AI-Based Inference System for Concrete Compressive Strength: Multi-Dataset Analysis of Optimized Machine Learning Algorithms

The prediction of concrete compressive strength (CSMPa) is fundamental in experimental civil engineering as it enables the optimization of mix design and complements laboratory testing through predictive tools. This study presents a systematic and reproducible methodology for comparing eight regression algorithms—including linear models, neural networks, and boosting methods—applied to three experimental datasets that represent different types of concrete: high-performance concrete (HPC), conventional concrete, and recycled-aggregate concrete (RAC). In order to make such comparison, some performance metrics were calculated (RMSE, MAE, MAPE, R2, and nRMSE) through hyperparameter optimization using RandomizedSearchCV and homogeneous cross-validation. The boosting methods achieved the best performance, with CatBoost standing out by reaching R2 values between 0.92 and 0.95 and RMSE between 3.4 and 4.4 MPa, confirming its inter-dataset stability and generalization capability. These results indicate consistent predictive accuracy across concretes of different compositions and production contexts. As an applied contribution, three interactive inference systems were developed in Google Colab to estimate CS from mix parameters, promoting reproducibility, open access, and practical use in quality-control processes.