Machine Learning Approach to Develop a Novel Multi-Objective Optimization Method for Pavement Material Proportion
Open Access
- 17 January 2021
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 11 (2), 835
- https://doi.org/10.3390/app11020835
Abstract
Asphalt mixture proportion design is one of the most important steps in asphalt pavement design and application. This study proposes a novel multi-objective particle swarm optimization (MOPSO) algorithm employing the Gaussian process regression (GPR)-based machine learning (ML) method for multi-variable, multi-level optimization problems with multiple constraints. First, the GPR-based ML method is proposed to model the objective and constraint functions without the explicit relationships between variables and objectives. In the optimization step, the metaheuristic algorithm based on adaptive weight multi-objective particle swarm optimization (AWMOPSO) is used to achieve the global optimal solution, which is very efficient for the objectives and constraints without mathematical relationships. The results showed that the optimal GPR model could describe the relationship between variables and objectives well in terms of root-mean-square error (RMSE) and R2. After the optimization by the proposed GPR-AWMOPSO algorithm, the comprehensive pavement performances were enhanced in terms of the permanent deformation resistance at high temperature, crack resistance at low temperature as well as moisture stability. Therefore, the proposed GPR-AWMOPSO algorithm is the best option and efficient for maximizing the performances of composite modified asphalt mixture. The GPR-AWMOPSO algorithm has advantages of less computational time and fewer samples, higher accuracy, etc. over traditional laboratory-based experimental methods, which can serve as guidance for the proportion optimization design of asphalt pavement.Funding Information
- National Natural Science Foundation of China (51978309)
This publication has 53 references indexed in Scilit:
- Experimental Characterization of Viscoelastic Behaviors of Nano-TiO2/CaCO3 Modified Asphalt and Asphalt MixtureNanomaterials, 2021
- Influence of basalt fiber on mode I and II fracture properties of asphalt mixture at medium and low temperaturesTheoretical and Applied Fracture Mechanics, 2020
- A mixture design approach for mitigating cracking issue of asphalt concrete pavementConstruction and Building Materials, 2020
- A criterion of asphalt pavement rutting based on the thermal-visco-elastic-plastic modelInternational Journal of Pavement Engineering, 2020
- Characterization and prediction of rutting resistance of rock asphalt mixture under the coupling effect of water and high-temperatureConstruction and Building Materials, 2020
- Experimental study of high modulus asphalt mixture containing reclaimed asphalt pavementJournal of Cleaner Production, 2020
- Freeze-thaw damage and creep behavior of cement asphalt composite binderConstruction and Building Materials, 2020
- Effects of freeze-thaw on dynamic mechanical behavior of cement emulsified asphalt composite binderConstruction and Building Materials, 2019
- Open Graded Friction Course in Resisting Low-Temperature Transverse Cracking in Asphalt PavementJournal of Cold Regions Engineering, 2018
- Laboratory evaluation on performance of diatomite and glass fiber compound modified asphalt mixtureMaterials & Design (1980-2015), 2015