| Abstract: |
The origins of artificial intelligence, the most controversial andpromising field of computer science, can be traced back to the 1950s. In1956, at a Dartmouth Conference, John McCarthy coined the term”artificial intelligence” (AI). However, if one travels down the lane ofhistory, Stanford University stands out as the institution that triggered thisrevoiution. This field of computer science is concerned with designingintelligent computer systems[24].Expert systems (ES), a promising branch \of AI, has achievedconsiderable success in recent years. This area of AI has concentrated onthe construction of high- performance programs in specialized professionaldomains. The area of expert systems investigates methods and techniquesfor constructing man-machine systems with specialized problem solvingexpertise. Expertise consists of knowledge about a particular domain,understanding of domain problems, and skill at solving some of theseproblems. Knowledge in any specialty is usually of two sorts : Public andprivate. Public knowledge includes the published definitions, facts, andtheories of which textbooks and references in the domain of study aretypically composed. But expertise usually involves more than just thispublic knowledge. Human experts generally possess private knowledgethat has not found its way into the published literature. This privateknowledge consists largely of rules of thwnb that have come to be calledheuristics. Heuristics enable the human expert to make educated guesseswhen necessary, to recognize promising approaches to problems, and todeal effectively with errorful or incomplete data. Elucidating andreproducing such knowledge is the central task in building expertsystems [ 19].Expert systems are fmding their place in the field of water resourcesengineering with all the dangers of being oversold or missused. The rolesof water resources engineering have expanded beyond the traditionalconcepts of design and synthesis to a large multidisciplinary functionserving a broad social environment. Development, in time, of this fieldfollows three basic phases : (i) construction (emphasis on the design andconstruction); (ii) planning (emphasis on the examination of wider range ofalternatives); (iii) operation and maintenance (emphasis on the carefulmanagement of existing projects). This has created a pressing need for anoverall review of engineering education with the main accent on itsincreased multidisciplinary character, supported by the availableknowledge base and experience. Since their first introduction to the fieldof water resources in the early 1980’s, expert systems have been used indesign, planning and operation. The relative importance of expert systemsto impovements in water resources projects has not yet been established,but some practicial experience has already been documented[37].1-2 Objectives of the ThesisThe main objectives of this work can be summarized as follows:1- Describing the present state of artificial intelligence and expert systemsresearch and development.2- Investigating different ways to create expert systems.3- Analyzing its possible use in the field of water resources engineering.4- Examining several important advantages of knowledge - basedtechnology over classical procedural approach for water resources, engmeenng.5- Gaining some experience in structuring and representing knowledgefrom the water resources field.6- Designing and building a prototype expert system for irrigationmethods selection, The proposed expert system will help the noviceirrigation engineers in selecting the suitable irrigation methodscompatible with their requirements. The proposed expert system will beapplied to one or more case study to examine its validity,1-3 Thesis OrganizationThe thesis consists of seven chapters and three appendices whichcan be summarized as follows:Chapter 1 introduces a background on artificial intelligence andexpert systems, the main objectives of the thesis and the thesisorganization.Chapter 2 represents an introduction to the important issues of AIand ES. This chapter examines the following points: AI defmitions and
|
|
|