Neural Network-Based Prediction: The Case of Reinforced Concrete Members under Simple and Complex Loading

The objective of this study is to compare conventional models used for estimating the load carrying capacity reinforced concrete (RC) members, i.e., Current Design Codes (CDCs), with method based on different assumptions, Compressive Force Path (CFP) and a non-conventional problem solver, an Artificial Neural Network (ANN). For purpose, four databases details critical parameters (i) RC beams in simply supported conditions without transverse steel or stirrups (BWOS) (BWS), (ii) columns cantilever-supported (CWA), (iii) T-beams (TBWOS) (TBWS) (iv) flat slabs under punching (SCS) are developed data from available experimental studies. These obtained published studies helped us estimate member response at ultimate limit-state (ULS). results show that predictions CFP ANNs often correlate closer as compared CDCs.