This thesis describes the development of a knowledge based system which encapsulates some of the expertise used by a number of experienced construction planners for planning the construction stage of low rise house building projects in the U.K. The general objective of the research was to investigate the feasibility of using knowledge engineering for developing models of construction planning expertise, which could be employed for tackling some of the existing knowledge bottlenecks in the construction industry. The resulting system can be described as a knowledge based framework designed for supporting the decision making process involved in planning house building at a tactical level. One of the main features of this framework is its ability to cope with incomplete information. The knowledge acquisition process involved both the elicitation of knowledge directly from experts, and the analysis of construction plans from several past housing developments. The model was implemented on an expert system shell called LEONARDO Level 3, which runs in any standard IBM-PC micro-computer or compatibles. The evaluation of the system focused on the validity of the model, i.e. the degree at which the outcomes of the system resembled the outcomes of the human expertise being modelled in the knowledge base. A prescriptive method of validation was devised specifically for this study, involving both experts that had provided expertise for the system, and external experts.
Identifer | oai:union.ndltd.org:IBICT/oai:lume.ufrgs.br:10183/18667 |
Date | January 1991 |
Creators | Formoso, Carlos Torres |
Contributors | University of Salford, Não informado |
Source Sets | IBICT Brazilian ETDs |
Language | English |
Detected Language | English |
Type | info:eu-repo/semantics/publishedVersion, info:eu-repo/semantics/doctoralThesis |
Format | application/pdf |
Source | reponame:Biblioteca Digital de Teses e Dissertações da UFRGS, instname:Universidade Federal do Rio Grande do Sul, instacron:UFRGS |
Rights | info:eu-repo/semantics/openAccess |
Page generated in 0.002 seconds