Original scientific paper
https://doi.org/10.30765/er.2464
Modeling of creep compliance and creep modulus behavior in modified asphalt mixes using Artificial Neural Networks (ANN) and Adaptive Neuro-Fuzzy Inference Systems (ANFIS)
Lyacia Sadoudi
; Faculty of Civil Engineering, University of Sciences and Techology Houari Boumediene, BP 32 El Alia Bab Ezzouar Algiers, Algeria
*
Mohammed Amin Benbouras
; Faculty of Civil Engineering, University of Sciences and Techology Houari Boumediene, BP 32 El Alia Bab Ezzouar Algiers, Algeria
Ratiba Mitiche-Kettab
; Department of Civil Engineering, Ecole Nationale Polytechnique d’Alger, Algeria
* Corresponding author.
Abstract
This study investigates the impact of rubber on the creep compliance and creep modulus of asphalt mixtures, aiming to enhance their mechanical performance and promote environmental sustainability. Rubber was incorporated into the asphalt mixture using the dry process. Asphalt samples were prepared using different content of rubber both the gyratory compactor and the Marshall Method and tested at different temperatures. The results showed that adding a low percentage of rubber (0.25%) improved creep modulus and reduced deformation, while higher percentages led to decreased performance. Additionally, the study utilized advanced machine learning techniques, including Artificial Neural Networks (ANN) and Adaptive Neuro-Fuzzy Inference Systems (ANFIS), to model creep modulus and creep compliance. The ANFIS model demonstrated superior performance in predicting these properties compared to the ANN model. The findings of this research provide valuable insights into the influence of rubber on the creep behavior of asphalt mixtures and offer a robust framework for predicting their performance using machine learning techniques.
Keywords
asphalt; creep properties; artificial neural network (ANN); adaptive neuro-fuzzy inference system (ANFIS)
Hrčak ID:
341327
URI
Publication date:
9.10.2025.
Visits: 328 *