| description abstract | Infrastructure management decisions, such as condition assessment, performance prediction, needs analysis, prioritization, and optimization are often based on data that is uncertain, ambiguous, and incomplete and incorporate engineering judgment and expert opinion. Soft computing techniques are particularly appropriate to support these types of decisions because these techniques are very efficient at handling imprecise, uncertain, ambiguous, incomplete, and subjective data. This paper presents a review of the application of soft computing techniques in infrastructure management. The three most used soft computing constituents, artificial neural networks, fuzzy systems, and genetic algorithms, are reviewed, and the most promising techniques for the different infrastructure management functions are identified. Based on the applications reviewed, it can be concluded that soft computing techniques provide appealing alternatives for supporting many infrastructure management functions. Although the soft computing constituents have several advantages when used individually, the development of practical and efficient intelligent tools is expected to require a synergistic integration of complementary techniques into hybrid models. | |
