Predicting the internal bond strength of particleboard, utilizing a radial basis function neural network

Development of a model to identify process relationships and predict parameter values in a continuous manufacturing operation is often a difficult undertaking. Process parameters are typically dynamic, and are functions of complex relationships and interactions between process parameters. A radial basis function (RBF) neural network was used to develop a process model for predicting the strength of particleboard. The RBF algorithm was modified using a conscience function to ensure that the distribution of the data was described in each dimension. The trained network was successful at predicting the internal bond strength parameter with an average prediction error of 12.5%. This predictive capability is superior to other neural-network and statistical models developed to predict internal bond. Predictions of this accuracy would allow the trained network model to be used to improve process control in a particleboard manufacturing plant. (C) 1997 Elsevier Science Ltd.