Modelling the fresh properties of self-compacting concrete using support vector machine approach

The main objective of the study presented in this paper was to investigate the feasibility using support vector machines (SVM) for the prediction of the fresh properties of self-compacting concrete. The radial basis function (RBF) and polynomial kernels were used to predict these properties as a function of the content of mix components. The fresh properties were assessed with the slump flow, T50, T60, V-funnel time, Orimet time, and blocking ratio (L-box). The retention of these tests was also measured at 30 and 60 min after adding the first water. The water dosage varied from 188 to 208 L/m3, the dosage of superplasticiser (SP) from 3.8 to 5.8 kg/m3, and the volume of coarse aggregates from 220 to 360 L/m3. In total, twenty mixes were used to measure the fresh state properties with different mixture compositions. RBF kernel was more accurate compared to polynomial kernel based support vector machines with a root mean square error (RMSE) of 26.9 (correlation coefficient of R2 = 0.974) for slump flow prediction, a RMSE of 0.55 (R2 = 0.910) for T50 (s) prediction, a RMSE of 1.71 (R2 = 0.812) for T60 (s) prediction, a RMSE of 0.1517 (R2 = 0.990) for V-funnel time prediction, a RMSE of 3.99 (R2 = 0.976) for Orimet time prediction, and a RMSE of 0.042 (R2 = 0.988) for L-box ratio prediction, respectively. A sensitivity analysis was performed to evaluate the effects of the dosage of cement and limestone powder, the water content, the volumes of coarse aggregate and sand, the dosage of SP and the testing time on the predicted test responses. The analysis indicates that the proposed SVM RBF model can gain a high precision, which provides an alternative method for predicting the fresh properties of SCC.

Performance of sustainable SCC mixes with mineral additions for use in precast concrete industry

The aim of this research was to study the impact that different mineral powders have on the properties of self-compacting concrete (SCC) in order to obtain relations that make it possible to optimize their dosages for being used in precast concrete applications. Different combinations and contents of cement, mineral additions (active and inert), superplasticizers, and aggregates are considered. A new approach for determining the saturation point of superplasticizers is introduced. The fresh state performance was assessed by means of the following tests: slump flow, V-funnel, and J-ring. Concrete compressive strength values at different ages up to 56 days have been retained as representative of the materials’ performance in its hardened state. All these properties have been correlated with SCC proportioning. As a result, a number of recommendations for the precast concrete industry arise to design more stable SCC mixes with a reduced carbon footprint.

Statistical modelling of cement slurries for self compacting SIFCON containing silica fume

This paper reports a study carried out to develop a self-compacting fibre reinforced concrete containing a high fibre content with slurry infiltrated fibre concrete (SIFCON). The SIFCON was developed with 10% of steel fibres which are infiltrated by self-compacting cement slurry without any vibration. Traditionally, the infiltration of the slurry into the layer of fibres is carried out under intensive vibration. A two-level fractional factorial design was used to optimise the properties of cement-based slurries with four independent variables, such as dosage of silica fume, dosage of superplasticiser, sand content, and water/cement ratio (W/C). Rheometer, mini-slump test, Lombardi plate cohesion meter, J-fibre penetration test, and induced bleeding were used to assess the behaviour of fresh cement slurries. The compressive strengths at 7 and 28 days were also measured. The statistical models are valid for slurries made with W/C of 0.40 to 0.50, 50 to 100% of sand by mass of cement, 5 to 10% of silica fume by mass of cement, and SP dosage of 0.6 to 1.2% by mass of cement. This model makes it possible to evaluate the effect of individual variables on measured parameters of fresh cement slurries. The proposed models offered useful information to understand trade-offs between mix variables and compare the responses obtained from various test methods in order to optimise self-compacting SIFCON.

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.

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.

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.

Testing of a novel flexible concrete arch system

This paper describes the testing of a novel flexible masonry concrete arch system which requires no centering in the construction phase or steel reinforcement in the long-term. The arch is constructed from a 'flat pack' system by use of a polymer reinforcement for supporting the self-weight of the concrete voussoirs and behaves as a masonry arch once in the arch form. The paper outlines the construction of a prototype arch and load testing of the backfilled arch ring. Some comparisons to the results from analysis software have been made. The arch had a load carrying capacity far in excess of the current Highways Agency (United Kingdom) design wheel loads.