DEVELOPMENT OF ARTIFICIAL NEURAL NETWORKS FOR PREDICTING CONCRETE COMPRESSIVE STRENGTH

This research work focuses on development of Artificial Neural Networks (ANNs) in prediction of compressive strength of concrete after 28 days. To predict the compressive strength of concrete six input parameters that are cement, water, silica fume, super plasticizer, fine aggregate and coarse aggregate are identified. A total of 639 different data sets of concrete was collected from the technical literature. Training data sets comprises 400 data entries, and the remaining data entries (239) are divided between the validation and testing sets. Different combinations of layers, number of neurons, activation functions, different values for learning rate and momentum were considered and the results were validated using an independent validation data set. A detailed study was carried out, considering two hidden layers for the architecture of neural network. The performance of the 6-12-6-1 architecture was the best possible architecture. The MSE for the training set was 5.33% for the 400 training data points, 6.13% for the 100 verification data points and 6.02 % for the 139 testing data points. The results of the present investigation indicate that ANNs have strong potential as a feasible tool for predicting the compressive strength of concrete.

[1]  Hong-Guang Ni,et al.  Prediction of compressive strength of concrete by neural networks , 2000 .

[2]  Wps Dias,et al.  NEURAL NETWORKS FOR PREDICTING PROPERTIES OF CONCRETES WITH ADMIXTURES , 2001 .

[3]  M. Baziar,et al.  Evaluation of lateral spreading using artificial neural networks , 2005 .

[4]  Jerzy Hoła,et al.  Application of artificial neural networks to determine concrete compressive strength based on non‐destructive tests , 2005 .

[5]  Jerzy Hoła,et al.  New technique of nondestructive assessment of concrete strength using artificial intelligence , 2005 .

[6]  Yong Wang,et al.  Prediction of fire resistance of concrete filled tubular steel columns using neural networks , 2002 .

[7]  Noam Harpaz,et al.  Artificial neural networks distinguish among subtypes of neoplastic colorectal lesions. , 2002, Gastroenterology.

[8]  Mauro Serra,et al.  Concrete strength prediction by means of neural network , 1997 .

[9]  I-Cheng Yeh,et al.  Modeling of strength of high-performance concrete using artificial neural networks , 1998 .

[10]  Seung-Chang Lee,et al.  Prediction of concrete strength using artificial neural networks , 2003 .

[11]  Neil N. Eldin,et al.  Measurement and prediction of the strength of rubberized concrete , 1994 .

[12]  J. Kasperkiewicz.  The applications of ANNs in certain materials-analysis problems , 2000 .

[13]  Wang Ji-Zong,et al.  The application of automatic acquisition of knowledge to mix design of concrete , 1999 .

[14]  A. Öztas,et al.  Appraisal of long-term effects of fly ash and silica fume on compressive strength of concrete by neural networks , 2007 .

[15]  S. Masri,et al.  Identification of Nonlinear Dynamic Systems Using Neural Networks , 1993 .

[16]  Ragip Ince,et al.  Prediction of fracture parameters of concrete by Artificial Neural Networks , 2004 .

[17]  Artur Dubrawski,et al.  HPC Strength Prediction Using Artificial Neural Network , 1995 .

[18]  Murat Dicleli,et al.  Predicting the shear strength of reinforced concrete beams using artificial neural networks , 2004 .

[19]  Maria Q. Feng,et al.  Application of neural networks for estimation of concrete strength , 2002 .