Prediction of compressive strengths of pumice-and diatomite-containing cement mortars with artificial intelligence-based applications

In this study, two different Artificial neural networks (ANN) and two different adaptive network-based fuzzy inference systems (ANFIS) models were constructed to predict the compressive strength of 7 different cement mortar samples with or without pumice and/or diatomite on different days. Five parameters including day, PC, pumice, diatomite and water were employed as the inputs, and the compressive strength was used as the output variable. The compressive strengths used in the model construction were obtained from laboratory experiments accounting for a total of 168 data. Statistical methods such as R2, RMS and MAPE preferred in the literature were used to compare the four different models. According to the test results obtained from R2, RMS and MAPE, ANN and ANFIS models were able to make very good predictions performance. For this reason, it can be said that these cement mortars' compressive strength can be estimated with a very small error and in a short time with both ANN and ANFIS models.

Automated summary

In this study, two different Artificial neural networks (ANN) and two different adaptive network-based fuzzy inference systems (ANFIS) models were constructed to predict the compressive strength of cement mortar samples with or without pumice and/or diatomite on different days. The models showed very good predictive performance, with a small error, for estimating the compressive strength of the cement mortars.