Quality Prediction and Control of Injection Molding Process using Multistage MWGRNN Method

A multistage moving window generalized regression neural network (GRNN) was demonstrated to injection molding batch process. Firstly analyzing the changes of process correlation can lead to effective division of a process into several "operation" stages, in good agreement with process knowledge. Then the nonlinearly and dynamic relationship between process variables and final qualities was made at different stages, and a multistage on-line quality prediction model was built. In addition, a closed-loop quality control system is proposed. Application has demonstrated that this method can not only give a valid quality prediction, but also effectively carry on quality closed-loop control.