The material extrusion fused deposition modeling (FDM) technique has become a widely used technique that enables the production of complex parts for various applications. To overcome limitations of PLA material such as low impact toughness, commercially available materials such as UltiMaker Tough PLA were produced to improve the parent PLA material that can be widely applied in many engineering applications. In this study, 3D-printed parts (test specimens) considering six different printing parameters (i.e., layer height, wall thickness, infill density, build plate temperature, printing speed, and printing temperature) are experimentally investigated to understand their impact on the mechanical properties of Tough PLA material. Three different standardized tests of tensile, flexural, and compressive properties were conducted to determine the maximum force and Young’s modulus. These six properties were used as responses in a design of experiment, definitive screening design (DSD), to build six regression models. Analysis of variance (ANOVA) is performed to evaluate the effects of each of the six printing parameters on Tough PLA mechanical properties. It is shown that all regression models are statistically significant ($p<0.05$) with high values of adjusted and predicted $R^2$. Conducted confirmation tests resulted in low relative errors between experimental and predicted data, indicating that the developed models are adequately accurate and reliable for the prediction of tensile, flexural, and compressive properties of Tough PLA material.

The application of additive manufacturing technologies for producing parts from polymer composite materials has gained significant attention due to the ability to create fully functional components that leverage the advantages of both polymer matrices and fiber reinforcements while maintaining the benefits of additive technology. Polymer composites are among the most advanced and widely used composite materials, offering high strength and stiffness with low mass and variable resistance to different media. This study aims to experimentally investigate the impact of selected process parameters, namely, wall thickness, raster angle, printing temperature, and build plate temperature, on the flexural properties of carbon fiber reinforced polyamide (CFrPA) fused deposition modeling (FDM) printed samples, as per ISO 178 standards. Additionally, regression and artificial neural network (ANN) models have been developed to predict these flexural properties. ANN models are developed for both normal and augmented inputs, with the architecture and hyperparameters optimized using random search technique. Response surface methodology (RSM), which is based on face centered composite design, is employed to analyze the effects of process parameters. The RSM results indicate that the raster angle and build plate temperature have the greatest impact on the flexural properties, resulting in an increase of 51% in the flexural modulus. The performance metrics of the optimized RSM and ANN models, characterized by low MSE, RMSE, MAE, and MAPE values and high R² values, suggest that these models provide highly accurate and reliable predictions of flexural strength and modulus for the CFrPA material. The study revealed that ANN models with augmented inputs outperform both RSM models and ANN models with normal inputs in predicting these properties.

Waste management is significant for achieving climate goals, considering its contribution to global greenhouse gas emissions. While differences in waste management systems and generation rates across European countries are closely linked to socio-economic, demographic, and environmental factors, previous studies have predominantly focused on specific regions or local municipalities. This study addresses this gap by analyzing Europe as a single entity, providing an overview of the current waste management practices and legislation, assessing influencing factors and employing machine learning (ML) models for MSW generation rates estimation. A comprehensive dataset includes 14 socio-economic, demographic and environmental factors collected for 40 European countries over 2000-2021. To capture regional differences more effectively, the countries were further grouped, and separate models were developed in addition to the general model. Three ML models, namely Artificial Neural Network (ANN), Support Vector Regression (SVR), and Kernel Ridge Regression (KRR) were developed and evaluated. SHAP (SHapley Additive exPlanations) analysis was applied to assess the contribution of individual factors to the predictions of MSW generation rates. Despite being trained on heterogeneous data, all models demonstrated high predictive ability. In all developed models, KRR demonstrated the best performances for the general model and for models for high, medium and low-income countries. The most significant variable in estimating MSW generation rates is average annual wages. The findings of this study may help in bridging the gap between EU and non-EU countries, emphasizing the necessity for robust environmental policies and cross-national collaboration.