Optimisation of gate location based on weld line in plastic injection moulding using computer-aided engineering, artificial neural network, and genetic algorithm

Abstract

Gate location is one of the most important design elements of an injection mould. Injection moulding is a very complex process with several parameters having interactive effects on each other; hence, computer-aided engineering and artificial intelligence were utilised to optimise mould design based on weld line. Therefore, the finite element analysis, artificial neural network and genetic algorithm were linked to find optimum gate location in a plastic product. A reliable numerical model was developed by Moldflow software based on a real product to simulate injection process. Moldflow was used to predict weld line length and position of the part. Weld lines are visually undesirable and a plastic part is structurally weak at weld line positions. This study describes how the weld line was formed on the part. Polyamide-6 (PA-66) was used as the plastic material. To find optimum gate location, the finite element predictions were implemented to train a neural network, which was used later in the genetic algorithm. The optimisation objective was to find gate location which led to minimum weld line length. This research concluded that the developed procedure can efficiently optimise complex manufacturing processes and prevent flaws in products and thus, can be applied practically in the injection moulding process.