GENETIC-ALGORITHM PROGRAMMING OF ROAD MAINTENANCE AND REHABILITATION

The authors of this paper developed a computer model based on genetic algorithms, an optimization tool capable of overcoming combinatorial explosion. PAVENET-R, the model described, is designed to solve the pavement maintenance-rehabilitation trade-off problem at the network level. An integer coding scheme is chosen for parameter representation in the model. Two genetic-algorithm operators are used--the crossover operator and the mutation operator. To ensure that only valid offspring are created from a parent pool, a "change table" encodes constraints to the genetic-algorithm operations. Four numerical examples of road networks of 30 pavement sections, each with different relative costs of rehabilitation and maintenance activities, are analyzed to illustrate the trade-off relationship between pavement rehabilitation and maintenance activities. The maintenance and rehabilitation schedules of the solutions are presented in detail as well as the convergence characteristics of each solution.

Language

  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 00721059
  • Record Type: Publication
  • Files: TRIS, ATRI
  • Created Date: May 3 1996 12:00AM