پيش‌بيني ابعاد قطعه‌هاي قالب‌گيري تزريقي با استفاده از پروفيل فشار مذاب در قالب و شبكه عصبي‌

Dimensional Prediction of Injection Molded Parts Using Melt Pressure Trace and Neural Network

The variations in plastic injection molding process may lead to the inconsistency of molded partsʹ dimensions. Furthermore, due to the speed of production as well as post-shrinkage of molded part s make the control of process difficult and give inaccurate molded parts. The objective of this research is to predict the dimensions of injection molde d parts on the basis of cavity pressure during the molding process. At the first stage of experimentations, the variations of molding process were determined under a base setting condition by using cavity pressure measurement approach. At the second stage, the effects of moldin g parameter s on the cavity pressure profile as well as partʹs dimen sions 1- - - - - - - - - - were studied. Following, an artific ial neural-network model was implemented capable of predicting the molded partʹs dimen sions based on the cavity pressure. To increase the efficiency of proposed model , three features of the cavity pressure trace encompassing maximum cavity pressure, cavi ty pressure-time integral value , as well as time to reach the maximum pressure were selected as neural- network input s.