Integration of Artificial Neural Network and Taguchi Method for Prediction and Minimisation of Thick-Walled Polypropylene Gear Shrinkage

The main aim of this research is to optimize the injection molding process parameters in order to mitigate the shrinkage of polypropylene (PP) spur gears. The methodology used integrated experimental approaches with artificial neural networks (ANN), and Taguchi methods to determine the optimal combination of injection molding parameters. The experimental data was used to create an ANN model using Matlab software that accurately predicts unseen data with a variation of less than 5%. The trained ANN model was further used to predict gear shrinkage in the context of Taguchi-based design of experiments. The investigation involved the use of Taguchi and analysis of variance techniques, determining that cooling time is the most important and relevant parameter. This is followed by packing time and melt temperature. The analysis revealed that the gears saw the least amount of shrinkage when the molding was carried out using the optimal combination of injection molding parameters.

Integration of Artificial Neural Network and Taguchi Method for Prediction and Minimisation of Thick-Walled Polypropylene Gear Shrinkage Keywords:

Injection moulding , Polypropylene gear , shrinkage , Artificial Neural Network , Optimisation