A Study on the Prediction of Compressive Strength of Self-Compacting Recycled Aggregate Concrete Utilizing Novel Computational Approaches

Abstract

A considerable amount of discarded building materials are produced each year worldwide, resulting in ecosystem degradation. Self-compacting concrete (SCC) has 60–70% coarse and fine particles in its composition, so replacing this material with another waste material, such as recycled aggregate (RA), reduces the cost of SCC. This study compares novel Artificial Neural Network algorithm techniques—Levenberg–Marquardt (LM), Bayesian regularization (BR), and Scaled Conjugate Gradient Backpropagation (SCGB)—to estimate the 28-day compressive strength (f’c) of SCC with RA. A total of 515 samples were collected from various published papers, randomly splitting into training, validation, and testing with percentages of 70, 10 and 20. Two statistical indicators, correlation coefficient (R) and mean squared error (MSE), were used to assess the models; the greater the R and lower the MSE, the more accurate the algorithm. The findings demonstrate the higher accuracy of the three models. The best result is achieved by BR (R = 0.91 and MSE = 43.755), while the accuracy of LM is nearly the same (R = 0.90 and MSE = 48.14). LM processes the network in a much shorter time than BR. As a result, LM and BR are the best models in forecasting the 28 days f’c of SCC having RA. The sensitivity analysis showed that cement (28.39%) and water (23.47%) are the most critical variables for predicting the 28-day compressive strength of SCC with RA, while coarse aggregate contributes the least (9.23%).

Artificial neural network, machine learning modelling of compressive strength of recycled coarse aggregate based self-compacting concrete

“…The highest number of frequencies for the chemical admixture is noted above 60, with chemical admixture as 4 Kg/Cu.m noted in Fig 6 . Similar visualisation of the collected data variables is reported in the literature [ 19 – 21 ]. The data variables show that the distribution of the number of data is distributed with different ranges of frequencies of variables.…”

“…Most of the ANN tools are used to forecast the output variables, which is used as a decision-making tool in various fields. ANN consists of a number of interconnected neurons using processing elements called layers, which work together to solve the given problems [ 20 , 21 ]. ANN consists of three different layers processed with the help of different neurons.…”

“…This analysis is also necessary to assess the performance of the predicted results compared to the actual results with the help of different parameters like the coefficient of determination (R 2 ), root mean square error (RMSE), mean square error (MSE), etc., If there are too many input variables are used to estimate the output variables with help of any statistical or ML approach, sensitive analysis is essential. Sensitivity assessment forecasts the effect of the different independent input variables on the particular dependent output variable [ 20 , 21 ]. In this study, the sensitive analysis was performed with the help of various indicators like R 2 , RMSE and MSE.…”

Enhanced fresh and hardened properties of foamed concrete modified with nano-silica

“…For conventional concrete, the relationship between the compressive strength and splitting tensile strength is developed using the power type equation proposed in the literature [ 99 ]. The relationship between the splitting tensile strength and compressive strength of conventional concrete and self-compacting concrete was similar [ 100 ].…”

Influence of Sintering on Thermal, Mechanical and Technological Properties of Glass Foams Produced from Agro-Industrial Residues

“…Today, there is a growing worldwide concern regarding the uncontrolled disposal of wastes in the environment, which makes recycling fundamental in the production of new materials [ 1 ] because it presents advantages such as decreased energy consumption and mitigation of greenhouse gas (CO 2 , SO x and NO x ) emissions [ 2 , 3 , 4 ]. Recycling can reduce the use of natural and synthetic raw materials, adding value to waste by transforming it into a co-product, and thus strengthening the circular economy of regions through its commercialization and processing [ 5 , 6 , 7 , 8 ].…”