Bayesian techniques are vital in mechanical manufacturing for uncertainty quantification and process optimization. This review explores their diverse applications, highlighting advantages in handling small data and incorporating expertise for improved decision-making in quality control, reliability, and machining. It also discusses integration with machine learning and applications in specialized areas. Future research should focus on Industry 4.0 integration and user-friendly tools, emphasizing Bayesian methods' role in intelligent manufacturing.

The present study introduces a machine learning approach for designing new aluminum alloys tailored for directed energy deposition additive manufacturing, achieving an optimal balance between hardness and conductivity. Utilizing a comprehensive database of powder compositions, process parameters, and material properties, predictive models—including an artificial neural network and a gradient boosting regression model, were developed. Additionally, a variational autoencoder was employed to model input data distributions and generate novel process data for aluminum-based powders. The similarity between the generated data and the experimental data was evaluated using K-nearest neighbor classification and t-distributed stochastic neighbor embedding, with accuracy and the F1-score as metrics. The results demonstrated a close alignment, with nearly 90% accuracy, in numerical metrics and data distribution patterns. This work highlights the potential of machine learning to extend beyond multi-property prediction, enabling the generation of innovative process data for material design.

This study investigated the effect of the hatch spacing parameter on the microstructure and mechanical properties of SA508 Gr.3 steel manufactured by laser powder bed fusion (L-PBF) for a nuclear pressure vessel. Materials were prepared with varying hatch spacing (0.04 mm [H4] and 0.06 mm [H6]). The H4 exhibited finer and more uniformly distributed grains, while the H6 showed less porosity and a lower defect fraction. The yield strength of the H4 material was higher than that of the H6 material, but there was a smaller difference between the materials in tensile strength. The measured elongation was 5.65% for the H4 material and 10.41% for the H6 material, showing a significantly higher value for H6. An explanation for this is that although the H4 material had a microstructure of small and uniform grains, it contained larger and more numerous pore defects than the H6 material, facilitating stress concentration and the initiation of microcracks.

A cold roll-bonding (CRB) process is applied to fabricate an AA1050/AA5052 layered sheet. In the process, commercial AA1050 and AA5052 sheets of 1 mm thickness, 40 mm width and 300 mm length are stacked onto each other, and then reduced to a thickness of 0.5 mm through a 2-pass cold rolling process without lubricant. The roll-bonded AA1050/AA5052 layered sheet is then annealed for 1 h at various temperatures from 200 to 400 °C. The specimens annealed at temperatures below 250 °C showed a typical deformation structure in which the grains were elongated along the rolling direction. However, the specimens annealed at temperatures higher than 300 °C exhibited recrystallization structures in both the AA1050 and AA5052 regions. All the roll-bonded and subsequently annealed specimens showed an inhomogeneous distribution of hardness in the thickness direction, in which the hardness in the AA5052 regions was higher than that in the AA1050 regions. As the annealing temperature increased, the tensile and yield strengths decreased and the elongation increased gradually. The mechanical properties were compared to those of commercial AA1050 and AA5052 materials and CRBed AA5052-2L materials from a previous study.

This study develops a machine learning-based tool life prediction model using spindle power data collected from real manufacturing environments. The primary objective is to monitor tool wear and predict optimal replacement times, thereby enhancing manufacturing efficiency and product quality in smart factory settings. Accurate tool life prediction is critical for reducing downtime, minimizing costs, and maintaining consistent product standards. Six machine learning models, including Random Forest, Decision Tree, Support Vector Regressor, Linear Regression, XGBoost, and LightGBM, were evaluated for their predictive performance. Among these, the Random Forest Regressor demonstrated the highest accuracy with R2 value of 0.92, making it the most suitable for tool wear prediction. Linear Regression also provided detailed insights into the relationship between tool usage and spindle power, offering a practical alternative for precise predictions in scenarios with consistent data patterns. The results highlight the potential for real-time monitoring and predictive maintenance, significantly reducing downtime, optimizing tool usage, and improving operational efficiency. Challenges such as data variability, real-world noise, and model generalizability across diverse processes remain areas for future exploration. This work contributes to advancing smart manufacturing by integrating data-driven approaches into operational workflows and enabling sustainable, cost-effective production environments.

