检索结果-内蒙古大学图书馆

A Force Control Method Using the Relative Motion between the Manipulator and a Workpiece

IFAC Proceedings Volumes 1993年第2期26卷 461-464页

作者： K. Watanabe T. Fukuda S.G. Tzafestas Department of Mechanical Engineering Faculty of Science and Engineering Saga University Honjomachi-1 Saga 840 Japan Department of Mechano-Informatics and Systems Faculty of Engineering Nagoya University Furocho Nagoya 464-1 Japan Intelligent Robotics and Control Unit Computer Science Division National Technical University of Athens Zografou Athens 157 73 Greece

Control methods based on using the relative motion between the manipulator and the workpiece are described for controlling the force of a one-dimensional manipulator, in which it is assumed that there are no collisions between the manipulator and the workpiece and we use a computed force law which is similar to the computed torque law in the trajectory tracking problem of a manipulator. We consider two cases depending on whether the position and velocity of the workpiece (or end-effector) are available or not to calculate the computed force control. The effectiveness of the proposed control methods is illustrated by some computer simulations.

关键词： PID control contact motion force control robots manipulator servomechanisms

来源：评论

学校读者我要写书评

暂无评论

NAVAL SURFACE COMBATANT SHIP DESIGNERS AID

引用

NAVAL ENGINEERS JOURNAL 1993年第3期105卷 70-77页

作者： ANDERT, EP The Author:has over 14 years' experience in computer systems development and analysis including naval applications intelligent systems parallel processing signal processing and real-time systems. As vice president of Conceptual Software Systems Inc. he leads software development activities. He is the principal investigator on the development of an automated ship designer's aid automated naval ship producibility tools parallel processing software tools computer-aided software engineering tools and neural networks for sensor data processing. Previously Mr. Andert worked on a data analysis expert system for naval missile tracking the FAA air-traffic control system satellite sensor data processing and the SQS-53 sonar beam-former. Mr. Andert received a B.A. degree and an M.S. in computer science from California State University Fullerton. He has published more than 15 articles on computing in various technical journals books and proceedings.

The naval surface combatant ship design process can be greatly enhanced by a computerized, knowledge-based designer's aid. Naval surface ship design is a technological challenge to maximize ordnance on target which requires the use of rapidly advancing techniques and systems for surveillance, detection, communication, information processing, ordnance deliverv, and propulsion, among others. This paper discusses the first step in the development of a computerized, knowledge-based (expert svstem) tool to assist ship designers in selecting requirements and incorporating the most appropriate combat svstems and certain hull, machinery and electrical system (HM&E) equipment. This Naval Surface Combatant Ship Designer's Aid (NAVSURF) svstem allows the designer to select the type of ship to be developed and required ship characteristics such as speed. It then suggests a set of requirements for the ship along with a set of combat and HM&E equipment based on the selected requirements. The NAVSURF svstem is an interactive environment that suggests requirements and equipment while allowing the user to select alternatives, ask for reports of selected items, upgrade the databases of available requirements, and upgrade the knowledge-base that makes suggestions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Self learning process control systems by neural networks

Self learning process control systems by neural networks

引用

IEEE Conference on Decision and Control

作者： M. Khalid S. Omatu R. Yusof Department of Information Science and Intelligent Systems Faculty of Engineering University of Tokushima Tokushima Japan

The authors discuss the development of a backpropagation neural network control scheme with application to two kinds of processes: a water bath and a multi-input multi-output furnace. The scheme can be easily implemented to solve two different control problems using only the input-output characteristics of the plants without the need for any initial conventional controller or knowledge regarding dynamics. The neurocontrol schemes developed on the two processes have been compared to self-tuning control and conventional digital-PID (proportional plus integral plus derivative) control schemes. Several experiments have been conducted to show the reliability of the neurocontrol scheme. The experimental results also show that the neural-network-based processes are superior and robust. Drawbacks in the neuro-control scheme are the requirement for prior training and the need for a judicious selection of the neural network models.< >

