Computational & Technology Resources
an online resource for computational,
engineering & technology publications |
|
Civil-Comp Proceedings
ISSN 1759-3433 CCP: 35
DEVELOPMENTS IN ARTIFICIAL INTELLIGENCE FOR CIVIL AND STRUCTURAL ENGINEERING Edited by: B.H.V. Topping
Paper IX.1
COBDA: An Expert System for the Assessment of Deterioration of Concrete Bridges J.G. Cabrera*, K.S. Kim# and R. Dixon*
*Department of Civil Engineering, University of Leeds, Leeds, UK
J.G. Cabrera, K.S. Kim, R. Dixon, "COBDA: An Expert System for the Assessment of Deterioration of Concrete Bridges", in B.H.V. Topping, (Editor), "Developments in Artificial Intelligence for Civil and Structural Engineering", Civil-Comp Press, Edinburgh, UK, pp 151-157, 1995. doi:10.4203/ccp.35.9.1
Abstract
In recent years there has been growing concern regarding the
safety of existing concrete bridges due to deterioration mainly
caused by frequent use of de-icing salts and an increase in
highway bridge loading The problems of bridge assessment
and the requirements for repair, strengthening and
replacement are issues which have become increasingly
important, not only in the UK, but also In other countries
Concrete bridge engineers recommending implementation of
repair work are increasingly under severe time and budget
limitation Furthermore, the existing bridge assessment
methodologies present a considerable problem due to the
qualitative and subjective nature of the assessments which can
be inconsistent and lead to a fuzzy situation.
This paper describes and discusses the development of COBDA an expert system which includes three methods to deal with the uncertainty problems in the evaluation of concrete bridges The structure of the expert system IS given and the methodology for decision making for deteriorated concrete bridges is discussed. COBDA is configured by PROLOG for use In a personal computer It comprises 3 different methodologies Performance Index, Fuzzy logic and Bayesian subjective probability. purchase the full-text of this paper (price £20)
go to the previous paper |
|