Multiple Regression Model for Load Rating of Reinforced Concrete Bridges

This paper describes the development of a multiple regression model to estimate the load rating of reinforced concrete bridges. There are over 250,000 reinforced concrete bridges in the U.S. many of which do not have a load rating on record nor the plans required to perform the calculations. The U.S. Army owns and maintains hundreds of these bridges throughout the U.S. An exploratory data analysis of the 2017 National Bridge Inventory (NBI) data was performed for the selection of a representative data sample. The data required significant processing to extract a reliable sample for modeling. After processing, a data sample of 31,112 bridges remained, which provided a sufficient sample for model training and validation. A six-variable linear model that relates inventory rating to span length, deck width, year built, region, design load, and superstructure condition was determined to provide the best performance while maintaining a desired low level of complexity. The model had an adjusted R(2)of 0.514 and a standard error of 6.51 metric tons (7.17 tons). The model was validated against unseen data by comparing the percentage of cases that fell within its 95% prediction interval, which resulted in 94.9% of the real values falling within the prediction interval.