Utilizing Soft Computing Techniques to Estimate the Axial Permanent Deformation of Asphalt Concrete

Rutting is a crucial concern impacting asphalt concrete pavements’ stability and long-term performance, negatively affecting vehicle drivers’ comfort and safety. This research aims to evaluate the permanent deformation of pavement under different traffic and environmental conditions using an Artific...

Full description

Saved in:
Bibliographic Details
Published in:Applied system innovation Vol. 8; no. 2; p. 26
Main Authors: Albayati, Amjad H., Jweihan, Yazeed S., Al-Kheetan, Mazen J.
Format: Journal Article
Language:English
Published: Basel MDPI AG 01.04.2025
Subjects:
Aggregates
Artificial intelligence
Artificial neural networks
Asphalt
asphalt concrete
Asphalt pavements
Cement
Concrete mixing
Concrete pavements
Data points
Deformation
Design parameters
Independent variables
Load
Machine learning
Methods
Neural networks
Physical properties
Prediction models
Repeated loading
rutting
Sensitivity analysis
Shear tests
Soft computing
Specific gravity
Temperature
uniaxial load
Viscosity
Iraq
Baghdad Iraq
ISSN:2571-5577, 2571-5577
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Rutting is a crucial concern impacting asphalt concrete pavements’ stability and long-term performance, negatively affecting vehicle drivers’ comfort and safety. This research aims to evaluate the permanent deformation of pavement under different traffic and environmental conditions using an Artificial Neural Network (ANN) prediction model. The model was built based on the outcomes of an experimental uniaxial repeated loading test of 306 cylindrical specimens. Twelve independent variables representing the materials’ properties, mix design parameters, loading settings, and environmental conditions were implemented in the model, resulting in a total of 3214 data points. The network accomplished high prediction accuracy with an R2 of 0.93 and a mean squared error (MSE) of 0.0039. Results based on the sensitivity analysis and variable importance techniques showed that the percentage of aggregate passing the 4.75 mm sieve and the (rice) theoretical maximum specific gravity (Gmm) were the most significant factors in predicting axial permanent strain (εp). Furthermore, the connection weight method highlighted input variables’ distinct positive and negative impacts on permanent deformation.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2571-5577
2571-5577
DOI:10.3390/asi8020026