Concrete bridge deterioration diagnosis using fuzzy inference system

Abstract

Bridge management systems (BMSs) are being developed in recent years to assist various authorities on the decision making in various stages of bridge maintenance, which requires, first of all, appropriate preliminary deterioration diagnosis and modeling. This paper presents a knowledge-based system for bridge damage diagnosis that aims to provide bridge designers with valuable information about the impacts of design factors on bridge deterioration. The validity of the influence parameters is verified by the principal component analysis (PCA). Fuzzy logic is utilized to handle uncertainties and imprecision involved, and a modified mountain clustering method (MMM) is employed for knowledge acquisition. The generated rule base is further optimized by the descent method (DM). Illustrative examples indicate that the techniques of the MMM, the PCA and the DM are reliable and efficient tools in generating diagnosis rules and in developing inference systems.