Two-stage approach to multiobjective optimization of maintenance scheduling for pavements


Denysiuk, Roman; Moreira André V.; Matos, José C.; Oliveira, Joel; Santos, Adriana

Pavement; Maintenance scheduling; Multiobjective optimization; Evolutionary algorithms

Pavements heavily influence the management costs in highway networks. Operating pavements represents a challenging task6 involving complex decisions on the application of maintenance actions to keep them at a reasonable level of performance. The major diffi-7 culty in applying computational tools to support decision making lies in a large number of pavement sections as a result of a high length of8 road networks. This paper addresses maintenance scheduling for pavements by consolidating this task into two stages. In each stage, multi-9 objective optimization is used to optimize maintenance schedules. The main motivation is to obtain a computationally treatable model for10 large road networks. The first stage is defined by a collection of pavement sections composing the road network. In this stage, the performance11 and maintenance models are addressed. These models account for uncertainties in the future performance and effects of maintenance by12 defining model parameters as random variables. The second stage refers to combining maintenance schedules for individual sections to13 determine the optimal maintenance plan at the network level. The results obtained for the real road network demonstrate the validity14 and usefulness of the proposed framework. Moreover, this framework is general and can be extended to different types of infrastructure15 assets.