0
Non-Linear Inverse Analysis of Transportation Structures Using Neuro-Adaptive Networks with Hybrid Learning Algorithm

Excerpt

The load-bearing capacity of pavement structures is a fundamental structural performance metric of transportation infrastructure networks in the context of safe and efficient movement of people and goods from one place to another. Non-destructive test (NDT) methods are typically employed to routinely evaluate the structural condition of pavement structures, their lifespan and the appropriate maintenance activities to be carried out. This involves computing the Young's modulus of each layer of the pavement structure through inverse analysis of acquired NDT data. Over the past two decades, soft computing techniques such as Artificial Neural Networks (ANNs), Genetic Algorithms (GAs), and Fuzzy Logic Approach (FLA) have been applied in numerous civil engineering fields for pattern recognition, function approximation, etc. This paper proposes the use of an Adaptive-Network-based Fuzzy Inference System (ANFIS) combined with Finite Element Modeling (FEM) for inverse analysis of multi-layered flexible pavement structures subjected to dynamic loading. Using the proposed approach, it will be possible for pavement engineers to characterize the non-linear, stress-dependent modulus of the pavement layers based on the NDT data in real time, identify the pavement defects, and better determine the appropriate rehabilitation strategy.

  • Abstract
  • Introduction
  • FWD Testing and Inverse Analysis of Pavement Systems
  • Adaptive-Network-Based Fuzzy Inference System (ANFIS) Methodology
  • ANFIS Based Approach to Pavement Structural Evaluation
  • Summary and 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