Identification of dehumidifying coils by radial basis function networks

Abstract

An extension of radial basis functions in numerical analysis, radial basis function networks (RBFN) are used to model dehumidifying coils and compared with multilayer perceptron networks (MLPN). A method similar to backpropagation is used to train the network in a supervised fashion. During the training of the network, all parameters are updated to minimize the difference between the desired outputs and outputs of the network response to the corresponding input vector.