Optimization of cooling rate of Q-P treated 42SiCr steel using AI digital twinning.

In the continuously advancing field of mechanical engineering, digitalization is bringing a major transformation, specifically with the concept of digital twins. Digital twins are dynamic digital models of real-world systems and processes, crucial for Industry 4.0 and the emerging Industry 5.0, which are changing how humans and machines work together in manufacturing. This paper explores the combination of physics-based and data-driven modeling using advanced Artificial Intelligence (AI) and Machine Learning (ML) techniques. This approach provides a comprehensive understanding of mechanical systems, improving materials design and manufacturing processes. The focus is on the advanced 42SiCr alloy, where AI-driven digital twinning is used to optimize cooling rates during Quenching and Partitioning (Q-P) treatments. This leads to significant improvements in the mechanical properties of 42SiCr steel. Given its complex properties influenced by various factors, this alloy is perfect for digital twinning. The Q-P heat treatment process not only restores the material's deformability but also gives it advanced high-strength steel (AHSS) properties. The findings show how AI and ML can effectively guide the development of high-strength steels and enhance their treatment processes. Additionally, integrating digital twins with new technologies like the Metaverse offers exciting possibilities for simulated production, remote monitoring, and collaborative design. By establishing a clear workflow from physical to digital twins and presenting empirical results, this paper connects theoretical modeling with practical applications, paving the way for smarter manufacturing solutions in mechanical engineering. Furthermore, this paper analyzes how digital twins can be integrated into advanced technologies like the Metaverse, opening up new possibilities for simulated production, remote monitoring, design collaboration, training simulations, analytics, and complete supply chain visibility. This integration is a crucial step toward realizing the full potential of digitalization in mechanical engineering.

The Optimization of Mechanical Alloying Conditions of Powder for the Preparation of a Fe-10Al-4Cr-4Y2O3 ODS Nanocomposite.

Mechanical alloying (MA) of powders represents the first processing step in the production of oxide dispersion-strengthened (ODS) alloys. MA is a time and energy-consuming process also in the production of Fe-10Al-4Cr-4Y2O3 creep and oxidation-resistant ODS nanocomposite, denoted as the FeAlOY, and it deserves to be optimized. MA is performed at two different temperatures at different times. The powder after MA, as well as the microstructure and high-temperature strength of the final FeAlOY, are characterized and the optimal MA conditions are evaluated. The obtained results show that the size distribution of the powder particles, as well as the dissolution and homogenization of the Y2O3, becomes saturated quite soon, while the homogenization of the metallic components, such as Al and Cr, takes significantly more time. The high-temperature tensile tests and grain microstructures of the secondary recrystallized FeAlOY, however, indicate that the homogenization of the metallic components during MA does not influence the quality of the FeAlOY, as the matrix of the FeAlOY is sufficiently homogenized during recrystallization. Thus, the conditions of MA correspond to sufficient dissolution and homogenization of Y2O3 and can be considered the optimal ones.

Substantial Improvement of High Temperature Strength of New-Generation Nano-Oxide-Strengthened Alloys by Addition of Metallic Yttrium.

Oxide-dispersion-strengthened (ODS) Fe-Al-Y2O3-based alloys (denoted as FeAlOY) containing 5 vol. % of nano-oxides have a potential to become top oxidation and creep-resistant alloys for applications at temperatures of 1100-1300 °C. Oxide dispersoids cause nearly perfect strengthening of grains; thus, grain boundaries with limited cohesive strength become the weak link in FeAlOY in this temperature range. One of the possibilities for significantly improving the strength of FeAlOY is alloying with appropriate elements and increasing the cohesive strength of grain boundaries. Nearly 20 metallic elements have been tested with the aim to increase cohesive strength in the frame of preliminary tests. A positive influence is revealed for Al, Cr, and Y, whereby the influence of Y is enormous (addition of 1% of metallic Y increases strength by a factor of 2), as it is presented in this paper.

Development of Machine Learning Models to Evaluate the Toughness of OPH Alloys.

Oxide Precipitation-Hardened (OPH) alloys are a new generation of Oxide Dispersion-Strengthened (ODS) alloys recently developed by the authors. The mechanical properties of this group of alloys are significantly influenced by the chemical composition and appropriate heat treatment (HT). The main steps in producing OPH alloys consist of mechanical alloying (MA) and consolidation, followed by hot rolling. Toughness was obtained from standard tensile test results for different variants of OPH alloy to understand their mechanical properties. Three machine learning techniques were developed using experimental data to simulate different outcomes. The effectivity of the impact of each parameter on the toughness of OPH alloys is discussed. By using the experimental results performed by the authors, the composition of OPH alloys (Al, Mo, Fe, Cr, Ta, Y, and O), HT conditions, and mechanical alloying (MA) were used to train the models as inputs and toughness was set as the output. The results demonstrated that all three models are suitable for predicting the toughness of OPH alloys, and the models fulfilled all the desired requirements. However, several criteria validated the fact that the adaptive neuro-fuzzy inference systems (ANFIS) model results in better conditions and has a better ability to simulate. The mean square error (MSE) for artificial neural networks (ANN), ANFIS, and support vector regression (SVR) models was 459.22, 0.0418, and 651.68 respectively. After performing the sensitivity analysis (SA) an optimized ANFIS model was achieved with a MSE value of 0.003 and demonstrated that HT temperature is the most significant of these parameters, and this acts as a critical rule in training the data sets.

Strain-rate sensitive ductility in a low-alloy carbon steel after quenching and partitioning treatment.

We investigate an extraordinarily high ductility in a low alloy carbon steel at an elevated temperature after a quenching and partitioning (Q&P) treatment. The conventional (quenched and tempered) reference material does not show similar behavior. Interestingly, the Q&P treated material's ductility is considerably reduced at increasing strain rates while strength remains almost constant. These results indicate the presence of a diffusion-controlled deformation mechanism at elevated temperatures. Our research shows that interlath retained austenite is more stable during deformation at higher temperatures, resulting in a delayed transformation to martensite and therefore to a more pronounced contribution to plastic deformation at (and in the vicinity of) the many interfaces inherently present in this multi-phase steel.