Machine learning (ML) is one of the artificial intelligence tools which uses past data to learn the relationship between input and output and helps to predict future trends. Powder bed fusion additive manufacturing (PBF-AM) is extensively used for a wide range of applications in the industry. The AM process establishment for new material is a crucial task with trial-and-error approaches. In this work, ML techniques have been applied for the prediction of the density of PBF-AM. Density is the most vital property in evaluating the overall quality of the AM building part. The ML techniques, namely, artificial neural network (ANN), K-nearest neighbor (KNN), support vector machine (SVM), and linear regression (LR), are used to develop a model for predicting the density of the stainless steel (SS) 316L build part. These four methods are validated using R-squared values and different error functions to compare the predicted result. The ANN and SVM model performed well with the R-square value of 0.95 and 0.923, respectively, for the density prediction. The ML models would be beneficial for the prediction of the process parameters. Further, the developed ML model would also be helpful for the future application of ML in additive manufacturing.

The effects of build orientation and heat treatment on the crack growth behavior of 316L stainless steel (SS) fabricated via a selective laser melting additive manufacturing process were investigated. Available research results on additively manufactured metallic parts still require a substantial expansion. The most important issue connected with the metal properties after additive manufacturing are the high anisotropy properties, especially from the fatigue point of view. The study examined the crack growth behavior of additively manufactured 316L in comparison to a conventionally made reference material. Both groups of samples were obtained using precipitation heat treatment. Different build orientations in the additively manufactured samples and rolling direction in the reference samples were taken into account as well. Precipitation heat treatment of additively manufactured parts allowed one to achieve microstructure and tensile properties to similar to those of conventionally made pieces. The heat treatment positively affected the fatigue properties. Additionally, precipitation heat treatment of additively manufactured elements significantly affected the reduction of fatigue cracking velocity and changed the fatigue cracking mechanism.

In this paper, the influence of disinfection on structural and mechanical properties of additive manufactured (AM) parts was analyzed. All AM parts used for a fight against COVID19 were disinfected using available methods—including usage of alcohols, high temperature, ozonation, etc.—which influence on AM parts properties has not been sufficiently analyzed. During this research, three types of materials dedicated for were tested in four different disinfection times and two disinfection liquid concentrations. It has been registered that disinfection liquid penetrated void into material’s volume, which caused an almost 20% decrease in tensile properties in parts manufactured using a glycol-modified version of polyethylene terephthalate (PETG).

The research shows the comparison between two types of polyamide-based (PA) composites and pure, base material. The conducted analysis describes how the additions of carbon fibers and glass microbeads affect the material’s properties and its behavior during the bending tests. All samples have been tested in the three main directions available during the FFF process. To extend the scope of the research, additional digital-image-correlation tests and fracture analyses were made. The obtained results indicated a positive influence of the addition of carbon fibers into the material’s volume (from 81.39 MPa in the case of pure PA to 243.62 MPa in the case of the PA reinforced by carbon fibers).

The significant growth of Additive Manufacturing (AM), visible over the last ten years, has driven an increase in demand for small gradation metallic powders of a size lower than 100 µm. Until now, most affordable powders for AM have been produced using gas atomization. Recently, a new, alternative method of powder production based on ultrasonic atomization with melting by electric arc has appeared. This paper summarizes the preliminary research results of AM samples made of two AISI 316L steel powder batches, one of which was obtained during Ultrasonic Atomization (UA) and the other during Plasma Arc Gas Atomization (PAGA). The comparison starts from powder particle statistical distribution, chemical composition analysis, density, and flowability measurements. After powder analysis, test samples were produced using AM to observe the differences in microstructure, porosity, and hardness. Finally, the test campaign covered an analysis of mechanical properties, including tensile testing with Digital Image Correlation (DIC) and Charpy’s impact tests. A comparative study of parts made of ultrasonic and gas atomization powders confirms the likelihood that both methods can deliver material of similar properties.