检索结果-内蒙古大学图书馆

Automatic generation of digital filters by NN based learning: An application on paper pulp inspection

6th International Work-Conference on Artificial and Natural Neural Networks, IWANN 2001

作者： Campoy-Cervera, Pascual Munoz-García, David F. Pena, Daniel Calderón-Martínez, José A. Department of Automatic Control Electrical Engineering and Industrial Computing Universidad Politecnica de Madrid C/ Jose Gutierrez Abascal 2 Madrid28006 Spain Instituto Tecnologico de Aguascalientes SEP CONACYT Mexico

ISBN: (纸本)9783540422372

This paper presents an implementation of a digital filtering inspection system applied on a paper pulp sheet production process. The automation of the inspection phase is particularly critical during this process and its solution is highly complex. The system is based on neural network learning, allowing a compromise between resolution and processing speed. The experimental results demonstrating the use of this algorithm for the visual detection of defects in images obtained from a real factory environment are presented. These results show that the developed learning method generates filters that fulfil the required inspection standard. © Springer-Verlag Berlin Heidelberg 2001.

关键词： Inspection

来源：评论

学校读者我要写书评

暂无评论

Self-tuning position and force control of an underwater hydraulic manipulator

Self-tuning position and force control of an underwater hydr...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： A.C. Clegg M.W. Dunnigan D.M. Lane Advanced Control Technology Club Industrial Systems and Control Limited Glasgow UK Ocean Systems Laboratory Department of Computing and Electrical Engineering Heriot-Watt University Edinburgh UK

ISBN: (纸本)0780365763

Current generation unmanned underwater vehicles, equipped with robotic manipulators, are teleoperated and consequently place a large workload burden on the human operator. A greater degree of automation could improve the efficiency and accuracy with which underwater tasks are carried out. These tasks can involve manipulator motion that is both unconstrained and/or constrained. For unconstrained motion, where a trajectory requires following, a prerequisite is good joint angle control. An adaptive self-tuning pole-placement controller is used for joint angle control. Practical results show the benefits compared to the conventional fixed-gain control. For constrained motion, simultaneous controls of position and force are often required. An adaptive hybrid position/force controller is proposed and compared to a fixed-gain version. Simulation and practical results illustrate the merits and drawbacks of each scheme.

关键词： Force control Automatic control Adaptive control Programmable control Motion control Inspection Mechanical variables control Manipulator dynamics control systems Underwater vehicles

来源：评论

学校读者我要写书评

暂无评论

A GENERAL UPDATING RULE FOR DISCRETE HOPFIELD-TYPE NEURAL NETWORK WITH TIME-DELAY AND THE CORRESPONDING SEARCH ALGORITHM

引用

International Journal of Computational Intelligence and Applications 2001年第4期1卷 399-412页

作者： DANIEL S. YEUNG SHENSHAN QIU ERIC C. C. TSANG XIZHAO WANG Dept. of Computing The Hong Kong Polytechnic University HungHom Hong Kong China Department of Automatic Control Engineering South China University of Technology Guangzhou 510640 China Hubei University Hubei China

In this paper, the Hopfield neural network with delay (HNND) is studied from the standpoint of regarding it as an optimizing computational model. Two general updating rules for networks with delay (GURD) are given based on Hopfield-type neural networks with delay for optimization problems and characterized by dynamic thresholds. It is proved that in any sequence of updating rule modes, the GURD monotonously converges to a stable state of the network. The diagonal elements of the connection matrix are shown to have an important influence on the convergence process, and they represent the relationship of the local maximum value of the energy function to the stable states of the networks. All the ordinary discrete Hopfield neural network (DHNN) algorithms are instances of the GURD. It can be shown that the convergence conditions of the GURD may be relaxed in the context of applications, for instance, the condition of nonnegative diagonal elements of the connection matrix can be removed from the original convergence theorem. A new updating rule mode and restrictive conditions can guarantee the network to achieve a local maximum of the energy function with a step-by-step algorithm. The convergence rate improves evidently when compared with other methods. For a delay item considered as a noise disturbance item, the step-by-step algorithm demonstrates its efficiency and a high convergence rate. Experimental results support our proposed algorithm.

