Utilization of neural networks for the recognition of variance shifts in correlated manufacturing process parameters

Traditional statistical process control (SPC) charting techniques were deve loped for use in discrete industries where independence exists between proc ess parameters over time. Process parameters from many manufacturing indust ries are not independent, however, but they are serially correlated. Conseq uently, the power of traditional SPC charts was greatly weakened. The paper discusses the development of neural network models to identify successfull y shifts in the variance of correlated process parameters. These neural net work models can be used to monitor manufacturing process parameters and sig nal when process adjustments are needed.