Development of Enhanced Stress Prediction Models for Fixed Traffic Loads on Flexible Pavements Based on Response Surface Methodology (RSM) and Machine Learning (ML) Techniques

Pavement design is influenced by traffic load, which affects its lifespan. Traditional methods classify traffic load into fixed traffic, fixed vehicle, variable traffic, and vehicle/axle loads. In fixed traffic, pavement thickness is based on the maximum expected wheel load without considering load repetitions. Meanwhile, in fixed vehicle scenarios, it is calculated by the repetitions of a standard axle load. For nonstandard axle loads, the equivalent axle load is determined by multiplying repetitions by the corresponding equivalent load factor. In variable traffic, each axle and its repetitions are analyzed independently. This study proposes enhanced models for fixed traffic loads, focusing on single, dual, and tridem axles in a single-layer pavement model, to improve stress prediction accuracy. The results show that a quadratic model with a base-10 logarithmic transformation accurately predicts stresses. Additionally, machine learning models, especially Gradient Boosting, provided more accurate predictions than traditional models, with lower mean squared error (MSE) and root mean squared error (RMSE). The results show that these models are effective in predicting the stress in pavement. These findings provide valuable insights that can lead to better pavement design and more effective maintenance practices.