COMBINING A RADIAL BASIS NEURAL-NETWORK WITH TIME-SERIES ANALYSIS TECHNIQUES TO PREDICT MANUFACTURING PROCESS PARAMETERS

The accurate prediction of the values of critical quality parameters o f a product during the production stage is a key factor in the success of a manufacturing operation. Neural network algorithms have been use d to successfully predict process parameter values. However; technique s to further improve the predictive capability of neural network model s are sought. Thus, an analysis was conducted to determine if the pred ictive capability of the network would be im proved rf the prediction from a time series model of a manufacturing process parameter were inc luded in the training data set of a radial basis function neural netwo rk model. A manufacturing process data set was evaluated and the use o f the time series model prediction significantly improved the neural n etwork's prediction of critical process parameters. Often in a manufac turing environment, the collection of adequate amounts of data for net work training is difficult. This integrated technique offers potential for improving network performance without collecting additional data.