Developing a Pavement Management Computer Program Based on Genetic Algorithms

In this research a computer model formulated on the operating principle of genetic algorithms to serve as an analytical aid for pavement maintenance engineers is introduced. Analyses are conducted to show the characteristics of important operation parameter of the program. These parameters include: (1) Parent pool size; (2) Mutation rate in offspring generation. The effects of road maintenance parameter such as choice of warning level are analyzed. Examples are presented to illustrate the application of program to the selection of maintenance warning levels. Finally the detailed maintenance and rehabilitation schedules with two objective functions; minimization the present worth of maintenance costs budget and maximization of network pavement condition index; are presented.