Application of Fuzzy Case-Based Reasoning to Bridge Management

Abstract

Case-based reasoning (CBR), one of the artificial intelligence (AI) learning approaches, is drawing the attention of many researchers in Civil Engineering. However, due to vagueness and uncertainties in knowledge representation, retrieval, and inference of cases in CBR, -- especially when dealing with similarity assessment -, it is difficult to find the cases in a case base which are exactly the same as the query case. Therefore, fuzzy theory h as been incorporated into CBR, which promises more robust, flexible, and accurate models. In this research, fuzzy case -based reasoning (FCBR) has been used to develop a model for bridge management. This model can deal with multiple objectives, namely, pr edicting the future health condition of a bridge deck, and recommending the appropriate maintenance, rehabilitation and replacement (MR&R) actions. The FCBR model’s learning capabilities have been validated using the cross-validation method. The code is implemented using the programming language C++, and all the cases used for both training and testing are extracted from the electronic bridge database of the Kansas Department of Transportation. In this paper, recommending MR&R actions, the second function of the developed bridge management model, is focused on.