NEURAL NETWORKS AND AASHO ROAD TEST

The American Association of State Highway Officials (AASHO) road test, conducted during the period of 1958 through 1960, was factorial test of pavement durability that considered layer depths, axle load, and nu mber of load applications as the primary variables. These data were pr ocessed using traditional statistical techniques. The AASHO formula is the resulting databased model of the road-test data. In the present p aper, we reexamine the AASHO road-test data, using the Monte Carlo Hie rarchical Adaptive Random Partitioning (MC-HARP) neural-network model developed by Banan and Hjelmstad (1995), and show that an MC-HARP mode l can represent the data far better than the AASHO formula can. We con clude that the MC-HARP neural network may be an appropriate tool for t he development of databased models of pavement performance in the futu re.