Multiscale approach for bone remodeling simulation based on finite element and neural network computation

In this paper, a novel multiscale hierarchical model based on finite element analysis and neural network computation was developed to link mesoscopic and macroscopic scales to simulate bone remodeling process. The finite element calculation is performed at macroscopic level and trained neural networks are employed as numerical devices for substituting the finite element computation needed for the mesoscale prediction. Based on a set of mesoscale simulations of representative volume elements of bone taken from different bone sites, a neural network is trained to approximate the responses at meso level and transferred at macro level.