Łukasiewicz Research Network - Metal Forming Institute

This study presents the first application of Machine Learning (ML) models to optimise Powder Bed Fusion using Laser Beam (PBF-LB) process parameters for H13 steel fabricated on a 350 °C preheated building platform. A total of 189 cylindrical specimens were produced for training and testing machine learning (ML) models using variable process parameters: laser power (250-350 W), scanning speed (1050-1300 mm/s), and hatch spacing (65-90 μm). Eight ML models were investigated: 1. Support Vector Regression (SVR), 2. Kernel Ridge Regression (KRR), 3. Stochastic Gradient Descent Regressor, 4. Random Forest Regressor (RFR), 5. Extreme Gradient Boosting (XGBoost), 6. Extreme Gradient Boosting with limited depth (XGBoost LD), 7. Extra Trees Regressor (ETR) and 8. Light Gradient Boosting Machine (LightGBM). All models were trained using the Fast Library for Automated Machine Learning & Tuning (FLAML) framework to predict the relative density of the fabricated samples. Among these, the XGBoost model achieved the highest predictive accuracy, with a coefficient of determination R2=0.977, mean absolute percentage error MAPE = 0.002, and mean absolute error MAE = 0.017. Experimental validation was conducted on 27 newly fabricated samples using ML predicted process parameters. Relative densities exceeding 99.6% of the theoretical value (7.76 g/cm3) for all models except XGBoost LD and KRR. The lowest MAE = 0.004 and the smallest difference between the ML-predicted and PBF-LB validated density were obtained for samples made with LightGBM-predicted parameters. Those samples exhibited a hardness of 604 ± 13 HV0.5, which increased to approximately 630 HV0.5 after tempering at 550 °C. The LightGBM optimised parameters were further applied to fabricate a part of a forging die incorporating internal through-cooling channels, demonstrating the efficacy of machine learning-guided optimisation in achieving dense, defect-free H13 components suitable for industrial applications.

According to the results of the analysis, it was revealed that the rigid binding of the shell’s parts surface of the skins to the bypass-forming contours of the coverage does not allow us to detect some properties of circulation associated with their internal geometry, regardless of the three-dimensional space of the coverage itself. If the surface of the shell part is sheathed beyond the lines of curvature in specifying orthogonal coordinate lines, then the shape of the stretch punch can be similarly characterized by changing the geometry of the Earth's surface. In this case, the orientability of the surface of the tight punch relative to the main line of curvature along the shaping contour, the direction of which is determined by the direction of the impact during tightening. Such a coincidence is found when monitoring the symmetrical development of focal deformation and the predominant formation of a plastic deformation zone in the foci of partial sheet deformation. As a result of solving the problem of shaping the shell parts of the skins by tightening, which is found to be detected in various sheets of the workpiece and the absence of wrinkles and ruptures.

This paper presents an innovative solution in the form of a virtual reality (VR) and high performance computing (HPC) system dedicated to aid designing rotary forming processes with laser beam reheating the material formed. The invented method allowing a virtual machine copy to be coupled with its actual counterpart and a computing engine utilizing GPU processors of graphic NVidia cards to accelerate computing are discussed. The completed experiments and simulations of the 316L stainless steel semi-product spinning process showed that the developed VR-HPC system solution allows the manufacturing process to be effectively engineered and controlled in industrial conditions.

Breakage of joint arthroplasty components are rare, yet during an implant retrieval program we found several cases. In this study we examined the components to determine the causes and mechanisms of breakage of these implants. From our collection of 849 retrievals we selected 682 cases with metal parts (503 hip, 79 knee arthroplasties) and identified fractured components: seven hip resurfacing implants, five total hip replacement stems, one monopolar femoral head, and one modular revision femoral stem from. Implants were examined using optical and scanning electron microscopy; metallographic sections were prepared and samples of periprosthetic tissues underwent microscopic examination. In the resurfacing components breakage occurred in small stems placed in the femoral neck due to necrosis of femoral heads, with no metal flaws detected. Fatigue breakage of femoral stems was caused by presence of material flaws in the CoCrMo alloy, and corrosion. The monopolar head failed in fatigue fracture mechanism, breakage was initiated in an undercut near the taper connection for femoral component. The modular stem from Ti alloy sustained fatigue fracture induced by corrosion caused by debris from previously revised stem; no material flaws were detected in this sample. In most cases periprosthetic tissues had a morphology typical for aseptic loosening. In our series failure was caused by material flaws, presence of stress raisers and localized corrosion. Our findings indicate that sharp edges and other features which can act as stress raisers should be avoided in newly designed implants. Corrosion induced fracture of the modular Ti stem indicates the need for a detailed debridement of periprosthetic tissues during revision arthroplasties.

Abstract This paper presents the results of the study aimed at determination of plasticity of selected grades of hard-deformed aluminium alloys of 5xxx series in terms of parameters characteristic for the process of extrusion. The examinations were carried out for 5083 and 5754 alloys in the torsion test using STD 812 torsion plastometer. Using the empirical tests, the study evaluated yield stress of alloys depending on strain, strain rate and temperature and the results were approximated and mathematical models of rheological properties of the aluminium grades studied were determined within the range of parameters of deformation and temperature.