Prediction of Pavement Damage under Truck Platoons Utilizing a Combined Finite Element and Artificial Intelligence Model

Ramakrishnan, Aravind; Liu, Fangyu; Jayme, Angeli; Al-Qadi, Imad

Permalink

https://hdl.handle.net/2142/125178 Copy

Description

Title

Prediction of Pavement Damage under Truck Platoons Utilizing a Combined Finite Element and Artificial Intelligence Model

Author(s)

• Ramakrishnan, Aravind
• Liu, Fangyu
• Jayme, Angeli
• Al-Qadi, Imad

Issue Date

2024-12

Keyword(s)

• Rutting
• Pavement Damage
• Permanent Deformation
• Pavement Performance Modeling
• Asphalt Concrete
• Burger’s Model
• Flow-Number Test
• Connected and Autonomous Trucks
• Truck Platoons
• Rest Period
• Load-Pass Approach
• Pavement Model
• Graph Neural Networks
• Machine Learning

Abstract

For robust pavement design, accurate damage computation is essential, especially for loading scenarios such as truck platoons. Studies have developed a framework to compute pavement distresses as function of lateral position, spacing, and market-penetration level of truck platoons. The established framework uses a robust 3D pavement model, along with the AASHTOWare Mechanistic–Empirical Pavement Design Guidelines (MEPDG) transfer functions to compute pavement distresses. However, transfer functions include high variability and lack physical significance. Therefore, as an improvement to effectively predict permanent deformation, this study utilized a conventional Burger’s model, incorporating a nonlinear power-law dashpot, in lieu of a transfer function. Key components, including stress increments and the Jacobian, were derived for implementation in ABAQUS as a user subroutine. Model parameters were determined through asphalt concrete (AC) flow number and dynamic modulus tests. Using a nonlinear power-law dashpot, the model accurately characterized rutting under varying conditions. The Burger’s model was both verified and validated to check the accuracy of implementation and representative of the actual behavior, respectively. Initially developed in 1D domain, the validated Burger’s model was integrated into the robust 3D finite element (FE) pavement model to predict permanent deformation. A new load-pass approach (LPA) enabled reduction in computational domain and cost, along with implementing transient loads more efficiently. The combined integration of the LPA and the Burger’s model into the pavement model effectively captured the rutting progression per loading cycle. Moreover, a graph neural network (GNN) was established to extend the prediction power of the framework, while strategically limiting the FE numerical matrix. The FE model data was transformed into a graph structure, converting FE model components into corresponding graph nodes and edges. The GNN-based pavement simulator (GPS) was developed to model 3D pavement responses, integrating three key components: encoder, processor, and decoder. The GPS model employed two-layer multilayer perceptrons (MLP) for the encoder and decoder, while utilizing graph network (GN) technology for the processor. Validation occurred through two case studies—OneStep and Rollout—with results compared against FE model data as ground truth. Results demonstrated that the GPS model provides an accurate and computationally efficient alternative to traditional 3D pavement FE simulations.

Publisher

Illinois Center for Transportation/Center for Connected and Automated Transportation

Has Part

https://doi.org/10.36501/0197-9191/24-030

Series/Report Name or Number

ICT-24-030

Type of Resource

text

Language

eng

Sponsor(s)/Grant Number(s)

Grant No. 69A3552348301

Copyright and License Information

No restrictions. This document is available through the National Technical Information Service, Springfield, VA 22161.

Owning Collections