Computational & Technology Resources
an online resource for computational,
engineering & technology publications
PROCEEDINGS OF THE SIXTH INTERNATIONAL CONFERENCE ON THE APPLICATION OF ARTIFICIAL INTELLIGENCE TO CIVIL AND STRUCTURAL ENGINEERING
Edited by: B.H.V. Topping and B. Kumar
Using Fuzzy Set Theory (FST) in Selecting a Suitable Foundation Type
H.K. Amin+, K.M. El Zahaby+, M.A. Taha* and A.S. Bazaraa*
+Housing and Building Research Center, Cairo, Egypt
H.K. Amin, K.M. El Zahaby, M.A. Taha, A.S. Bazaraa, "Using Fuzzy Set Theory (FST) in Selecting a Suitable Foundation Type", in B.H.V. Topping, B. Kumar, (Editors), "Proceedings of the Sixth International Conference on the Application of Artificial Intelligence to Civil and Structural Engineering", Civil-Comp Press, Stirlingshire, UK, Paper 6, 2001. doi:10.4203/ccp.74.6
Keywords: fuzzy, FST, pi-curve, defuzzification, fuzzy arithmetic, foundation, geotechnical.
In this paper, fuzzy set analysis is used as a tool to find a suitable foundation type for a given site with known characteristics.
Fuzzy set analysis is a relatively recent technique that generalizes the conventional crisp sets by making use of partial membership grades. This property enables FST to deal with qualitative rather than quantitative pieces of information. FST depends mainly on the experts' opinions that specify weights and membership grades for each of the variables selected to be used in the analysis. These weights are then applied to actual projects and results in fuzzy numbers for the different available choices. These numbers can then be defuzzified into crisp numbers where the highest crisp number represents the best choice for the studied case.
Fuzzy set theory is introduced through presenting the definitions of its basic concepts. Furthermore, the mathematical definitions of fuzzy arithmetic, as well as defuzzification, used in this paper, are explained. The -curve is used as a tool for the transforming the linguistic terms into fuzzy numbers.
A set of 23 fuzzy variables, covering 6 main subgroups is used in the current analysis. The selected subgroups consist of: structural identification, field information related to construction, soil characteristics, ground water table information, neighboring conditions, and site dependent variables.
A total of (84) projects have been collected from 6 major consulting offices in Egypt, and is gathered where sufficient information is available to test the proposed development using fuzzy variables to select a suitable foundation type. The projects are chosen in such a way to cover a variety of soil stratification as well as a significant number of projects possessing the selected foundation types.
An interactive, structured, FORTRAN computer program is prepared for the computation of fuzzy weighted average. The center of area (COA) method is used for the defuzzification of the obtained results.
A parametric study is performed to test the significance of each of the used fuzzy variables in addition to the fuzzy variable groups. The obtained results are logical and converts the weights originally assigned by the experts for the importance and the relative influence of each of the fuzzy variables used in this study. The obtained results are useful and can be easily utilized by geotechnical engineers to help them select a suitable foundation type.
purchase the full-text of this paper (price £20)