RESUMEN
This study involved the optimization of the molded pieces manufacturing process from a poly-3-hydroxybutyrate-co-3-hydroxyvalerate biocomposite containing 30% wood flour by mass. The amount of wood flour and preliminary processing parameters were determined on the basis of preliminary tests. The aim of the optimization was to find the configuration of important parameters of the injection process to obtain molded pieces of good quality, in terms of aesthetics, dimensions, and mechanical properties. The products tested for quality were dog bone specimens. The biocomposite was produced using a single-screw extruder, whereas molded pieces were made using an injection molding process. The Taguchi method was applied to optimize the injection molding parameters, which determine the products quality. Control factors were selected at three levels. The L27 orthogonal plan was used. For each set of input parameters from this plan, four processing tests were performed. The sample weight, shrinkage, elongation at break, tensile strength, and Young's modulus were selected to assess the quality of the molded parts. As a result of the research, the processing parameters of the tested biocomposite were determined, enabling the production of good-quality molded pieces. No common parameter configuration was found for different optimization criteria. Further research should focus on finding a different range of technological parameters. At the same time, it was found that the range of processing parameters of the produced biocomposite, especially processing temperature, made it possible to use it in the Wood Polymer Composites segment.
RESUMEN
This study optimized friction stir welding (FSW) parameters for 1.6 mm thick 2024T3 aluminum alloy sheets. A 3 × 3 factorial design was employed to explore tool rotation speeds (1100 to 1300 rpm) and welding speeds (140 to 180 mm/min). Static tensile tests revealed the joints' maximum strength at 87% relative to the base material. Hyperparameter optimization was conducted for machine learning (ML) models, including random forest and XGBoost, and multilayer perceptron artificial neural network (MLP-ANN) models, using grid search. Welding parameter optimization and extrapolation were then carried out, with final strength predictions analyzed using response surface methodology (RSM). The ML models achieved over 98% accuracy in parameter regression, demonstrating significant effectiveness in FSW process enhancement. Experimentally validated, optimized parameters resulted in an FSW joint efficiency of 93% relative to the base material. This outcome highlights the critical role of advanced analytical techniques in improving welding quality and efficiency.