Backcalculation of Rigid Pavement Layer Parameters Using Artificial Neural Networks


The objective of this research study was to develop artificial neural network (ANN)-based models for nondestructively assessing the condition of the concrete (rigid) pavement systems. The backcalculated layer properties consisted of concrete pavement layer modulus (EPCC), coefficient of subgrade reaction (ks), and radius of relative stiffness (1) for rigid pavements. The input parameters used in the analyses are the Falling Weight Deflectometer (FWD) deflection basin data and the thickness of the concrete pavement layer (hPCC). The effect of the load transfer efficiency (LTE) on the interior loading deflections was also investigated in this study and the results were summarized. In order to develop ANN-based backcalculation models for rigid pavement systems, ISLAB2000 finite element (FE) model solutions were utilized to generate the synthetic database using some 7,800 runs. The ISLAB2000 solutions and ANN model predictions showed excellent agreement with each other. Based on the results of the analysis, the developed ANN models have significant potential to predict the concrete pavement layer modulus, coefficient of subgrade reaction, and radius of relative stiffness with high accuracy.

  • Abstract
  • Introduction
  • Generating ISLAB2000 Finite Element Solution Database
  • Load Transfer Efficiency (LTE) Sensitivity Study
  • Artificial Neural Network (ANNS) as Pavement Analysis Tools
  • Results
  • Conclusions
  • References

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In