Machine Learning Approach to Develop a Novel Multi-Objective Optimization Method for Pavement Material Proportion

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.

Determination of Weights for Multiobjective Combinatorial Optimization in Incident Management With an Evolutionary Algorithm

“…Here, the machine learning part of the approach is for determining a complex and not explicitly given objective function. A similar approach regarding an asphalt mixture problem is studied in [32]. In [33], the problem of weight determination is discussed for more complex multiobjective problems as in systems design.…”

CPSO-XGBoost segmented regression model for asphalt pavement deflection basin area prediction

“…PSO-ELM not only possesses higher accuracy but also lies in the fact that the predicted resilient modulus (M r ) usually produces the same distribution and trend as the observed M r . Liang et al [32] develop a new multi-objective PSO (MOPSO) algorithm that uses a Gaussian process regression (GPR) with a machine learning approach to solve asphalt mixture ratio design. In the optimization step, the metaheuristic algorithm based on adaptive weight MOPSO (AWMOPSO) is used to achieve the global optimal solution.…”

Construction Planning and Scheduling of a Renovation Project Using BIM-Based Multi-Objective Genetic Algorithm

“…In real construction projects, there are always multiple objectives forming a set of solutions as optimization data for project managers to make decisions. Consequently, the field of multi-objective optimization has been studied intensively [32,33]. Multi-objective genetic algorithms (MOGA) were first introduced by Tadahiko Murata in 1995 to provide decision-makers with Pareto optimization instead of constant weights [34].…”