关键词： Process control Neural networks PD control Pi control Proportional control Backpropagation Furnaces Digital control Robustness

来源：评论

学校读者我要写书评

暂无评论

Abnormal convergence of numerical solutions and Runge‐Kutta‐type methods admitting no such phonemenon

引用

Electronics and Communications in Japan (Part III: Fundamental Electronic science) 1992年第3期75卷 84-91页

作者： Maeda, Shigeru Department of Information Science and Intelligent Systems Faculty of Engineering Tokushima University Tokushima 770 Japan

When the standard Runge‐Kutta method is applied to a certain system of linear differential equations, the numerical solution converges to the origin but the true solution diverges to infinity. This phenomenon is named the abnormal convergence of numerical solutions. Abnormal convergence has not been studied fully;however, many concepts involving A‐stability have been established to treat the phenomenon that the numerical solution diverges even though the true one converges, as is apt to occur in integration of a stiff system. An example will be illustrated here in which the standard Runge‐Kutta method generates abnormal convergence. Further, it will be proved that the abnormality is caused by the existence of an intersection of the absolute stability region and the right‐half plane. Even if the 1/8 formula method is used instead of the standard one, the same phenomenon can be seen because all four‐stage, fourth‐order, explicit Runge‐Kutta methods have the unique absolute stability region. This paper seeks for Runge‐Kutta methods that are A‐stable and never generate abnormal convergence, even though this might be an excessive requirement. Concretely, two types of methods will be proposed whose absolute stability region coincides with the left‐half plane. Furthermore, it will be reported that Gauss‐Legendre methods are typical ones. Copyright © 1992 Wiley Periodicals, Inc., A Wiley Company

关键词： abnormal convergence A‐stability Differential equations numerical methods Runge‐Kutta method

来源：评论

学校读者我要写书评

暂无评论

Performance of Generated Moments by Neural Network to Recognise Invariant Image Representation

Performance of Generated Moments by Neural Network to Recogn...

引用

IJCNN International Joint Conference on Neural Networks

作者： P.Raveendran Sigeru Omatu Wong Wing Yue Engineering Faculty University of Malaya Kuala Lumpur 59100 Malaysia Dept. of Information Science and Intelligent Systems University of Tokushima Tokushima 770 Japan

In this paper we explore the possibility of using moment invariant features in the presence of *** of the conventional technique of computing the moment invariant features,we use a dual neural net,the first as a feature extractor trained to generate the second and third order *** generated moments were used as inputs to the second neural net,which functions as a classifier. To measure the effectiveness of using the above scheme we compared it with a single neural network and two statistical classifiers to classify the images of numerals of 32×32 matrix which have been translated,scaled and rotated and perturbed with *** statistical classifiers used are nearest-neighbour and mininum-mean-distance. Back-propagation learning algorithm is used in the training of neural *** as well as noisy images are used in the training of neural *** is found that dual neural net performs much better than the single neural net and the statistical classifiers in the presence of noise.

关键词： image net Performance of Generated Moments by Neural Network to Recognise Invariant Image Representation

来源：评论

学校读者我要写书评

暂无评论

A NEW BACK-PROPAGATION ALGORITHM WITH COUPLED NEURON

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1991年第5期2卷 535-538页

作者： FUKUMI, M OMATU, S Department of Information Science and Intelligent Systems Faculty of Engineering University of Tokushima Tokushima Japan

In this letter a new neuron model and its learning algorithm are presented. They provide a new approach for speeding up convergence in the learning of layered neural networks and for training networks of neurons with a nondifferentiable output function by using the gradient descent method. The neuron is called a saturating linear coupled neuron (sl-CONE). From simulation results, it is shown that the sl-CONE has a high convergence rate in learning compared with the conventional back-propagation algorithm.