关键词： Discrete Hopfield neural network convergence conditions stable state convergence theorem

来源：评论

学校读者我要写书评

暂无评论

Self-Tuning Position and Force control of an Underwater Hydraulic Manipulator

引用

IFAC Proceedings Volumes 2001年第7期34卷 149-154页

作者： A.C. Clegg M.W. Dunnigan D.M. Lane Advanced Control Technology Club Industrial Systems and Control Ltd. 50 George Street Glasgow G1 1QE United Kingdom Ocean Systems Laboratory Department of Computing and Electrical Engineering Heriot-Watt University Riccarton Edinburgh EH14 4AS United Kingdom

Current generation unmanned underwater vehicles, equipped with robotic manipulators, are teleoperated and consequently place a large workload burden on the human operator. A greater degree of automation could improve the efficiency and accuracy with which underwater tasks are carried out. These tasks can involve manipulator motion that is both unconstrained and/or constrained. For unconstrained motion, where a trajectory requires following, a prerequisite is good joint angle control. An adaptive self-tuning pole-placement controller is used for joint angle control. Practical results show the benefits compared to conventional fixed-gain control. For constrained motion, often simultaneous control of position and force is required. An adaptive hybrid position/force controller is proposed and compared to a fixed-gain version. Simulation and practical results illustrate the merits and drawbacks of each scheme.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Regularization and validation of neural network models of nonlinear systems

引用

e & i Elektrotechnik und Informationstechnik 2000年第1期117卷 24-31页

作者： I. Petrović M. Baotić N. Perić Faculty of Electrical Engineering and Computing Department of Control and Computer Engineering in Automation University of Zagreb Zagreb Croatia

A characteristic feature of the neural network models is the large number of parameters. A model offering many parameters usually gives rise to problems, and the variance contribution to the modeling error might be very high. Therefore, it is crucial to find the model with the optimal number of parameters. In this paper two techniques of selection of the optimal number of model parameters are described and compared: explicit and implicit regularization techniques. Model validation forms the final stage of an identification procedure with the aim of assessing objectively whether the identified model agrees sufficiently well with the observed data. In this paper the reliability of the correlation-based validation tests and the χ2-test is analyzed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Knowledge-Base Generating Fuzzy-Neural controller

引用

IFAC Proceedings Volumes 2000年第28期33卷 207-212页

作者： Ivan Petrović Kristijan Maček Nedjeljko Perić Department of Control and Computer Engineering in Automation Faculty of Electrical Engineering and Computing University of Zagreb Unska 3 10000 Zagreb Croatia

This paper presents a modification to the Kandadai and Tien’s learning algorithm for tuning a fuzzy-neural controller that is able to automatically generate a knowledge base. Tuning is based on reinforcements from a dynamical system, thus giving a pseudosupervised learning scheme using error backpropagation. Originally, a weak reinforcement in the form of a binary failure signal was assumed which proved to be insufficient in terms of steady-state error. Therefore, a continuous reinforcement signal is applied enabling the system to correct the error as well as decreasing the overall control effort in the learning phase.

关键词： expert systems intelligent control fuzzy logic neural networks

来源：评论

学校读者我要写书评

暂无评论

Pole Placement controller Design Based on Fuzzy Process Model

引用

IFAC Proceedings Volumes 2000年第28期33卷 219-224页

作者： Robert Cupec Nedjeljko Perić Ivan Petrović Department of Control and Computer Engineering in Automation Faculty of Electrical Engineering and Computing university of Zagreb Unska 3 10000 Zagreb Croatia

An explicit self-tuning controller based on the Takagi-Sugeno fuzzy model of the process is proposed. The fuzzy model is represented as a linear regression model whose parameters are functions of some of the process variables. Such a model can be considered as a linear time-varying model whose parameter values are known at every moment. The pole placement design procedure modified for time-varying systems is applied to obtain the polynomial controller parameters that provide the desired closed-loop poles. The proposed algorithm is very simple, and thus suitable for on-line controller design in adaptive control systems.

