Artificial Intelligence Based Compressive Strength Prediction of Medium-to-High Strength Ready-Mixed Concrete

One of the most crucial parameters in concrete design is characteristic compressive strength of concrete. The compressive strength of concrete is comparatively resistant to environmental effects. The manufacturing of concrete’s compressive strength is significantly impacted by harsh weather and rising humidity levels. A necessary requirement is the ability to predict the compressive strength of concrete prior to casting. This helps ready-mixed concrete (RMC) people to know about the engineering property, which is the compressive strength of concrete before casting it. It also has a lot of scope for future researchers. This paper aims at developing an artificial intelligence-based model for compressive strength prediction based on experimental data. An experimental laboratory program on tests pertaining to characteristic compressive strength is covering the main variables that affect the test results which was conducted. Then, artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) models were developed based on four targets compressive strength (40, 60, 70, and 80 MPa), three testing ages (7, 28, and 90 days), three protocols of curing, two different specimens shapes (cylinder and cube), and three different specimens sizes. For both the ANN and ANFIS techniques, the model output, the projected compressive strength, showed a good agreement with the experimental test findings. The ANN and ANFIS models had correlation values of 0.976 and 0.989, respectively. Because it offers a little lower root mean squared error and a higher correlation coefficient, ANFIS produces the best results.