In this paper, using a large database from the Long Term Pavement Performance program, the authorsdeveloped an Artificial Neural Network (ANN) to estimate the structural performance of asphalt pave-ments from roughness data. Considering advantages of modern high-performance survey devices inthe acquisition of road pavement functional parameters, it would be of practical significance if the struc-tural state of a pavement could be estimated from its functional conditions. To differentiate various roadsection conditions, several significant input parameters, related to traffic, weather, and structural aspects,have been included in the analysis. The results are very interesting and prove that the ANN represents anadequate model to evidence this relation. The papers shows the effectiveness of the adoption of a largedatabase for the analysis of the correlation. ANN provides also better results in comparison with LinearRegression. Further, the authors trained three different ANNs to analyse the effects of modified datasetsand different variables. The numerical outcomes confirm that, by using this approach, it is possible to cor-relate with good accuracy roughness and structural performance, allowing road agencies to actuallyreduce the deflection test frequency, since they are generally more costly, time consuming, and disrup-tive to traffic than functional surveys.
|Numero di pagine||10|
|Rivista||Construction and Building Materials|
|Stato di pubblicazione||Published - 2017|
All Science Journal Classification (ASJC) codes