Optimal Machine Learning-Based Method for Gauging Compressive Strength of Nanosilica-Reinforced Concrete

As nanotechnology developed, new materials emerged that might be employed to improve the mechanical properties of materials like concrete. Intensity factors are proportional to the kind of nanomaterial and its concentration. There is not yet a reliable prediction model for the uniaxial compressive strength (UCS) of nanomaterial-reinforced concrete. Access to such models is crucial for developing and evaluating nanomaterial-reinforced concrete structures. This study investigated the potential of eleven well-known machine learning (ML) algorithms to determine the most accurate and suitable ones to estimate the UCS of nanosilica-reinforced concrete. For this purpose, 460 data points were collected from experimental tests, including five input parameters and one target (UCS). The considered input parameters are the percentage of nanosilica in concrete cement (NS), sample diameter (D), sample length (L), porosity (n), and P-wave velocity (Vp). 80% of the data points were used for training and 20% for testing. The models were then verified using statistical analysis, and their behavior was compared to that in practice. Statistical analysis showed that all the models have achieved good accuracy compared to the experimental results, so the model with the lowest accuracy was the decision tree regressor (DTR) model, with a correlation coefficient of 0.68. However, comparing the behavior of the models with the practice mode by changing the value of one of the input parameters while keeping the values of other parameters constant showed that only the support vector regression (SVR) and null space SVR (NuSVR) models behave correctly. These two models were proposed as the most suitable for estimating the UCS of nanosilica-reinforced concrete. To further aid in the estimation of the UCS of nanosilica-reinforced concrete for engineering challenges, a graphical user interface (GUI) for the ML-based models was developed.