International Journal of Applied Science and Engineering 2015. 13. 3: 187-204 Int. J. Appl. Sci. Eng., 2015. 13,3 187 Artificial Neural Networks for the Prediction of Compressive Strength of Concrete Palika Chopra a , Rajendra Kumar Sharma a , and Maneek Kumar b a School of Mathematics and Computer Applications, Thapar University, Patiala, India b Department of Civil Engineering, Thapar University, Patiala, India Abstract: In the paper, an artificial neural network (ANN) model is proposed to predict the compressive strength of concrete. For developing the ANN model the data bank on concrete compressive strength has been taken from the experiments conducted in the laboratory under standard conditions. The data set is of two types; in one dataset 15% cement is replaced with fly ash and the other one is without any replacement. Several training algorithms, like Quasi-Newton algorithm with Broyden, Fletcher, Goldfarb, and Shanno (BFGS) update (BFG), Fletcher-reeves conjugate gradient algorithm (CGF), Polak-Ribiere conjugate gradient algorithm (CGP),Powell-Beale conjugate gradient algorithm (CGB), Levenberg–Marquardt (LM), Resilient backpropagation (RP), Scaled conjugate gradient backpropagation (SCG), One step Secant backpropagation (OSS) along with various network architectural parameters are experimentally investigated to arrive at the most suitable model for predicting the compressive strength of concrete. It is found that Levenberg–Marquardt (LM) with tan-sigmoid activation function is best for the prediction of compressive strength of concrete. In-situ concrete compressive strength data, based on varying mix proportions, have been taken from one of the research paper present in literature for the validation of the model. It is also recommended that ANN model with the training function, Levenberg–Marquardt (LM) for the prediction of compressive strength of concrete is one of the best possible tool for the purpose. Keywords: Artificial neural network; prediction of compressive strength; concrete. 1. Introduction Concrete is, by far, the most used construction material all over the world. It is known for its high compressive strength, durability, impermeability, fire resistance and abrasion resistance. Having the capability to be formed into any shape and size, it has formed the background of many appealing structures. From a simple material easily formed by just adding coarse aggregates, sand, cement and water in desired proportions. Concrete development for varying needs has been the topic of interest of many researchers. By playing around with its basic ingredients, researchers have been able to develop concretes which not only have very high compressive strength, but have good durability properties as well. The results of compressive strengths vary not only for different concrete mixtures, but for the same mixture as well, which has been attributed to various factors (ACI214R-02). Statistical procedures provide tools of considerable value when evaluating the results of strength tests. Information derived from such  Corresponding author; e-mail: palika.chopra@thapar.edu Received 11 January 2015 Revised 20 March 2015 ○C 2015 Chaoyang University of Technology, ISSN 1727-2394 Accepted 7 May 2015