(Received 22 April 2008; accepted 10 November 2008)
Published Online: 2008
| ||Format||Pages||Price|| |
|PDF (312K)||10||$25||  ADD TO CART|
Cite this document
The prediction of the resilient modulus values of rubberized mixtures containing reclaimed asphalt pavement (RAP) materials involves a number of interacting factors or engineering parameters (variables) and is a very complex issue. Artificial neural networks (ANN) are useful tools in place of conventional physical models for analyzing complex relationships involving multiple variables and have been successfully used in many civil engineering applications. The objective of this study was to develop a series of ANN models to simulate the resilient modulus of rubberized mixtures (ambient and cryogenic rubbers) at 5, 25, and 40°C using seven input variables including material components such as rubber and RAP percentages as well as the rheological properties of modified binders (i.e., viscosity, G*sin δ, stiffness, and m-values). The sensitivity analysis and important index of each variable were performed in this study. The results indicated that ANN-based models are more effective than the regression models and can easily be implemented in a spreadsheet, thus making it easy to apply. In addition, the validation analysis of the models showed that ANN-based models might be used for other types of mixtures. Moreover, the results of the sensitivity analysis and important index of input variables in ANN models also indicated that the rheological properties of asphalt binders can be employed to predict the resilient modulus values effectively at various testing temperatures. The validation of the model also illustrates that the developed ANN can be used to predict the resilient modulus values from other research projects.
Research Assistant Professor, Department of Civil Engineering, Asphalt Rubber Technology Service (ARTS), Clemson University, Clemson, SC
Amirkhanian, Serji N.
Professor, Department of Civil Engineering, Clemson University, Clemson, SC
Stock #: JTE101834