PROMOTING ACCESS TO AFRICAN RESEARCH

Nigerian Journal of Technology

Log in or Register to get access to full text downloads.

Remember me or Register



Predicting the Compressive Strength of Concretes Made with Granite from Eastern Nigeria Using Artificial Neural Networks

CC Nwobi-Okoye, IE Umeonyiagu, CG Nwankwoc

Abstract


Cases of collapsed buildings and structures are prevalent in Nigeria. In most of these cases the cause of the collapse could be traced to the strength of the construction materials, mainly concrete. Secondly, experimental determination of the strength of concrete materials used in buildings and structures is quite expensive and time consuming. This research seeks to develop a computational model based on arti cial neural networks for the determination of the compressive strength of concrete materials made from a prevalent coarse aggregate component from Nigeria. The work involved building a multilayer perceptron neural network model which was trained using experimental data obtained from compressive strength test of concrete made from granite. The compressive strength predictions were compared with predictions from an alternative model based on regression analysis. The results of the study show that for the granite based concrete, the regression model prediction has a sum of squares error of 20.289 and a mean absolute percentage (relative) error of 1.149, while the neural network model prediction has a sum of squares error of 0.299 and a mean absolute percentage (relative) error of 0.047. Generally, the models predicted well, but the neural network model predicted better than the regression model. The result of the study has ably demonstrated a cheap, simple, very quick and accurate alternative to experimental method of concrete strength determination. The method is also simpler and quicker than analytical methods based on regression analysis. This work is therefore expected to be of immense bene t to civil engineers and construction professionals, and would help in economically determining the strength, as well as economical selection of appropriate mix of construction materials, a prelude to building strong and cheap buildings and structures.

Keywords: artificial neural network, concrete, granite, regression, modelling





AJOL African Journals Online