关键词： fuzzy control fuzzy modeling adaptive control

来源：评论

学校读者我要写书评

暂无评论

Model structure selection for nonlinear system identification using feedforward neural networks

Model structure selection for nonlinear system identificatio...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： I. Petrovic M. Baotic N. Peric Faculty of Electrical Engineering and Computing Department of Control and Computer Engineering in Automation University of Zagreb Zagreb Croatia

The majority of nonlinear models based on neural networks are of the black-box structure. A nonlinear system can be nonlinear in many different ways, thus the nonlinear black-box model structure must be very flexible. This means that it must have many parameters. A model offering many parameters usually creates problems, and the variance contribution to the error might be high. For a particular identification problem, only a subset of the parameters may be necessary, and the main topic in nonlinear system identification is how to select a model structure that describes the system dynamics with the minimum number of parameters. This paper discusses nonlinear input-output models that are suitable for implementation of feedforward neural networks. The proposed model structures were tested and compared using the identification procedure of a pH process. The results indicated that a simplest model structure can satisfactorily represent the investigated process.

关键词： Nonlinear systems Neural networks Feedforward neural networks Nonlinear dynamical systems control engineering computing Computer networks Predictive models Automatic control Nonlinear control systems Automation

来源：评论

学校读者我要写书评

暂无评论

Refinement of fuzzy production rules by neuro-fuzzy networks

Refinement of fuzzy production rules by neuro-fuzzy networks

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： E.C.C. Tsang Shenshan Qiu D.S. Yeung Department of Computing Hong Kong Polytechnic University Hong Kong China Department of Automatic Control Engineering South China University of Technology Guangzhou China

The knowledge acquisition bottleneck is well-known in the development of fuzzy knowledge based systems (i.e. FKBSs), and knowledge maintenance and refinement are important issues. The paper improves fuzzy production rule (FPR) representation power by exploiting prior knowledge and develops refinement tools which assist in debugging a FKBS's knowledge, thus easing the knowledge acquisition and maintenance bottlenecks. We focus on knowledge refinement where the FKBS's knowledge is debugged or updated in reaction to evidence that the FKBS is faulty or out-of-date. Some of the applied methods are presented. To select a feasible fuzzy rule set for classification, the most difficult task is finding a set of rules pertaining to the specific classification by choosing adaptive knowledge representation parameters such as local and global weights in fuzzy rules. We map the weighted fuzzy rules to a new neural network (five-layer-based knowledge neural network) so the knowledge representation parameters can be refined and fuzzy rule representation power can be improved. The dynamic assigning neuron method, gradient-descent method with penalizing functions and evolving strategy are considered. We show that this refinement method can maintain the accuracy and improve the comprehensibility and representation power of FPRs. Experiments on a special domain indicate that the refinement method and evolving strategy are able to significantly increase an FPR's representation power when compared with standard fuzzy knowledge-based networks.

关键词： Fuzzy neural networks Refining Production Knowledge acquisition Fuzzy sets Knowledge representation Neural networks Fuzzy systems Knowledge based systems Debugging

来源：评论

学校读者我要写书评

暂无评论

Convergence of discrete Hopfield-type neural networks with delay

Convergence of discrete Hopfield-type neural networks with d...

引用

American control Conference (ACC)

作者： Shenshan Qiu Yongqing Liu T.S. Dillon Renguo Xiao Department of computing Hong Kong Polytechnic University Hong Kong China Department of Automatic Control and Engineering South China University of Technology Guangzhou China

An important property of discrete Hopfield-type neural networks is that it always converges to a stable state when operating in a serial mode and to a cycle of length at most 2 when operating in a full parallel mode. In this paper, convergence theorems of discrete Hopfield-type neural networks with delay are obtained. Under a proper assumption, i.e., which weight matrix is a symmetric matrix, it is proved that any discrete Hopfield-type neural networks with delay will converge to a stable state operating in serial mode, and extends convergence theorems in earlier works. The authors also relate the maximum of bivariate energy function to the stable state of neural networks with delay. In other words, this network can converge to a stable state in only one delay step while the energy function has converged. The correlation between convergence of the energy function and convergence corresponding to the network is also presented.

关键词： Convergence Neural networks Hopfield neural networks Neurons Equations Delay effects Computer networks Computational modeling Sufficient conditions

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：