A neural network model for the uplift capacity of suction caissons

Abstract

Abstract Suction caissons are frequently used for the anchorage of large compliant offshore structures. The uplift capacity of the suction caissons is a critical issue in these applications, and reliable methods of predicting the capacity are required in order to produce effective designs. In this paper a back-propagation neural network model is developed to predict the uplift capacity of suction foundations. A database containing the results from a number of model and centrifuge tests is used. The results of this study indicate that the neural network model serves as a reliable and simple predictive tool for the uplift capacity of suction caissons. As more data becomes available, the model itself can be improved to make more accurate capacity prediction for a wider range of load and site conditions. The neural network predictions are also compared with finite element based predictions.