Neural Networks for the Prediction of Fresh Properties and Compressive Strength of Flowable Concrete

Abstract

This paper presents the prediction of fresh concrete properties and compressive strength of flowable concrete through neural network approach. A comprehensive data set was generated from the experiments performed in the laboratory under standard conditions. The flowable concrete was made with two different types of micro particles and with single nano particles. The input parameter was chosen for the neural network model as cement, fine aggregate, coarse aggregate, superplasticizer, water-cement ratio, micro aluminium oxide particles, micro titanium oxide particles, and nano silica. The output parameter includes the slump Flow, L-Box flow, V Funnel flow and compressive strength of the flowable concrete. To develop a suitable neural network model, several training algorithms were used such as BFGS Quasi- Newton back propagation, Fletcher-Powell conjugate gradient back propagation, Polak - Ribiere conjugate gradient back propagation, Gradient descent with adaptive linear back propagation and Levenberg-Marquardt back propagation. It was found that BFGS Quasi- Newton back propagation and Levenberg-Marquardt back propagation algorithm provides more than 90% on the prediction accuracy. Hence, the model performance was agreeable for prediction purposes for the fresh properties and compressive strength of flowable concrete.

Prediction of Compressive Strengths for Rice Husks Ash incorporated concrete, Using Neural Network and Reviews

“…According to Revathy et al [3], for MAPE value of less than 10% was an indication of very good performance of model and for MAPE value greater than 10%, could be due to higher variation in experimental data. The MAPE values for this research was 9.73% for the overall data, with the lowest being for training data, with 9.19% and the highest for the validation/checking data, at 12.41%.…”

“…RHA Composition, Applicability and Effects Study by Thiedeitz et al [5] indicated specific surface area based on BET adsorption method for rice husk ash (grounded for 20 seconds with 20 Hertz frequency) and cement CEM 1 42.5R were 128 m 2 /g and 1.24m 2 /g respectively. Study by Fernandes et al [33] on RHA from thermoelectric company in Brazil, indicated mean diameter of 19.56 + 0.49 µm, specific weight of 2.22 + 0.0028 g/cm 3 and specific area of 11.35 + 0.21 m 2 /g, for RHA described in table 1. Based on Fernandes et al [33] study, the specific surface area reduced with thermal treatment temperatures.…”

“…Sathyan et al [2] used random kitchen sink algorithm and regularized least square to predict concrete rheological and hardened properties, with 32 data sets (80%) used for training and 8 datasets (20%) for testing. Revathy et al [3] used various types of network functions, one of the types using algorithm BFGS quasi-Newton back propagation, indicated using 34 datasets for training, 8 for validation and 8 for testing. For this study, the 72 data were divided into 51 (70.83%) for training, 10 (13.89%) for validation or checking and 11 (15.28%) for testing.…”

“…Sathyan et al [2] used random kitchen sink algorithm and regularized least square to predict concrete rheological and hardened properties, results indicated RMSEs and mean absolute errors(MSEs) of less than 0.05. According to Revathy et al [3] the MAPE represent model performance and RMSE -Equation (3)-represent the error between the experimental and predicted results. Sathyan et al [2] study on prediction of concrete rheological and hardened properties, input parameters enclosed weights of ingredients including cement, coarse aggregates, fine aggregates, four superplasticizers dosage and water.…”

Prediction of Compressive Strengths of Concrete with Partial Fine Aggregate of Plastic Using Artificial Neural Network and Revisions

“…Al-Swaidani and Khwies [4] research, using ANNs established in MATLAB and trained by Levenberg-Marquardt backpropagation on concrete containing volcanic-scoria as cement replacement, 0 % (control) to 35 %, indicated that ANN models were not only practical for compressive strength prediction but also highly efficient for water permeability prediction and porosity, the model performing better than multi-linear regression. Revathy et al [5] carried out a study, where mean absolute percentage error (MAPE) represented the model performance and root mean square error (RMSE) represented the error between experimental and predicted results, for neural network models generated to predict compressive strength and fresh properties of flowable concrete, using MATLAB; they used 34 data set for training, 8 for validation and 8 for testing, using BFGS quasi-newton back propagation training algorithm for neural network. Sathyan et al [6] used random kitchen sink algorithm and regularized least square algorithm; the two applications come together in the grand unified regularized least square (GURLS) tool bar in MATLAB; the training data had 32 datasets and to measure model accuracy 8 test dataset were used; hardened stages of self-compacting concrete were used for modeling.…”