Prediction of compression strength of high performance concrete using artificial neural networks

Abstract

Abstract. High-strength concrete is undoubtedly one of the most innovative materials in construction. Its manufacture is simple and is carried out starting from essential components (water, cement, fine and aggregates) and a number of additives. Their proportions have a high influence on the final strength of the product. This relations do not seem to follow a mathematical formula and yet their knowledge is crucial to optimize the quantities of raw materials used in the manufacture of concrete. Of all mechanical properties, concrete compressive strength at 28 days is most often used for quality control. Therefore, it would be important to have a tool to numerically model such relationships, even before processing. In this aspect, artificial neural networks have proven to be a powerful modeling tool especially when obtaining a result with higher reliability than knowledge of the relationships between the variables involved in the process. This research has designed an artificial neural network to model the compressive strength of concrete based on their manufacturing parameters, obtaining correlations of the order of 0.94.

Modelización del ensayo de resistencia a compresión del concreto de alta resistencia mediante una red neuronal artificial. Obtención de la incertidumbre del resultado

“…El resultado es superior al obtenido por [10] en su estudio de los intervalos de confianza de las predicciones en los mercados de energía en el cual se obtuvieron PICP(%) entre 92.6 y 94.1%. El resultado obtenido es también superior al obtenido por [28] en su estudio de los intervalos de confianza de las predicciones de demanda del mercado eléctrico, los cuáles obtuvieron PICP(%) entre el 50% y el 100%.…”

“…Los ensayos de compresión axial se realizaron en una máquina TONI-TECHNIK provista de una célula de 3.000KN y TINIUS OLSEN DE 1.500KN. De acuerdo a estudios similares realizados anteriormente [10][11][12]. Como variables explicativas se tomaron el tiempo de curado, tipo cantidad y porcentaje de aditivo; tipo, porcentaje y cantidad de microsílice; cantidades de agua, piedra, arena y cemento; el TNM de la piedra, los pesos específicos de la arena y la piedra y la relación agua-cemento.…”

Properties prediction of environmentally friendly ultra-high-performance concrete using artificial neural networks

“…Their ANN model was able to predict experimental results accurately. Torre et al (2015) also constructed a multilayer perceptron model to predict compressive strength of high-performance concrete. The model accurately predicted the compressive strength of concrete.…”

Performance comparison of neural network training algorithms in the modeling properties of steel fiber reinforced concrete

“…The application of artificial neural networks (ANNs) for prediction and optimization of concrete properties is relatively a new research area and recent studies have demonstrated that ANN is one of the best machine learning tools for this purpose (Chopra et al., 2015; Muthupriya et al., 2011; Torre et al., 2015). The comparison between ANN and some classical modeling techniques such as response surface methodology (RSM), Plackett-Burman designs, full factorial designs and randomized block designs showed the supremacy of ANN as a modeling technique in analyzing non-linear relationships of data sets, which consequently provides good fitting for data and as well as better predictive ability (Hacene et al., 2013).…”