AUTOMATIC TUNING AND REGULATION OF INJECTION-MOLDING BY THE VIRTUAL SEARCH METHOD

Methodical specification of process inputs for injection molding is hi ndered by the absence of accurate analytical models. For these process es, the input variables are assigned either by trial and error, based on heuristic knowledge of an experienced operator, or by statistical D esign of Experiments (DOE) methods which construct a comprehensive emp irical model between the inputs and part quality attributes. In this p aper an iterative method of input selection (tuning) referred to as th e Virtual Search Method (VSM) is introduced that conducts most of the search for appropriate machine inputs in a 'virtual' environment provi ded by an approximate input-output (I-O) model. VSM applies the inputs to the process only when it has exhausted the search based on the cur rent I-O model. It evaluates the quality of inputs from the search and updates the I-O model for the next round of search based on measureme nts of parr quality attributes (e.g., size tolerances and surface inte grity) after each process iteration. According to this strategy, VSM u pdates the model only when needed, and thus selectively develops the m odel as required for timing the process. This approach has been shown to lead to shorter tuning sessions than required by DOE methods.