Model Identification of Nonlinear Temperature System with Time-Delay Based on Neural Network

A DFOPDT model of nonlinear temperature system with time-delay is established. An algorithm is presented, which is an effective way to solve unknown parameters of the model by neural network. In the method, the network can soon converge through the iterative calculation in which the value of unknown parameters is predicted continuously. Meanwhile, it also solves to train a network with unknown output by the function "train" in MATLAB neural network toolbox. The DFOPDT model of the system is identified by the method through step response. It is proved that the method has a good convergence, concise algorithm and high accuracy.