A New Approach for Predicting Strength Based on Temperature-Time History Using Two-Parameter Maturity ANN Models.

One widely used method to predict concrete strength development based on temperature variations during curing is the equivalent maturity time (te) method. This method uses the activation energy (Ea) as its key parameter, which reflects the cement's sensitivity to temperature. However, research shows that the Ea value varies depending on factors such as cement type, water/cement ratio, temperature, and additives. The permanent subject of discussion is the question of what value of the Ea parameter should be assumed. In this paper, a new approach is proposed by using a neural network analysis method to develop a strength-temperature history model. It was assumed that the ANN-fc% = f(Q, E, T, t) model would have 4 inputs: hydration heat (Q), activation energy (Ea), temperature (T), and time (t). The research was conducted on mortars using 6 cements, at curing temperatures ranging from 5 to 35 °C, assessing strength over a 90 day period. The results showed that the ANN analysis method allows for estimating the relative compressive strength with sufficient accuracy. Analysis of the input nodes indicated that Q influences early strength gain, while Ea affects later strength development. The application of the ANN model for calculating strength based on temperature changes during maturation was illustrated.