Computerized system for on-line treating with failure parameter using RBF neural network

This paper investigates the applications of a radial basis function (RBF) neural network (NN) to the treatment of failure parameter in the floodgate integrated automation system. For avoiding the drawbacks of arbitrary selecting centers, the RBF NN employs a learning procedure based on the orthogonal least squares (OLS) method. This procedure rational way until an adequate network has been constructed. The OLS algorithm has the property that each selected center maximizes the increment to the explained variance or energy of the desired output. The application results show that the RBF NN can be considered as a suitable technique for treating with failure parameter.