International Scientific Journals
of Scientific Technical Union of Mechanical Engineering "Industry 4.0"

This study presents a machine learning framework for predicting the mechanical properties of 2xxx series Al-Cu alloys (2024, 2219, 2524) across 11 temper conditions. Monte Carlo augmentation generated 8,800 synthetic samples from compositional specification ranges of a literature-mined dataset. Three regression models, Random Forest, Gradient Boosting, and SVR-RBF were evaluated via 5-fold cross-validation (CV) to predict ultimate tensile strength (UTS), yield strength (YS), and elongation. All models achieved coefficient of determination R² > 0.991, with Mean Absolute Error MAE ≤ 7.4 MPa for UTS, ≤ 5.4 MPa for YS, and ≤ 0.51% for elongation. Feature importance analysis revealed that temper condition encoding dominated predictions (>75% importance), while individual compositional features contributed <5% each. The high predictive accuracy reflects the effectiveness of the augmentation scheme in capturing withingroup property–composition–temper relationships, though generalization to unseen alloy–temper conditions remains to be validated. The results illustrate the potential of combining corpus-mined data with Monte Carlo augmentation for rapid alloy property screening.

This study develops a machine learning framework for predicting the mechanical properties of 6xxx series Al-Mg-Si alloys (6061, 6063, 6082) across seven temper conditions. A hybrid dataset of 860 real measurement-based and 4,200 Monte Carlo augmented samples was generated from a literature-mined dataset. Random Forest (RF), Gradient Boosting (GBR), and Multilayer Perceptron (MLP) models were evaluated via 5-fold cross-validation (CV). RF achieved the best or comparable accuracy: coefficient of determination R² = 0.80 (ultimate tensile strength), 0.92 (yield strength), and 0.83 (elongation). Feature importance analysis showed that alloy type and temper encodings dominated predictions (>90% combined), while individual compositional features contributed <3% a result partly attributable to the augmentation strategy, which decoupled measured compositions from their corresponding property values. Learning curve analysis confirmed model convergence above 2,000 samples.

This study investigates the influence of Al₂ O₃ content on the mechanical properties of sintered Al-10Cu-xAl₂ O₃ (x = 2.5, 5, and 7.5 wt.%) composite materials, produced via powder metallurgy and subjected to quasi-static and dynamic compressive loadings. Quasistatic tests were performed at a constant strain rate of 0.003 s⁻ ¹, while dynamic tests were conducted at strain rates corresponding to impact velocities of approximately 10 m/s and 20 m/s. The results indicate that a higher Al₂ O₃ content enhances the mechanical properties of the composite under both quasi-static and dynamic compression. The most significant improvements were observed under high strain rate impact loading, highlighting the potential of sintered Al-10Cu-xAl₂ O₃ for applications in dynamic environments.

This paper investigates the mechanical behaviour of SnSb11Cu6 Babbitt alloys solidified under pressure and under atmospheric conditions. Quasi-static tests were performed at three different constant strain rates: 0.001 s⁻ ¹, 0.003 s⁻ ¹, and 0.01 s⁻ ¹, while dynamic tests were conducted at strain rates corresponding to impact speeds of 10 m/s and 20 m/s. The results indicate that alloys solidified under atmospheric conditions exhibit higher compressive strength in the quasi-static regime than those solidified under pressure. However, as the impact speed increases to 1400 s-1 the compressive strength of both materials converges. Beyond this rate (up to 2800 s⁻ ¹), the alloy solidified under pressure shows a slight performance shift, suggesting better property stability at higher loading rates. Overall, the alloy solidified under atmospheric conditions offers superior performance for low-strain applications, whereas the alloy solidified under pressure demonstrates more stable properties under high-strain loadings. These findings offer valuable insights for the selection and design of materials in tribological systems, particularly where performance varies under different loading conditions.

A modified version of the Split Hopkinson-Kolsky Pressure Bar is described, intended for impact testing of porous metals and other low-strength materials. In it, one bar is made of aluminum alloy and the other bar is a steel tube. Several variants of the mathematical model for working with such devices are described. The stress-strain diagram of the specimen is extracted from the first impact signal. Attention has been paid to the approach to choosing the initial moments from which the calculations must start. Several examples are shown with solid and porous aluminum alloy samples. Despite the lack of high accuracy of the diagram at small stresses, the facility is suitable for quickly obtaining the overall appearance of the diagram after crushing small cylindrical specimens (up to 10 mm in diameter and height) and estimating the stresses at which the material deforms plastically.

This study investigates the mechanical behaviour of Al10Cu materials fabricated through powder metallurgy and subjected to quasi-static and dynamic compressive loadings. The materials were sintered and tested under controlled conditions to evaluate their compressive strength. Quasi-static tests were performed at a constant strain rate of 0.003 s⁻ ¹, while dynamic tests were conducted at strain rates corresponding to impact speeds of about 10 m/s and 20 m/s. The results indicate that sintered Al10Cu materials are suitable for applications under high-strain impact loadings due to their high energy absorption. These findings highlight the potential of powdermetallurgy-derived Al10Cu alloys for applications requiring high strain rate performance, offering insight into their suitability for use in dynamic environments.

Four types of aluminium alloys (two casting and two plastically deformable) were used in the present study. A special press mould for compacting the aluminium alloy chips and subsequent extrusion of the resulting compacts was designed and manufactured. The compressive strength of the obtained samples was investigated, in relation to their chemical composition and technological parameters during their fabrication. The results of the research are presented in tabular and graphic form. It was established that compacted samples from AW-6082, AC-48000 and AW-2024 alloy possess high compression strength (in the range of 766 – 866 MPa) under compression loading at 60% deformation. It seems that the extrusion process improves compression properties of AW-2024 and AC-48000 alloy but has negative effect on AW-6082 and AC-42000.

The fatigue strength of 40X steel at 25 oC was determined following ASTM E606M standard for strain-controlled tests. The studied experimental dependence was modelled with a power function as well as with the functions and coefficients described in the standard. The material expresses plastic properties for cyclic loadings above 0.2% strain amplitude.

The influence of registered signals smoothing on the calculated diagram of the test specimen was analysed for impact test using split Hopkinson-Kolsky pressure bar. Two methods are used to smooth the signals: low-pass filtering built into the software and arithmetic mean averaging. When determining the elastic modulus and the upper yield stress in these high-strain rate tests, it is concluded that more accurate values are obtained by filtering with a cut-off frequency in the range of 60 to 80 kHz. For the second method, it is concluded that it is best to average the curves with an amplitude of 3 or 4 microseconds. Attention is paid to the correct ch oice of the initial moments from which the reading of the signals begins because the wrong choice leads to inaccurate calculations and conclusions about the properties of the tested material.