Please cite this article as: A.M. Alani, An evolutionary approach to modelling concrete degradation due to sulphuric acid attack, Applied Soft Computing Journal (2014), http://dx.doi.org/10. 1016/j.asoc.2014.08.044 This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of the manuscript. The manuscript will undergo copyediting, typesetting, and review of the resulting proof before it is published in its final form. Please note that during the production process errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.
EPR ProcessPage 2 of 38 A c c e p t e d M a n u s c r i p t 2 Highlights 1-We present a new evolutionary approach for modelling the degradation of concrete 2-The developed models predict the mass loss of concrete due to acid attack 3-Optimum concrete mix to maximise resistance against degradation is determined
Abstract:Concrete corrosion due to sulphuric acid attack is known to be one of the main contributory factors for degradation of concrete sewer pipes. This paper proposes to use a novel data mining technique, namely, evolutionary polynomial regression (EPR), to predict degradation of concrete subject to sulphuric acid attack. A comprehensive dataset from literature is collected to train and develop an EPR model for this purpose. The results show that the EPR model can successfully predict mass loss of concrete specimens exposed to sulphuric acid.Parametric studies show that the proposed model is capable of representing the degree to which individual contributing parameters can affect the degradation of concrete. The developed EPR model is compared with a model based on artificial neural network (ANN) and the advantageous of the EPR approach over ANN is highlighted. In addition, based on the developed EPR model and using an optimisation technique, the optimum concrete mixture to provide maximum resistance against sulphuric acid attack has been identified.