-based complex Morlet wavelet transform (SE-CMWT) and adaptive-genetic-algorithm-based matching pursuit (AGA-MP) methods to achieve satisfactory localization performance. The Hilbert transform method is used to identify events of interest. The SE-CMWT-based power spectral density method is applied to acquire channels of interest (CoIs). By using the Morlet wavelets as the dictionary elements, the AGA-MP method combined with Morlet wavelets is developed to detect high-frequency oscillations (HFOs) on CoIs with faster speed and higher accuracy than the AGA-MP method. And the characteristics of HFOs are used to localize SOZs based on the half-maximum method. A comparison shows that our method has higher sensitivity and specificity than four existing methods. © 2017

关键词： Epilepsy Four-stage localization method High-frequency oscillation (HFO) Seizure onset zone (SOZ)

来源：评论

学校读者我要写书评

暂无评论

A Novel Deep Learning Approach: Stacked Evolutionary Auto-encoder

A Novel Deep Learning Approach: Stacked Evolutionary Auto-en...

引用

International Joint Conference on Neural Networks

作者： Yaoming Cai Zhihua Cai Meng Zeng Xiaobo Liu Jia Wu Guangjun Wang School of Computer Science China University of Geosciences Wuhan China Qinzhou University Guangxi China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Department of Computing Macquarie University Sydney NSW Australia

Deep neural networks have been successfully applied to many data mining problems in recent works. The training of deep neural networks relies heavily upon gradient descent methods, however, which may lead to the failure of training due to the vanishing gradient (or exploding gradient) and local optima problems. In this paper, we present SEvoAE method based on using Evolutionary Multiobjective Optimization (EMO) algorithm to train single layer auto-encoder, and sequentially learning deeper representation in a stacking way. SEvoAE is able to achieve accurate feature representation with good sparseness by globally simultaneously optimizing two conflicting objective functions and allows users to flexibly design objective functions and evolutionary optimizers. We compare results of the proposed method with existing architectures for seven classification problems, showing that the proposed method is able to outperform existing methods with a reduced risk of overfitting the training data.

关键词： Training Optimization Decoding Neural networks Linear programming Feature extraction Stacking

来源：评论

学校读者我要写书评

暂无评论

Relation Model of Burden Operation and State Variables of Blast Furnace Based on Low Frequency Feature Extraction*

引用

IFAC-PapersOnLine 2017年第1期50卷 13796-13801页

作者： Zhang, Kexin Wu, Min An, Jianqi Cao, Weihua Liu, Zhentao Ning, Fulong School of Automation China University of Geosciences Wuhan430074 China Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Faculty of Engineering China University of Geosciences wuhan430074 China Department of Computer Science School of Computing Tokyo Institute of Technology Yokohama226-8502 Japan

In the blast furnace ironmaking process, the running state of the blast furnace can be directly adjusted by the burden operation. Therefore, the explicit relation between the burden operation and the running state variables is vital for the blast furnace operators. However, the state variables of the blast furnace are affected by many factors and the burden matrix is complicated. In this paper, a support vector regression(SVR) predicting model based on low frequency feature extraction is proposed to solve these problems. First, the low frequency components of state variables time series which are mostly affected by the burden operation are extracted. Then, the dimensions of the burden matrix are reduced by a devised simple expression method. Finally, the relation model based on SVR is proposed to predict the values of the expected state variables according to the simplified burden matrix and the value of initial state variables. The simulation on real factory data indicates that the model reflects the accurate quantitative relation between the burden operation and the state variables. © 2017

关键词： Blast furnaces Blast furnace practice Extraction Feature extraction Support vector regression Blast furnace iron making Blast furnace operators burden operation Initial state variables Low frequency components Relation models State variables Support vector regression (SVR)

来源：评论

学校读者我要写书评

暂无评论

Privacy Preservation for Distributed Nonsmooth Constrained Optimization Based on Pseudo-Subgradient

Privacy Preservation for Distributed Nonsmooth Constrained O...

引用

第37届中国控制会议

作者： Xianlin Zeng Shu Liang Jie Chen Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing Advanced Innovation Center for Intelligent Robots and Systems (Beijing Institute of Technology) Key Laboratory of Biomimetic Robots and Systems (Beijing Institute of Technology) Ministry of Education

In this paper, we investigate a privacy preservation design in the distributed nonsmooth convex optimization with set constraints. To solve the distributed optimization problem while preserving the privacy, we use pseudo-subgradients involved with（non-integrable） set-valued functions. Based on pseudo-subgradients, we propose distributed nonsmooth optimization algorithms with keeping subgradient information confidential. Then we prove the correctness and convergence of the distributed privacy preservation optimization algorithms to achieve the exact solution of the original optimization problem.

关键词： Distributed nonsmooth convex optimization privacy preservation set constraints pseudo-subgradients

来源：评论

学校读者我要写书评

暂无评论

Stability and Neimark-Sacker bifurcation analysis for single gene discrete system with delay

Stability and Neimark-Sacker bifurcation analysis for single...

引用

Chinese control Conference

作者： Feng Liu Qicheng Mei Fenglan Sun Xinmei Wang Hua O. Wang Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China School of Automation China University of Geosciences Wuhan China Research Center of System Theory and Application Chongqing University of Posts and Telecommunications Chongqing China Department of Mechanical Engineering Boston University Boston MA USA

The network structure and functional properties of gene regulatory system and their relationships arc an important research field in systems biology. In this paper, a new improved model is proposed based on the study of gene expression process. The model takes into account the effect of protein concentration on the gene expression, so as to obtain a new bifurcation point and improve the performance of the system. The validity of the model is verified by theoretical analysis and data simulation.

关键词： Mathematical model Proteins Stability analysis Bifurcation Biological system modeling Delays RNA

来源：评论

学校读者我要写书评

暂无评论

An approach of joint-space trajectory generation 5

An approach of joint-space trajectory generation

引用

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

作者： Chen, Xin Jiang, Chen-Xu Zhou, Li School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex System Wuhanz430074 China School of Arts and Communication China University of Geosciences Wuhan430074 China

Trajectory generation is a prerequisite for robot control system and is divided into two regions, Cartesian space and joint space. This paper presents an approach to generate the trajectory in joint-space. This method uses normalization and transformation of the sine function to generate the desired trajectory, which is more smooth and continuous than the parabolic method in multiple time derivatives of the joint parameter. Compared with the third order polynomial method, this approach can depress the unacceptable infinite spikes in the jerk, which is the derivative of acceleration. Besides, the using of normalization in this approach is to make it more convenient and efficient be applied.

关键词： Trajectories

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：