Analysis of pavement management activities programming by genetic algorithms

Abstract

The application of genetic algorithms to programming of pavement maintenance activities at the network level is demonstrated. The operational characteristics of the genetic algorithm technique and its relevance to solving the programming problem in a Pavement Management System (PMS) are discussed. The robust search capability of genetic algorithms enables them to effectively handle the highly constrained problem of pavement management activities programming, which has an extremely large solution space of astronomical scale. Examples are presented to highlight the versatility of genetic algorithms in accommodating different objective function forms. This versatility makes the algorithms an effective tool for planning in PMS. It is also demonstrated that composite objective functions that combine two or more different objectives can be easily considered without having to reformulate the genetic algorithm computer program. Another useful feature of genetic algorithm solutions is the availability of near-optimal solutions besides the "best" solution. This has practical significance as it gives the users the flexibility to examine the suitability of each solution when practical constraints and factors not included in the optimization analysis are considered.