A Data-Driven Model for Ice-Breaking Resistance of Structure Based on Non-Smooth Discrete Element Method and Artificial Neural Network Method

In this paper, a data-driven model based on the Non-smooth Discrete Element Method (NDEM) and Artificial Neural Network (ANN) is proposed for computation of ice-breaking resistance structure. The idea so-called “meta-modelling”, which means establishing an pre-computed ice failure database to avoid time-consuming direct resolving fracture process, was integrated in non-smooth discrete element method (NDEM). developed validated by simulating process cone structure, computational results match well with experimental ones literature. After that, effects various parameters were analyzed model. It found that factors have great influence structure level condition are angle, navigation velocity thickness.