Modeling slump of concrete using the group method data handling algorithm

This paper proposes the group method data handling (GMDH) algorithm and applies it to estimate the slump of high-performance concrete (HPC). It is known that HPC is a highly complex material whose behaviour is difficult to model, especially for slump. To estimate the slump, it is a nonlinear function of the content of all concrete ingredients, including cement, fly ash, blast furnace slag, water, superplasticizer, and coarse and fine aggregate. Therefore, slump estimation is set as a function of the content of these seven concrete ingredients and additional four important ratios. The GMDH algorithm presented in this paper has the advantage of a heuristic self-organized and gradually complicated model for the complicated multi-variable HPC slump estimation. The model establishes the input-output relationship of a complex system using a multilayered perception-type structure that is similar to a feed-forward multilayer artificial neural network (ANN), but it expresses relationships using more explicit functions than ANN. Moreover, the GMDH has the ability to select significant variables and combine them properly and automatically. The results show that GMDH obtains a more accurate mathematical equation through learning procedures which outperforms the traditional multiple linear regression analysis (RA) and ANN, with lower estimating errors for predicting the HPC slump.