GENETIC-ALGORITHM PROGRAMMING OF ROAD MAINTENANCE AND REHABILITATION

This paper describes the development of a computer model (known as PAV ENET-R) based on genetic algorithms, an optimization tool capable of o vercoming combinatorial explosion, to solve the pavement maintenance-r ehabilitation trade-off problem at the network level. The formulation of the PAVENET-R model is described in detail. An integer coding schem e is selected for parameter representation in the model. Two genetic-a lgorithm operators, namely the crossover operator and the mutation ope rator, are used. A ''change table'' encodes constraints to the genetic -algorithm operations to ensure that only valid offspring are generate d from a parent pool. Four numerical examples of road networks of 30 p avement segments, each with different relative costs of rehabilitation and maintenance activities, are analyzed to demonstrate the trade-off relationship between pavement rehabilitation and maintenance activiti es. The detailed maintenance and rehabilitation schedules of the solut ions, and the convergence characteristics of each solution are present ed.