Identification of nonlinear processes with dead time by recurrent neural networks

Methods for identifying a nonlinear dynamic process with unknown and possibly variable dead times via an internal recurrent neural network (IRN) model are proposed. It is shown that an IRN with sufficient hidden nodes can be used directly for the identification of a process with dead times. If a process input window rather than just the current process input is used as the input to an IRN model, the number of the hidden nodes in the IRN model can be reduced, and the prediction performance of the IRN improves for process with long dead times