LAUSR

Pavement homogenous sectioning is a vital step in pavement management system (PMS) analysis. Sections can be created using either fixed, dynamic or static sectioning principles. Each of these has various implications with regard to the data collection and decision making strategy of management. Pavement management with true homogeneous section selection has great importance for cost minimization over a specified time period when modifying the pavement deterioration based on correct decisions in the PMS. This issue was proposed for cost reduction, minimization of sectioning errors, and accuracy improvement of pavement network analysis. Thus, the focus of this research is to investigate efficient hybrid methods applied for reducing complexity involved in this problem. Results show that various combinations of hybrid particle swarm optimization (PSO) and genetic algorithm (GA) were used for analysis of a given pavement network that play a better role as section makers than single GA or PSO in terms of network sectioning error, computation time (CPU time), and number of sections as well as convergence diagrams for network, project, and section management levels. Results indicated that hybrid approaches provide a highly suitable solution in a short time for each pavement branch in massive networks with big data and minimize the costs involved in the sectioning process.