ANN-based prediction of compressive strength in sustainable HPC using industrial waste

Sustainable high-performance concrete (HPC) with industrial waste is a new building material with environmental significance and engineering value. As a critical parameter of construction materials, the compressive strength of concrete is an important index for determining the practical engineering application of concrete materials, and it is of great significance to accurately predict the compressive strength of sustainable HPC with industrial waste. This study uses an improved artificial neural network (ANN) model to predict the compressive strength of sustainable HPC with industrial waste, considering eight input parameters. A high-performance concrete compressive strength prediction model based on ANNs was established using different optimization algorithms, and the model was validated using K-fold cross-validation. The proposed ANN model, optimized with virus colony search (VCS), achieved coefficient of determination R 2 > 0.97, root mean squared error ( RMSE ) of 1.95–2.33 MPa, and mean absolute error ( MAE ) of 1.26–1.39 MPa, outperforming traditional models. This research result plays an important role in accurately predicting the compressive strength of sustainable HPC under different mix ratios.