Abstract
A numerical procedure using an artificial neural network (ANN) has been developed to identify the model parameters of 0-dimensional radiator heat balance models. This model parameter identification method includes two steps as follows. The first step is an ANN learning step. The second step is a computational analysis step to identify the model parameters using learned ANN. The model parameters to be identified are radiator-water thermal conductance as a function of water flow rate, radiator-air thermal conductance as a function of air velocity, and radiator heat capacity as a constant. The validation results indicate that the present method can be applied to identify model parameters.
