H. Costa

Prediction of Fresh and Hardened State Properties of UHPC: Comparative Study of Statistical Mixture Design and an Artificial Neural Network Model

AbstractThe main objective of the research study described herein is to build two analytical models based on artificial neural networks (ANNs) and the statistical mixture design (SMD) method to predict the required performance of ultra-high-performance concrete (UHPC). Two different curing conditions—heat treatment and water storage—were applied to the specimens. To train the neural network, a total set of 53 different mixtures was designed based on the design matrix of SMD. The statistical analysis results showed the adequacy of both models to predict the required performance of UHPC; however, the ANN model could predict the compressive strength (water storage) and slump flow with higher accuracy than the SMD. The optimum combination of the cement, silica fume, and quartz flour was determined to be 24, 9, and 5% by total volume to achieve a flowable mixture with the highest compressive strength. The accuracy of the model was verified with additional experimental tests.

Design of UHPC using artificial neural networks

Ultra-high performance concrete (UHPC) results from the mixture of several constituents giving rise to a highly complex material in hardened state. The higher number of constituents in relation to current concrete, together with a higher number of possible combinations and relative proportioning, makes the behavior of this type of concrete more difficult to predict. Until now, most of the proposed mixture design methods are based on a trial and error procedure, which is expensive and work intensive. Moreover, these methods are not efficient in predicting neither the consistency in fresh state nor the strength in hardened state, and do not consider the effect of curing on the latter. The main objective of the research study herein described is to build an analytical model, based on artificial neural networks (ANN), to predict the required performance of UHPC. Specifically, back-propagation neural networks (BPNN) are adopted to model the relation between the input and the output parameters of UHPC, for two different curing conditions, including heat treatment and water storage. In order to train the neural network, a total set of 53 different mixtures were designed. It is concluded that the developed model can be used as a reliable method to predict the performance of UHPC.