Enabling Artificial Intelligence as Input Variable Control to Prevent Package Thickness Related Defect in Compression Molding

Abstract

This paper aims to identify the causes of package thickness related defects in compression mold process. Related defects include wrong package thickness, exposed wire and/or die and mold bleed out.
 There are three scenarios why package thickness problem is encountered in compression molding. These include wrong mold recipe selected against the actual lot, wrong lot loaded against the current recipe loaded and product input to mold having irregularities such as presence of stray die or damage on strip side rails and end rails. Applying artificial intelligence (AI) the mold machine to detect all abnormalities identified at input and prevent it from proceeding to molding.
 Applying AI was able to eliminate occurrence of all package thickness related defects and machine related downtimes.