USING DATA MINING TO EXPLORE THE DETERIORATION FACTORS OF REINFORCED CONCRETE (RC) HIGHWAY BRIDGES IN TAIWAN

摘要

Information about the factors that lead to the deterioration of bridges is essential for bridge maintenance. Pinpointing what these factors are will certainly enhance the effectiveness of bridge management. However, a review of the literature reveals that such deterioration factors are usually determined from expert opinion. In other words, there is no systematic way to identify the factors and the effect they have on different types of bridge members. This study identifies six common types of deterioration that affect RC bridge decks. Twenty-nine factors are extracted from a review of past related work as well as from the inventory of Taiwan Bridge Management System. After this, a data mining technique, Rough Set Theory (RST), is employed to find the factors that have the greatest impact on deterioration from thousands of visual inspection, traffic and environmental data. It is found that weather-related factors are rather significant for almost all types of deterioration. In addition to these, some functional and structural factors are major factors for cracking and traffic volume is a major factor in rebar corrosion and breakage.