检索结果-内蒙古大学图书馆

AN AUTOSYNTHESIZING NONLINEAR control-SYSTEM USING A RULE-BASED EXPERT SYSTEM

INTERNATIONAL JOURNAL OF ADAPTIVE control AND SIGNAL PROCESSING 1991年第1期5卷 21-39页

作者： TAYLOR, JH STRINGER, PG GE CORP RES & DEV CONTROL SYST LABSCHENECTADYNY 12301

An advanced non-linear control system is obtained by combining recent developments in non-linear control system synthesis with a rule-based system approach to real-time control. The basic problem to be addressed is the control of a non-linear plant which is sufficiently sensitive to both operating point and input amplitude that the desired control system performance can be obtained only with a non-linear controller that is 'retuned' or 'resynthesized' whenever the operating point changes significantly. (The term 'changes significantly' in this context signifies an operating point change that causes the non-linear control system input/output behaviour to change substantially in an undesirable way.) This is accomplished by a hierarchically organized intelligent control system with a conventional reprogrammable controller under the direction of a rule-based expert system. The function of the expert system is to (i) monitor the behaviour of the non-linear control system to determine when retuning or resynthesis is required;if the behaviour is satisfactory, then continue passive monitoring;else (ii) when retuning or resynthesis is required: set up and execute experiments to derive the model information required to tune or synthesize a new non-linear controller in terms of a given structure and parameterization;execute the retuning/resynthesis procedure;reprogramme the controller (download the parametrization);and recommission the updated non-linear control system and return to normal operation. In essence, the rule-based system provides supervisory control ('meta-control') for a conventional reprogrammable non-linear controller that will autotune or autosynthesize as required. Autosynthesis takes place to accommodate variability in plant behaviour due to operating point changes, and the non-linear controller thus synthesized corrects for amplitude sensitivity. This concept represents one way to combine artificial intelligence with control;it will be discussed and illustr

关键词： ai in real-time control INTELLIGENT control EXPERT SYSTEMS FOR control HEURISTIC PROGRAMMING

来源：评论

学校读者我要写书评

暂无评论

Knowledge-based vision systems in real-time control

引用

Annual Review in Automatic Programming 1989年第PART 2期15卷 13-18页

作者： Rodd, M.G Wu, Q.M Institute for Industrial Information Technology Department of Electrical and Electronic Engineering University of Wales Swansea United Kingdom

This review paper takes a user-orientated view of knowledge-based computer vision systems - a viewpoint biased towards the practical applications of the technology as a component in a real-time control system. It investigates the characteristics of this area of application and defines the potential role of vision-based systems. On the basis of this, it reviews current progress in fulfilling these roles. It highlights critical areas - especially the need to recognise that the industrial environment requires solutions which can co-exist in those environments, and can react at speeds which are acceptable in the closed-loop control situation of which they form a part. It is argued that simply bringing together well-understood low-level processing systems and currently-available expert systems-based high-level processing, is bound to fail and indeed partially accounts for the many unsuccessful installations. In practice, a total systems-approach must be taken, recognising the realities of the application - including the still-unresolved problems relating to knowledge-acquisition. The paper concludes that low- and high-level processing must be integrated into highly flexible, explicit knowledge-based solutions to produce systems which are capable of fast, deterministic performance, but have inherent learning capabilities to cope with changing applications. © 1990.

关键词： ai in real-time control Artificial Intelligence in control Computer Vision Expert Systems Image Processing Knowledge-Based Computer Vision

来源：评论

学校读者我要写书评

暂无评论

Knowledge-based Computer Vision Systems for Industrial control

引用

IFAC Proceedings Volumes 1990年第8期23卷 153-158页

作者： M.G. Rodd F. Deravi Q.M. Wu J. Powrie Department of Electrical and Electronic Engineering University of Wales Swansea. UK

There is a host of industrial parameters which are not yet capable of being measured by conventional instruments. In many of these areas, computer vision has been suggested as a possible measurement technique, and indeed in certain applications, success has been achieved. However, because of the mathematical processing complexity and the vast amount of data which have to be handled, it has been found impossible in practice to develop an application orientated computer vision system which meets on-line criteria. This paper investigates the problem of advanced computer vision systems, which call heavily on extensive explicit and implicit knowledge of the task at hand. It discusses the use of these systems in industrial control, with particular emphasis on the task of completing "CIM control-loops", i.e. sitations where a camera-based system is is used to observe the products produced by a series of manufacturing tasks, and the information gleaned from the observations used to control that process. The paper has its roots in practical applications by the authors' group over the past two years, which has led to the development of industrial products which are capable of operating at line speeds, using some highly innovative architectures and original algorithsm. A specific example of such an application is briefly reviewed.

关键词： ai in real-time control Knowledge-Based Vision Systems Computer Vision Image Processing

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Based Vision Systems in real-time control

引用

IFAC Proceedings Volumes 1989年第13期22卷 13-18页

作者： M.G. Rodd Q.M. Wu Institute for Industrial Information Technology Department of Electrical & Electronic Engineering University of Wales Swansea UK

This review paper takes a user-orientated view of knowledge-based computer vision systems – a viewpoint biased towards the practical applications of the technology as a component in a real-time control system. It investigates the characteristics of this area of application and defines the potential role of vision-based systems. On the basis of this, it reviews current progress in fulfilling these roles. It highlights critical areas – especially the need to recognise that the industrial environment requires solutions which can co-exist in those environments, and can react at speeds which are acceptable in the closed-loop control situation of which they form a part. It is argued that simply bringing together well-understood low-level processing systems and currently-available expert systems-based high-level processing, is bound to fail and indeed partially accounts for the many unsuccessful installations. In practice, a total systems-approach must be taken, recognising the realities of the application – including the still-unresolved problems relating to knowledge-acquisition. The paper concludes that low- and high-level processing must be integrated into highly flexible, explicit knowledge-based solutions to produce systems which are capable of fast, deterministic performance, but have inherent learning capabilities to cope with changing applications.

关键词： Artificial Intelligence in control Expert Systems Computer Vision Knowledge-Based Computer Vision ai in real-time control Image Processing

来源：评论

学校读者我要写书评

暂无评论

Dynamic Scene Description System – ODYS

引用

IFAC Proceedings Volumes 1990年第8期23卷 159-164页

作者： J. Malec Institue of Technical Cybernetics Technical University of Wroclaw Wybrzeże Wypiańskiego 27 50370 Wroclaw Poland

In the paper a system for analysing and describing dynamic scene of a robot is presented. The system, called ODYS (Opis DYnamiczej Sceny robota), is able to analyse descript ions of consecutive frames of the robot's environment, and to form on this basis high level descriptions of perceived objects' behaviours. The process of forming the description (and prediding the object's behaviour) is based on const ruding frames called events and scenarios , which form a four level hierarchy of description specificity . Frames at each level describe respectively: all the changes that were recognized on the scene, changes considered according to some criterions as important, collections of simultaneously occurring changes, and series of changes linked with each other by the cause—effect relationship. Events and scenarios belonging to higher layer of description specificity form more general and more concise descriptions of the robot's scene than events and scenarios of the layer below. The system presented in the paper is coded in a dialect of COMMON LISP, and partially debugged and running.

关键词： ai in real-time control Knowledge Acquisition Knowledge Representation Autonomous Vehicle 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：