Enhanced soft computing for ensemble approach to estimate the compressive strength of high strength concrete

• Main Authors: Munish KUMAR, Parveen SIHAG, Varun SINGH
• Format: Article
• Language: English
• Published: Mouloud Mammeri University of Tizi-Ouzou 2019-02-01
• Series: Journal of Materials and Engineering Structures
• Subjects: High strength concretes; Gaussian process; Support vectors Machine; artificial neural network
• Online Access: http://revue.ummto.dz/index.php/JMES/article/view/1757

High strength concrete (HCS) define as the concrete that meets unique mixture of performance uniformity requirements that cannot be reached routinely using conventional constituents and regular mixing, placing, and curing events. The modeling of such type of concrete is very difficult. In this investigation, the performance of the gaussian process (GP) regression, support vector Machine (SVM) and artificial neural network (ANN) were compared to estimate the 28th day compressive strength of the HSC. Total data set consists of 83 data out of which 70 % of total dataset used to train the model and residual 30% used to test the models. The model accuracy was depend upon the five performance evaluation parameter which were correlation coefficient (R), Bias, mean square error (MAE), root mean square error (RMSE) and Nash-Sutcliffe model efficiency (E). The results recommend that ANN model is more accurate to predict the compressive strength as compare to GP and SVM based models. Sensitivity analysis indicated that Cement (C), Silica fume (SF), Fly ash (FA) and Water (W) are the most valuable constituents in which compressive strength of the HCS is mainly depend for this data set.