Neural network approach to sensor design

A radial basis function (RBF) neural network is examined for modeling of acoustical properties of colloidal TiO/sub 2/ slurry. The colloidal slurry is a very complex multiphase medium. The RBF network with a set of local Gaussian functions is trained using the data from a previously developed physical model of TiO/sub 2/ slurry. The TiO/sub 2/ neural model is used for a prediction of the TiO/sub 2/ particle size distribution. The resulting prediction accuracies of the RBF network is 99.8% of the data used in the training process and 88% for the data not used in the training. Compared to other available techniques neural networks can offer an effective and time efficient approach for the modeling of complex materials. >