摘要:

Artificial intelligence is well over 30 years old. The paper reviews its development, with particular reference to the discovery of engineering principles within this field, and its relevance to the engineering of new systems.

DOI:10.1049/ip-d.1987.0037

出版商:IEE    

年代:1987

数据来源: IET

摘要:

The paper attempts a review of present knowledge-representation practices, with particular reference to the construction of expert systems. The principal techniques are described and illustrated, together with some indications of their strengths and weaknesses. A number of knowledge-representation tools which employ these techniques are then outlined.

DOI:10.1049/ip-d.1987.0038

出版商:IEE    

年代:1987

数据来源: IET

摘要:

Handling of uncertainty of various kinds is one of the key issues in expert systems. The first generation of expert systems have addressed this issue in a variety of imaginative ways. However, all these techniques have theoretical deficiencies which have been commented on in the literature. The literature also contains other innovative ideas on how this problem may be tackled. It is clear that the problem itself is very complex and does not appear to be capable of any general solution. The paper surveys the literature on reasoning with uncertain information and, in the course of doing so, articulates some of the underlying questions.

DOI:10.1049/ip-d.1987.0039

出版商:IEE    

年代:1987

数据来源: IET

摘要:

Artificial intelligence has progressed a long way from the early days of rule-based expert systems. For building diagnosis and machine health monitoring systems, there are many very powerful techniques available. The most important of which are qualitative reasoning, qualitative simulation and the use of deep models. Recently, online expert systems, that is systems which are permanently coupled to their test and measurement systems, are becoming increasingly important. In the paper the author examines several of the fundamental techniques which are employed in systems such as these today.

DOI:10.1049/ip-d.1987.0040

出版商:IEE    

年代:1987

数据来源: IET

摘要:

The role of knowledge in the modelling of complex dynamic systems is examined. It is proposed that the type of knowledge to be used should be determined by the task to be undertaken, and that the qualitative methods emerging from knowledge-based systems work complement the traditional analytic modelling techniques. The combination of these methods allows the formation of an abstraction hierarchy that provides a robust architecture for multilevel problem solving.

DOI:10.1049/ip-d.1987.0041

出版商:IEE    

年代:1987

数据来源: IET

摘要:

The paper demonstrates how AI and fuzzy logic techniques can be combined to implement real-time, regulatory and servo control of a simple process unit. The knowledge base for the regulatory controller was designed to provide smooth control near the set point, ‘typical’ feedback control in the intermediate region and as much control as necessary (available) to prevent the controlled variable from exceeding user-specified constraints. The servo controller implemented fast open-loop set-point changes by using two-level bang-bang control, and the knowledge base included rules to learn the switching parameters online. The controllers were implemented, in Prolog, on an IBM PC and interfaced to an actual process using an industrial PID controller as an interface. Experimental results showed that control performance met the objectives better than a conventional fixed-gain PID controller.

DOI:10.1049/ip-d.1987.0042

出版商:IEE    

年代:1987

数据来源: IET

摘要:

The emergence of expert system technology has made possible the capture of the control engineer's knowledge of tuning problems and the building of expert tuners for PI controllers. In the paper, the architecturally relevant issues which arise in the development of expert tuners for PI controllers are discussed, and the technical issues of representing the appropriate knowledge and using it effectively are addressed.

DOI:10.1049/ip-d.1987.0043

出版商:IEE    

年代:1987

数据来源: IET

摘要:

In the paper the authors describe two tools for use in an intelligent fault-detection system. The first tool is a method for fault localisation, called constraint suspension, which helps us find and identify the parts suspension, which helps us find and identify the parts of the process which are responsible for any inconsistencies in the measurements. The second tool gives us a flexible framework in which we can build a software model of the process in terms of hierarchies of component parts or objects, it is called object orientation. We use these tools to describe algorithms for automatic fault detection in a physical process plant. The algorithms are tested on a simulation of a liquid level control system.

DOI:10.1049/ip-d.1987.0044

出版商:IEE    

年代:1987

数据来源: IET

摘要:

Many applications of artificial intelligence to practical problems in industry require systems that run continuously and in real time. The paper describes our experiences from developing a number of such systems in the domains of air defence, ship positioning and online monitoring and diagnosis. The problems that arose in these systems were due to the inherent dynamism, time and space limitations on the processing possible, uncertainty over the current state of the world, resource limitations and several others. The characteristics of these problems are described in the paper along with their implications for choosing suitable AI techniques. A common theme in the applications we have studied is the loop of plan generation, monitoring, diagnosis and replanning; examples of how these processes can be performed are given and some of the possible pitfalls indicated. No claims are made for a universal panacea for the problems in these difficult domains, but techniques which have proved useful are given. The paper does not aim to be a complete dissertation on the subject of real-time AI systems but should provide a usable introduction.

DOI:10.1049/ip-d.1987.0045

出版商:IEE    

年代:1987

数据来源: IET

摘要:

Discrete-event digital simulation modelling is an important and increasingly used technique for analysing and solving complex problems in business, industry and the public service. Computer-aided systems are under development to improve the efficiency of what is currently an expensive time-consuming process. In particular, problem formulation is slow and inexact, an art which improves with experience. Artificial-intelligence aids have been developed to help the analyst in collaboration with the decision maker to solve the problem. The first attempts were based on expert systems. Limitations with these systems led to the development of a natural language understanding system. The way in which the natural language understanding system undertakes the task of aiding problem formulation is described, as well as the structure of the system itself. The role that such a system plays in the overall modelling process is described, with emphasis on limitations of the current system and how these might be overcome in future developments.

DOI:10.1049/ip-d.1987.0046

出版商:IEE    

年代:1987

数据来源: IET