Data mining and forecasting of pavement strength depending on the composition of asphalt concrete mix

Abstract

The article substantiates the need for widespread introduction of computer technology and information systems in the mix production process at ACF and their quality control, which is determined by the presence of a significant number of control objects, a large array of monitored indicators, high labor and material costs of testing, low efficiency and quality of processing complex multidimensional data. It is proposed to use Data Mining methods for intelligent data analysis and prediction of pavement durability depending on the composition of asphalt mix which enable to solve the tasks of classification, regression, clustering and forecasting using artificial intelligence methods. The algorithm of intellectual data analysis and prediction of durability of the mix depending on its composition is offered and the actions at each its stage, using additional methods of data analysis, are described. The example of real raw data processing obtained from the quality control laboratory of one of the asphalt plants using Data Mining tools of STATISTICA package according to the developed algorithm is given. The prospects of using modern data processing technologies in the field of asphalt concrete quality control are evaluated. It is shown that to assess the quality of the mix and pavement durability, it is necessary to move to complex quality indicators, taking into account pavement operating conditions.