Mathematical-neural model for assessing productivity of earthmoving machinery

Abstract

Many construction processes are carried out by machines working together and forming technological systems, eg earthmoving machinery made up of excavators and haulers (trucks). Productivity (W(N)) is a key to valuate the process design purposes. The paper presents the results obtained by applying artificial neural networks to predict productivity (W(N),S) for earthmoving machinery systems, consisting of c excavators and N haulers. Experimentally determined productivity values can form a standard basis for designing construction earthworks. Possessing the data set consisting of the technical parameters of earthmoving machinery systems and the corresponding productivities for different output hauling distances, one can train artificial neural networks and use subsequently for the reliable prediction of W (N),S.