Counterpropagation neural network for modelling a continuous correlated process

Variations of a counterpropagation (CP) neural network model were investigated for developing both a predictive model and an inverse mapping of process manufacturing operations. A brief explanation of the manufacturing process is provided, along with a review of recent neural network applications to manufacturing. Variations of Kohonen's self organizing map are discussed with respect to the counterpropagation algorithm. Methods are presented for determining the underlying distribution in a data set.