Jarosław Sęp

ΞThe dynamic development of hydrogen-powered unmanned aerial vehicles (UAVs) has increased the need for consistent methods to assess their mass–energy characteristics, particularly in multirotor platforms, which are characterised by high and continuous power demand during hover-dominated...

This article presents an investigation of the use of machine learning methodologies for the prediction of surface roughness in milling operations, using sensor data as the primary source of information. The sensors, which included current transformers, a microphone, and displacement sensors, captured comprehensive machining signals at a frequency of 10 kHz. The signals were subjected to preprocessing using the Savitzky–Golay filter, with the objective of isolating relevant moments of active material machining and reducing noise. Two machine learning models, namely Elastic Net and neural networks, were employed for the prediction purposes. The Elastic Net model demonstrated effective handling of multicollinearity and reduction in the data dimensionality, while the neural networks, utilizing the ReLU activation function, exhibited the capacity to capture complex, nonlinear patterns. The models were evaluated using the coefficient of determination (R²), which yielded values of 0.94 for Elastic Net and 0.95 for neural networks, indicating a high degree of predictive accuracy. These findings illustrate the potential of machine learning to optimize manufacturing processes by facilitating precise predictions of surface roughness. Elastic Net demonstrated its utility in reducing dimensionality and selecting features, while neural networks proved effective in modeling complex data. Consequently, these methods exemplify the efficacy of integrating data-driven approaches with robust predictive models to improve the quality and efficiency of surface.

This research focuses on the crucial role of monitoring tool conditions in milling to improve workpiece quality, increase production efficiency, and reduce costs and environmental impact. The goal was to develop predictive models for detecting tool condition changes. Data from a sensor-equipped research setup were used for signal analysis during different machining stages. The study applied logistic regression and a gradient boosting classifier for material layer identification, with the latter achieving an impressive 97.46% accuracy. Additionally, the effectiveness of the classifiers was further confirmed through the analysis of ROC (Receiver Operating Characteristic) curves and AUC (Area Under the Curve) values, demonstrating their high quality and precise identification capabilities. These findings support the classifiers’ utility in predicting the condition of cutting tools, potentially reducing raw material consumption and environmental impact, thus promoting sustainable production practices.

In this investigation, an AA2519-T62 FSW butt joint was subjected to shot peening with an air pressure of p = 0.6 MPa, a processing time of t = 10 min (per side), and a steel ball diameter of d_k = 1.5 mm. In order to evaluate the impact of shot peening on the low-cycle behavior, the samples were tested with coefficient R = 0.1 at total strain amplitudes of 0.35%, 0.4%, and 0.5%. The shot-peened welds are characterized by a higher value of stress amplitude, a lower value of plastic strain amplitude, and their fatigue life increased slightly. The cyclic strength coefficient and the cyclic strain hardening exponent were reduced by 45% and 55%, respectively, as the result of the surface layer hardening. The shot peening process had no noticeable effect on the character of crack initiation and propagation. Almost in all cases, the cracking started in the area under the weld face, located close to the boundary between the thermo-mechanically affected zone and the stir zone at the advancing side. Only at the heaviest loadings (ε_ac = 0.5%) were cracks initiated in the heat-affected zone at the retreating side. Despite the introduction of small cracks in the stir zone, their presence did not affect the decohesion character of the welded joint. Overall, it was observed that there is a minimal, positive impact of shot peening on the properties of the investigated joints.

The main purpose of present article is to present the burner rig station newly developed at the Rzeszow University of Technology in Poland. The burner rig is dedicated to operate on fuels rich in hydrogen. The burner rig is able to operate with fuels with hydrogen content up to 50 volume %. A detailed description of burner rig construction is presented. Moreover a mathematical model predicting temperature distribution within the combustion chamber is presented. The obtained results showed a good insulation of burner rig construction leading to the temperature gradient from 1674℃ in the burner rig to 214℃ on steel housing.

Under hard operating conditions such as high load, low speed and a lack of a sufficient quantity of lubricant, the sliding pairs could suffer serious damage. One of the methods that improves the tribological performance of sliding elements in hard operating conditions is the appropriate surface creation that keeps lubricating substance in cavities. This article presents the results obtained in experimental investigations of the oil film thickness in lubricated non-conformal contact with a different surface topography of the sliding element. The tests were conducted on a ball-on-disc instrument equipped with colorimetric interferometry. Balls of diameter equaled to 19.05 mm were produced from 100 Cr6 steel. To provide hard operating conditions, the glass disc rotated at small speeds in the range of 0.1–0.2 m/s. The tests were carried out at loads of 20 N and 30 N. As a result, in most cases, the highest minimum and average oil film thickness values were obtained when the surface of steel balls was characterized by high negative asymmetry with mainly shallow cavities and some valleys of great depth compared to the height of the peaks. The modified sliding surface that had better performance comprised a comparatively small number of peaks and the curvature of the peaks were large.