Neural network based model predictive control of spatially cellular uptake in tissue engineering

In this paper, a neural network based model predictive control (MPC) strategy is proposed to for the cellular uptake (as a function of space and time) of a tissue. First, a time/space separation method is used to transform the high-dimensional spatiotemporal data into low-dimensional temporal data. Then, the MPC strategy is posed using the identified temporal radial basis function neural network model. And the solution of NN-based MPC is obtained by a golden section method that can shorten the solution time of the optimization problem. The accuracy and effectiveness of this approach are demonstrated on an example motivated by tissue engineering.