Neural network approach to identify batch cell growth

A saturation-type transfer function with a backpropagation neural network (BPNN) is proposed for solving the modeling problem of a batch cell growth system. Trying to model the cell growth with information concerning only the initial conditions is not yet possible from a kinetic approach. The feasibility and capability of the neural network to model the pattern of batch cell growth by providing initial conditions only is tested. A two-three-eight BPNN with initial glucose and cell concentrations as the two inputs and cell densities measured at eight each hour as the eight outputs is thus constructed. The simulation and prediction results of this BPNN are presented to demonstrate the performance and applicability of this newly discovered transfer function. The sensitivity analysis of the initial factors from this neural network model (NNM) is also discussed. The optimization of the initial conditions for this system is performed