Neural Network Modeling of Rheological Parameters of Grouts Containing Viscosity-Modifying Agent

The development of artificial neural network (ANN) models to predict the rheological behavior of grouts is described is this paper and the sensitivity of such parameters to the variation in mixture ingredients is also evaluated. The input parameters of the neural network were the mixture ingredients influencing the rheological behavior of grouts, namely the cement content, fly ash, ground-granulated blast-furnace slag, limestone powder, silica fume, water-binder ratio (w/b), high-range water-reducing admixture, and viscosity-modifying agent (welan gum). The six outputs of the ANN models were the mini-slump, the apparent viscosity at low shear, and the yield stress and plastic viscosity values of the Bingham and modified Bingham models, respectively. The model is based on a multi-layer feed-forward neural network. The details of the proposed ANN with its architecture, training, and validation are presented in this paper. A database of 186 mixtures from eight different studies was developed to train and test the ANN model. The effectiveness of the trained ANN model is evaluated by comparing its responses with the experimental data that were used in the training process. The results show that the ANN model can accurately predict the mini-slump, the apparent viscosity at low shear, the yield stress, and the plastic viscosity values of the Bingham and modified Bingham models of the pseudo-plastic grouts used in the training process. The results can also predict these properties of new mixtures within the practical range of the input variables used in the training with an absolute error of 2%, 0.5%, 8%, 4%, 2%, and 1.6%, respectively. The sensitivity of the ANN model showed that the trend data obtained by the models were in good agreement with the actual experimental results, demonstrating the effect of mixture ingredients on fluidity and the rheological parameters with both the Bingham and modified Bingham models.

Optimisation of rheological parameters and mechanical properties of superplasticised cement grouts containing metakaolin and viscosity modifying admixture

The objective of this research was to optimise the rheological parameters, hardened properties, and setting times of cement grouts containing metakaolin (MTK), viscosity-modifying agent (VMA) and superplasticiser (SP). All mixes were made with water-to-binder ratio (W/B) of 0.40. The replacement of cement by MTK was varied from 6% to 20% (by mass), and dosages of SP and VMA were varied from 0.3% to 1.4%, and 0.01% and 0.06% (by mass of binder), respectively. Increased SP led to an increase in fluidity, reduction in flow time, plate cohesion, rheological parameters, and an increase in the setting times. Increased VMA demonstrated a reduction in fluidity, an increase in Marsh cone time, plate cohesion, yield stress, and plastic viscosity. Results indicate that the use of MTK increased yield stress, plastic viscosity, cohesion plate, and flow time due to the higher surface area associated with an increase in the water demand. MTK reduced mini-slump and setting times, and improved compressive strength.

Optimization of Cement Grouts Containing Silica Fume and Viscosity Modifying Admixture

There is an increasing need to identify the effect of mix composition on the rheological properties of cementitious grouts using minislump, Marsh cone, cohesion plate, washout test, and cubes to determine the fluidity, the cohesion, and other mechanical properties of grouting applications. Mixture proportioning involves the tailoring of several parameters to achieve adequate fluidity, cohesion, washout resistance and compressive strength. This paper proposes a statistical design approach using a composite fractional factorial design which was carried out to model the influence of key parameters on the performance of cement grouts. The responses relate to performance included minislump, flow time using Marsh cone, cohesion measured by Lombardi plate meter, washout mass loss and compressive strength at 3, 7, and 28 days. The statistical models are valid for mixtures with water-to-binder ratio of 0.37–0.53, 0.4–1.8% addition of high-range water reducer (HRWR) by mass of binder, 4–12% additive of silica fume as replacement of cement by mass, and 0.02–0.8% addition of viscosity modifying admixture (VMA) by mass of binder. The models enable the identification of underlying factors and interactions that influence the modeled responses of cement grout. The comparison between the predicted and measured responses indicated good accuracy of the established models to describe the effect of the independent variables on the fluidity, cohesion, washout resistance and the compressive strength. This paper demonstrates the usefulness of the models to better understand trade-offs between parameters. The multiparametric optimization is used to establish isoresponses for a desirability function for cement grout. An increase of HRWR led to an increase of fluidity and washout, a reduction in plate cohesion value, and a reduction in the Marsh cone time. An increase of VMA demonstrated a reduction of fluidity and the washout mass loss, and an increase of Marsh cone time and plate cohesion. Results indicate that the use of silica fume increased the cohesion plate and Marsh cone, and reduced the minislump. Additionally, the silica fume improved the compressive strength and the washout resistance.

Modelling the performance of self-compacting SIFCON of cement slurries containing limestone powder using genetic programming technique

The paper explores the potential of applicability of Genetic programming approach (GP), adopted in this investigation, to model the combined effects of five independent variables to predict the mini-slump, the plate cohesion meter, the induced bleeding test, the J-fiber penetration value, and the compressive strength at 7 and 28 days of self-compacting slurry infiltrated fiber concrete (SIFCON). The variables investigated were the proportions of limestone powder (LSP) and sand, the dosage rates of superplasticiser (SP) and viscosity modifying agent (VMA), and water-to-binder ratio (W/B). Twenty eight mixtures were made with 10-50% LSP as replacement of cement, 0.02-0.06% VMA by mass of cement, 0.6-1.2% SP and 50-150% sand (% mass of binder) and 0.42-0.48 W/B. The proposed genetic models of the self-compacting SIFCON offer useful modelling approach regarding the mix optimisation in predicting the fluidity, the cohesion, the bleeding, the penetration, and the compressive strength.