Bayesian optimization algorithm based support vector regression analysis for estimation of resilient modulus of crushed rock materials for pavement design

Abstract

The precise determination of the resilient modulus (MR) of the base and sub-base materials is a major preoccupation and a key criterion in the flexible pavement design process. The experimental determination of MR implies a challenging process which requires usually very difficult test procedures and extreme precautions and manpower. This is why soft computing techniques are increasingly popular and of growing importance. Many prediction techniques based primarily on linear and non-linear regression could not provide flexible use and consistent prediction of MR for practical engineering. This article introduces a hybrid of the Bayesian optimization algorithm (BOA) and support vector regression (SVR) as a new modelling tool for the MR prediction of crushed stone materials used as base and sub-base layers for pavement design. For this purpose, an experimental database was utilized to generate the hybrid BOA-SVR model of indirect estimation of the resilient modulus based on material type, basic engineering characteristics and loading conditions. The database consists of 260 experimental datasets obtained from repeated loading triaxial tests performed by the laboratory of the Central Transportation Agency located in Algiers, Algeria. To develop the model, all hyperparameters were optimised using the BOA technique. It was found that the average, median, standard deviation, minimum, maximum and interquartile range of the expected values of the developed hybrid model are very close to the experimental results. Results revealed that the hybrid BOA-SVR model predict the MR of the crushed stone materials with a coefficient of determination of 99.91% and root mean squared error of 3.55. Comparisons with traditional and other Artificial intelligence models showed that BOASVR hybrid model predictions are more accurate and robust than those of other models.