Artificial Intelligence Model for Flowable Concrete Mixtures Used in Underwater Construction and Repair

This study explores using artificial neural networks to predict the rheological and mechanical properties of underwater concrete (UWC) mixtures and to evaluate the sensitivity of such properties to variations in mixture ingredients. Artificial neural networks (ANN) mimic the structure and operation of biological neurons and have the unique ability of self-learning, mapping, and functional approximation. Details of the development of the proposed neural network model, its architecture, training, and validation are presented in this study. A database incorporating 175 UWC mixtures from nine different studies was developed to train and test the ANN model. The data are arranged in a patterned format. Each pattern contains an input vector that includes quantity values of the mixture variables influencing the behavior of UWC mixtures (that is, cement, silica fume, fly ash, slag, water, coarse and fine aggregates, and chemical admixtures) and a corresponding output vector that includes the rheological or mechanical property to be modeled. Results show that the ANN model thus developed is not only capable of accurately predicting the slump, slump-flow, washout resistance, and compressive strength of underwater concrete mixtures used in the training process, but it can also effectively predict the aforementioned properties for new mixtures designed within the practical range of the input parameters used in the training process with an absolute error of 4.6, 10.6, 10.6, and 4.4%, respectively.

Factorial Design of Modelling Mix Proportion Parameters of Underwater Composite Cement Grouts

There is an increasing need to identify the rheological properties of cement grout using a simple test to determine the fluidity, and other properties of underwater applications such as washout resistance and compressive strength. This paper reviews statistical models developed using a factorial design that was carried out to model the influence of key parameters on properties affecting the performance of underwater cement grout. Such responses of fluidity included minislump and flow time measured by Marsh cone, washout resistance, unit weight, and compressive strength. The models are valid for mixes with 0.35–0.55 water-to-binder ratio (W/B), 0.053–0.141% of antiwashout admixture (AWA), by mass of water, and 0.4–1.8% (dry extract) of superplasticizer (SP), by mass of binder. Two types of underwater grout were tested: the first one made with cement and the second one made with 20% of pulverised fuel ash (PFA) replacement, by mass of binder. Also presented are the derived models that enable the identification of underlying primary factors and their interactions that influence the modelled responses of underwater cement grout. Such parameters can be useful to reduce the test protocol needed for proportioning of underwater cement grout. This paper attempts also to demonstrate the usefulness of the models to better understand trade-offs between parameters and compare the responses obtained from the various test methods that are highlighted.

Effect of Mixture Composition on Washout Resistance of Highly Flowable Underwater Concrete

The underwater casting of relatively thin lifts of concrete in water requires the proportioning of highly flowable concrete that can resist water dilution and segregation and spread readily into place. An investigation was carried out to determine the effects of antiwashout admixture concentration, water-cementitious materials ratio, and binder composition on the washout resistance of highly flowable concrete. Two main types of antiwashout admixtures were used: 1) a powdered welan gum at concentrations of 0.07 and 0.15% (by mass of binder); and 2) a liquid-based cellulosic admixture with dosages up to 1.65 L/100 kg of binder. The water-cementitious materials ratios were set at 0.41 and 0.47, corresponding to high-quality underwater concrete. Four binder compositions were used: a standard Canadian Type 10 cement, the same cement with 10% silica fume replacement, the cement with 50% granulated blast-furnace slag replacement, and a ternary cement containing 6% silica fume and 20% Class F fly ash. The concentrations of anti-washout admixture have direct impact on washout resistance. For a given washout loss, greater slump flow consistency can be achieved with the increases in anti-washout admixture concentration and decreases in water-binder ratio. The washout mass loss can be reduced, for a given consistency

Effect of Mixture Composition on Relative Strength of Highly Flowable Underwater Concrete

Concrete used for underwater repair is often proportioned to spread readily into place and self-consolidate, and to develop high resistance to segregation and water dilution. An investigation was carried out to determine the effect of the dosage of antiwashout admixture, water-cementitious materials ratio (w/cm), and binder composition on the relative residual strength of highly flowable underwater concrete. Two types of antiwashout admixtures were used: a powdered welan gum at 0.07 and 0.15% by mass of binder, and a liquid-based cellulosic admixture employed at a high dosage of 1 to 1.65 L/100 kg of cementitious materials. The w/cms were set at 0.41 and 0.47 to secure adequate performance of underwater concrete for construction and repair. Four binder compositions were used: a Canadian Type 10 cement; a cement with 10% silica fume replacement; a cement with 50% replacement of granulated blast-furnace slag; and a ternary binder containing 6% silica fume and 20% Class F fly ash. Test results indicate that for a given washout mass loss and slump flow consistency, greater relative residual strength can be secured when the dosage of antiwashout admixture is increased, the w/cm is reduced, and a binary binder with 10% silica fume substitution or the ternary binder are employed. Such mixtures can develop relative residual compressive strengths of 85 and 80%, compared to mixtures cast in air, when the value of washout loss is limited to 4 and 6% for mixtures with slump flow values of 450 and 550 mm, respectively.