Date of Award
Doctor of Philosophy
Civil, Construction, and Environmental Engineering
Pavement management systems (PMS) play a significant role in cost-effective management of highway networks to optimize pavement performance over predicted service life of the pavements. Successful PMS implementation requires accurate performance prediction modeling to plan future maintenance and rehabilitation strategies.
The Iowa DOT manages three primary highway systems (i.e., Interstate, US, and Iowa highways) that represent 8% (approximately 9,000 miles) of the total roadway system in the state (114,000 miles), but these systems carry around 62% of the total vehicle miles traveled (VMT) and 92% of the total large truck VMT (ASCE, 2015). These highways play a major role in Iowa’s economy because highways are important to several sectors (e.g., agriculture, manufacturing, and industry). According to the Bureau of Transportation Statistics, in 2012 around 263.36 billion tons of goods valued at $195.99 billion were transported on Iowa highways (BTS, 2012). PMSs that use robust pavement prediction models are needed to ensure continued optimum performance of Iowa highways. In the past, these models were developed from historical information about pavement condition data.
In this research, historical climate data was acquired from the Iowa Environmental Mesonet and integrated with pavement condition data to include all related variables in prediction modeling. An artificial neural network (ANN) model was used to predict the performance of ride, cracking, rutting, and faulting indices on different pavement types. The goodness of fit of the ANN prediction models was compared with multiple linear regression (MLR) models. The results show that ANN models were more accurate in predicting future conditions than MLR models. The contribution of input variables in prediction models were also determined and discussed.
The results indicated that weather factors directly influence highway pavement conditions, and that ANN model results can be used by decision makers and maintenance engineers to determine proper treatment actions and pavement designs to withstand harsh weather over the years. An ANN model that was used to estimate the correlation between the rutting depth and structural capacity of asphalt pavements suggests that rutting depth can be an indicator of structural capacity. As such, an ANN approach might be feasible for small transportation agencies (e.g., cities and counties) that cannot afford to collect structural information.
Alharbi, Fawaz, "Predicting pavement performance utilizing artificial neural network (ANN) models" (2018). Graduate Theses and Dissertations. 16703.