Concrete Bridge Rating Expert System with Neuro-Fuzzy Hybrid System and its Application

Abstract

This article presents a new approach for developing a concrete bridge rating expert system for deteriorated concrete bridges, constructed from multi-layer neural networks with fuzzy logic in order to carry out fuzzy inference and machine learning. The system evaluates the performance of concrete bridges such as durability and load-carrying capability on the basis of a simple visual inspection and technical specifications. The main reason of applying the neural network is that it performs fuzzy inference in the network, facilitates refinement of the knowledge base by use of the Back-Propagation method, and prevents not only the inference mechanism of the expert system but also knowledge base after machine learning from becoming a black box. In this paper, comparisons between the diagnostic results of bridge experts and those of the proposed system are presented so as to demonstrate the validity of the system's learning capability. The training set for machine learning is obtained from inspection of actual in-service bridges and questionnaire surveys of bridge experts.