Artificial neural networks model for predicting excavator productivity

Abstract

This paper aims to develop a quantitative model for predicting the productivity of excavators using artificial neural networks (ANN), which is then compared with the multiple regression model developed by Edwards & Holt (2000). A neural network using the architecture of multilayer feedforward (MLFF) is used to model the productivity of excavators. Finally, the modelling methods, predictive behaviours and the advantages of each model are discussed. The results show that the ANN model is suitable for mapping the non‐linear relationship between excavation activities and the performance of excavators. It concludes that the ANN model is an ideal alternative for estimating the productivity of excavators.

Citation

TAM, C.M., TONG, T.K.L. and TSE, S.L. (2002), "Artificial neural networks model for predicting excavator productivity", Engineering, Construction and Architectural Management, Vol. 9 No. 5/6, pp. 446-452. https://doi.org/10.1108/eb021238