Polymer material framework for 3D printing using fusion deposition modelling

In today’s rapidly evolving world, the usage of proficient polymer material frameworks is a cornerstone in the domain of 3D printing employing fusion deposition modeling (FDM). This invention not only enhances design adaptability but also drives the development of long-lasting, complicated structures. The connection between polymer chemistry and FDM technology exemplifies the current approach to additive manufacturing, enabling unprecedented possibilities in sectors ranging from aircraft to healthcare and more. This study involved the collection of ABS datasets to evaluate the method presented. The data were preprocessed using z score normalization. The utilization of kernel principal component analysis (K-PCA) was implemented to extract features from the given dataset. We propose an innovative approach named White Shark Optimization-based Random Support Vector Machine (WSO-RSVM) to predict the dimensions in Fused Deposition Modeling (FDM) 3D printing. We addressed the results gained from the Central Composite Design (CCD) of ABS. WSO-RSVM predicted and actual value for various epochs was analyzed. The analysis is done on various parameters like RMSE (0.128), MAE (0.096), R² (0.961), and MSE (1.076). The findings were compared with existing methodologies with our proposed method WSO-RSVM. The findings of the study indicated that the suggested approach, WSO-RSVM, had superior performance compared to other established methodologies.