Uplift capacity prediction of suction caisson in sand bend using GMDH and method GMDH-ANN

Suction caissons generally used as anchor for large offshore structures. Uplift capacity is the main issue in their stabilities. If this issue doesn’t calculate correctly, suction caisson may be collapsed. During recent years, many Artificial Intelligence (AI) has been used for suction caisson uplift capacity prediction. One of this method is Group Method of Data Handling (GMDH). In this study, a model based on GMDH and a hybrid model GMDH-ANN were developed using programing code in MATLAB software. For validating developed methods, several statistical indices are calculated. Also the results of Finite Element Method (FEM) and Artificial Neural Network (ANN) were compared with developed methods. Comparison of these results showed that these developed methods had good performance in suction caisson uplift capacity.