Application of Adaptive Neuro-Fuzzy Inference Systems with Principal Component Analysis Model for the Forecasting of Carbonation Depth of Reinforced Concrete Structures

The carbonation of reinforced concrete is one the intrinsic factors that cause a significant decrease in service performance structures. To effect carbonation-induced corrosion during lifetime structure, prediction depth should be made. affected by many factors, such as compressive strength concrete, life, time, carbon dioxide concentration, working stress, temperature, and humidity. On basis these seven parameters, combined with predictive power adaptive network-based fuzzy inference system (ANFIS) principal component analysis (PCA), which can reduce data dimensions before modeling, we introduced novel approach—the PCA–ANFIS model—that predict concrete. Practical engineering examples were adopted to verify superiority suggested model, 90% used for training 10% testing. root mean square error (RMSE) values ANFIS, ANN, PCA–ANN, 12.23, 6.28, 5.42, 1.38, respectively. results showed model accurate fundamental tool predicting life