关键词： Neurons Neural networks Convergence Artificial neural networks Multi-layer neural network Pattern recognition Character recognition Feedforward neural networks Learning systems Optimization methods

来源：评论

学校读者我要写书评

暂无评论

A neural network based control scheme with an adaptive neural model reference structure

A neural network based control scheme with an adaptive neura...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： M. Khalid S. Omatu Department of Information Science and Intelligent Systems Faculty of Engineering University of Tokushima Japan

A neural network based control scheme with an adaptive neural model reference structure is described. A neural net emulator is first trained to model the plant's behavior. The neural net controller is next trained to learn the plant's inverse dynamics by backpropagating the error at the output of the plant through the emulator. The proposed structure of this method allows both the neural network controller and emulator to be continuously trained online. Simulation results to control a nonlinear temperature control process showed that the proposed neural network control method is easily implemented for a wide variety of control problems.< >

关键词： Neural networks Programmable control Adaptive control Control systems Artificial neural networks Temperature control Backpropagation Error correction Mathematical analysis Multi-layer neural network

来源：评论

学校读者我要写书评

暂无评论

Pattern classification for remote sensing using neural network

Pattern classification for remote sensing using neural netwo...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： S. Omatu T. Yosida Department of Information Science and Intelligent Systems Faculty of Engineering University of Tokushima Japan

The authors propose a pattern classification method for remote sensing data based on neural network theory. From geographical knowledge and Kohonen's self-organization feature maps, training areas for each pattern are selected. Using the backpropagation algorithm, a layered neural network is trained such that the training patterns can be classified within a level. After training the network, some pixels are omitted from the training areas if they are incorrectly classified and new training ones are determined. Once training is complete, remote sensing data are applied to the trained neural network. Experiments on Landsat TM (Thematic Mapper) data show that this approach produces excellent classification results which are more realistic and noiseless compared with the conventional Bayesian approach.< >

关键词： Pattern classification Remote sensing Neural networks Biological neural networks Bayesian methods Satellites Military computing Statistical analysis Error probability data analysis

来源：评论

学校读者我要写书评

暂无评论

Control of real-time processes using back-propagation neural networks

Control of real-time processes using back-propagation neural...

引用

International Conference on Industrial Electronics, Control and Instrumentation

作者： M. Khalid S. Omatu Department of Information Science and Intelligent Systems Faculty of Engineering University of Tokushima Tokushima Japan

The authors discuss the use of appropriately trained back-propagation neural networks as physical controllers similar to conventional feedforward controllers in real-time control systems. Experiments were concluded on two process models; one was a single-input single-output water bath process, and the other a multi-input multi-output nonlinear furnace. By obtaining a set of a plant's input-output patterns, the neural networks were trained to learn their inverse dynamics and then were configured as feedforward controllers to the plants. The results show that the neural network controllers perform well. The applicability of other types of neural network control schemes is discussed.< >

关键词： Process control Neural networks Control systems Optimal control Artificial neural networks Adaptive control Temperature control Programmable control systems engineering and theory Backpropagation

来源：评论

学校读者我要写书评

暂无评论

Application of generalised predictive control to a temperature control process

Application of generalised predictive control to a temperatu...

引用

International Conference on Industrial Electronics, Control and Instrumentation

作者： R. Yusof S. Omatu Department of Information Science and Intelligent Systems Faculty of Engineering University of Tokushima Tokushima Japan

The authors describe the application of the generalized predictive control (GPC) algorithm to control the temperature of a microcomputer-controlled water bath system. They highlight the ability of the algorithm to cope with the variation of the process dead time through some simulations and experimental results. They also investigate the effect of changing the design parameters of GPC for this system. Verification of the effectiveness of the algorithm is concluded through comparisons made with a self-tuning controller proposed by D.W. Clarke and P.J. Gawthrop (1975, 1979). The present investigation of the capability of the GPC to control the temperature of the water bath proves that the GPC algorithm can produce a good closed-loop response for this process and is also robust enough for processes with variable time delay. It is also shown that the design parameters of GPC are very flexible and easy to choose because they are integers.< >

关键词： Predictive control Temperature control Control systems Process control Adaptive control Robust control Open loop systems Algorithm design and analysis Industrial control Programmable control

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：