Particle Swarm Optimization Algorithm-Extreme Learning Machine (PSO-ELM) Model for Predicting Resilient Modulus of Stabilized Aggregate Bases

TLDR

Stabilized base/subbase materials provide greater structural support and durability than conventional materials, and resilient modulus (Mr) performance under wet‑dry cycles is essential for flexible pavement design. The study develops a Particle Swarm Optimization–based Extreme Learning Machine (PSO‑ELM) to predict the resilient modulus of stabilized aggregate bases subjected to wet‑dry cycles. The PSO‑ELM model was benchmarked against a PSO‑based Artificial Neural Network (PSO‑ANN) and a Kernel ELM (KELM) to evaluate its predictive performance. The PSO‑ELM achieved significantly lower RMSE and MAE and higher r² than PSO‑ANN and KELM, and its predicted Mr values followed the same distribution and trend as the observed data.

Abstract

Stabilized base/subbase materials provide more structural support and durability to both flexible and rigid pavements than conventional base/subbase materials. For the design of stabilized base/subbase layers in flexible pavements, good performance in terms of resilient modulus (Mr) under wet-dry cycle conditions is required. This study focuses on the development of a Particle Swarm Optimization-based Extreme Learning Machine (PSO-ELM) to predict the performance of stabilized aggregate bases subjected to wet-dry cycles. Furthermore, the performance of the developed PSO-ELM model was compared with the Particle Swarm Optimization-based Artificial Neural Network (PSO-ANN) and Kernel ELM (KELM). The results showed that the PSO-ELM model significantly yielded higher prediction accuracy in terms of the Root Mean Square Error (RMSE), the Mean Absolute Error (MAE), and the coefficient of determination (r2) compared with the other two investigated models, PSO-ANN and KELM. The PSO-ELM was unique in that the predicted Mr values generally yielded the same distribution and trend as the observed Mr data.