Application of KNN and ANN Metamodeling for RTM Filling Process Prediction

Abstract

Process simulation is frequently adopted to facilitate the optimization of the resin transfer molding process. However, it is computationally costly to simulate the multi-physical, multi-scale process, making it infeasible for applications involving huge datasets. In this study, the application of K-nearest neighbors and artificial neural network metamodels is proposed to build predictive surrogate models capable of relating the mold-filling process input-output correlations to assist mold designing. The input features considered are the resin injection location and resin viscosity. The corresponding output features investigated are the number of vents required and the resultant maximum injection pressure. Upon training, both investigated metamodels demonstrated desirable prediction accuracies, with a low prediction error range of 5.0% to 15.7% for KNN metamodels and 6.7% to 17.5% for ANN metamodels. The good prediction results convincingly indicate that metamodeling is a promising option for composite molding applications, with encouraging prospects for data-intensive applications such as process digital twinning.