Prediction of IRI in short and long terms for flexible pavements: ANN and GMDH methods

Prediction of pavement condition is one of the most important issues in pavement management systems. In this paper, capabilities of artificial neural networks (ANNs) and group method of data handling (GMDH) methods in predicting flexible pavement conditions were analysed in three levels: in 1 year, in 2 years (short term) and in the pavement life cycle (long term). For this purpose, three effective groups on pavement condition including traffic conditions, environmental changes and pavement structures were studied and nine effective variables were selected as input variables. International roughness index (IRI) was also used as the indicator of pavement performance. Various ANN structures and GMDH models in partial description configurations of 1st, 2nd, 3rd and 4th polynomials were formed and examined. Results indicate that while ANN models predict future condition of pavement with high accuracy in the short and long terms, GMDH models do not have accepted accuracy