Artificial Neural Network Estimation of the Effect of Varying Curing Conditions and Cement Type on Hardened Concrete Properties

Abstract

The use of mineral admixtures and industrial waste as a replacement for Portland cement is recognized widely for its energy efficiency along with reduced CO2 emissions. The use of materials such as fly ash, blast-furnace slag or limestone powder in concrete production makes this process a sustainable one. This study explored a number of hardened concrete properties, such as compressive strength, ultrasonic pulse velocity, dynamic elasticity modulus, water absorption and depth of penetration under varying curing conditions having produced concrete samples using Portland cement (PC), slag cement (SC) and limestone cement (LC). The samples were produced at 0.63 and 0.70 w/c (water/cement) ratios. Hardened concrete samples were then cured under three conditions, namely standard (W), open air (A) and sealed plastic bag (B). Although it was found that the early-age strength of slag cement was lower, it was improved significantly on 90th day. In terms of the effect of curing conditions on compressive strength, cure W offered the highest compressive strength, as expected, while cure A offered slightly lower compressive strength levels. An increase in the w/c ratio was found to have a negative impact on pozzolanic reactions, which resulted in poor hardened concrete properties. Furthermore, carbonation effect was found to have positive effects on some of the concrete properties, and it was observed to have improved the depth of water penetration. Moreover, it was possible to estimate the compressive strength with high precision using artificial neural networks (ANN). The values of the slopes of the regression lines for training, validating and testing datasets were 0.9881, 0.9885 and 0.9776, respectively. This indicates the high accuracy of the developed model as well as a good correlation between the predicted compressive strength values and the experimental (measured) ones.

Sustainable Design and Engineering: A Relationship Analysis between Digital Destructive and Non-Destructive Testing Process for Lightweight Concrete

“…Dynamic modulus of elasticity basically originates out via pulse waves; the formula is given above. It can also be found by putting the values of density and pulse velocity and poisons ratio [3,30]. Figure 23 shows the relation between percentage beads replacement and Ed at 7 and 28 days.…”

“…The main parameter that is obtained from the velocity values is the dynamic modulus of elasticity [3], which leads towards the true relation between velocity and Ed [30]. Figure 24 shows the relation between these two parameters.…”

“…Lightweight material production is destined to become a dominant building material in the new era [1]. The basic constituents of concrete are cement, fine aggregate (sand), coarse aggregate, and water [2,3]. Concrete is extremely hard and rigid, and its thermal as well as natural qualities are not very high [4].…”

A Comparative Study of Machine Learning Methods for Compressive Strength of Concrete

“…Kaplan et al [27] also estimate the compressive strength using artificial neural networks. The values of the slopes of the regression lines for training, validating and testing datasets were 0.9881, 0.9885 and 0.9776, respectively.…”

“…RMSE MAE R Bresler and Pister (1958) [4] 137.5 100.8 0.559 88.20 Ottosen (1977) [5] 26.84 19.90 0.890 14.20 Willam and Warnke (1975) [6] 47.73 28.17 0,840 25.94 ANN method [22] 5. [26] 13.58 9.82 0.984 6.84 GP method II (Babanajad et al 2017) [26] 7.87 5.91 0.990 3.95 GP method III (Babanajad et al 2017) [26] 11.14 7.11 0.988 5.60 ANN compressive (Getahum, et al 2018) [21] 0.64 0.48 --ANN compressive (Getahum, et al 2018) [21] 0.07 0.05 --ANN method (Kaplan, et al 2019) [22] 6.24 4.85 0.996 -…”