In this study, Ni-Y2O3 powder was prepared by alloying recomposition oxidation sintering (AROS), solution combustion synthesis (SCS), and conventional mechanical alloying (MA). The microstructure and mechanical properties of the alloys were investigated by spark plasma sintering (SPS). Among the Ni-Y2O3 powders synthesized by the three methods, the AROS powder had approximately 5 nm of Y2O3 crystals uniformly distributed within the Ni particles, whereas the SCS powder contained a mixture of Ni and Y2O3 nanoparticles, and the MA powder formed small Y2O3 crystals on the surface of large Ni particles by milling the mixture of Ni and Y2O3. The average grain size of Y2O3 in the sintered alloys was approximately 15 nm, with the AROS sinter having the smallest, followed by the SCS sinter at 18 nm, and the MA sinter at 22 nm. The yield strength (YS) of the SCS- and MA-sintered alloys were 1511 and 1688 MPa, respectively, which are lower than the YS value of 1697 MPa for the AROS-sintered alloys. The AROS alloy exhibited improved strength compared to the alloys fabricated by SCS and conventional MA methods, primarily because of the increased strengthening from the finer Y2O3 particles and Ni grains.

YSZ (Y2O3-stabilized zirconia)-based ceramics have excellent mechanical properties, such as high strength and wear resistance. In the application, YSZ is utilized in the bead mill, a fine-grinding process. YSZ-based parts, such as the rotor and pin, can be easily damaged by continuous application with high rpm in the bead mill process. In that case, adding WC particles improves the tribological and mechanical properties. YSZ-30 vol.% WC composite ceramics are manufactured via hot pressing under different pressures (10/30/60 MPa). The hot-pressed composite ceramics measure the physical properties, such as porosity and bulk density values. In addition, the phase formation of these composite ceramics is analyzed and discussed with those of physical properties. For the increased applied pressure of hot pressing, the tetragonality of YSZ and the crystallinity of WC are enhanced. The mechanical properties indicate an improved tendency with the increase in the applied pressure of hot pressing.

Boron carbide (B4C) is highly significant in the production of lightweight protective materials when added to aluminum owing to its exceptional mechanical properties. In this study, a method for fabricating Al-B4C composites using high-energy ball milling and directed energy deposition (DED) is presented. Al-4 wt.% B4C composites were fabricated under 21 different laser conditions to analyze the microstructure and mechanical properties at different values of laser power and scan speeds. The composites fabricated at a laser power of 600 W and the same scan speed exhibited the highest hardness and generated the fewest pores. In contrast, the composites fabricated at a laser power of 1000 W exhibited the lowest hardness and generated a significant number of large pores. This can be explained by the influence of the microstructure on the energy density at different values of laser power.

Metal additive manufacturing (AM) has transformed conventional manufacturing processes by offering unprecedented opportunities for design innovation, reduced lead times, and cost-effective production. Aluminum alloy, a material used in metal 3D printing, is a representative lightweight structural material known for its high specific strength and corrosion resistance. Consequently, there is an increasing demand for 3D printed aluminum alloy components across industries, including aerospace, transportation, and consumer goods. To meet this demand, research on alloys and process conditions that satisfy the specific requirement of each industry is necessary. However, 3D printing processes exhibit different behaviors of alloy elements owing to rapid thermal dynamics, making it challenging to predict the microstructure and properties. In this study, we gathered published data on the relationship between alloy composition, processing conditions, and properties. Furthermore, we conducted a sensitivity analysis on the effects of the process variables on the density and hardness of aluminum alloys used in additive manufacturing.

Although the Ti–6Al–4V alloy has been used in the aircraft industry owing to its excellent mechanical properties and low density, the low formability of the alloy hinders broadening its applications. Recently, laser-powder bed fusion (L-PBF) has become a novel process for overcoming the limitations of the alloy (i.e., low formability), owing to the high degree of design freedom for the geometry of products having outstanding performance used in hightech applications. In this study, to investigate the effect of bulk shape on the microstructure and mechanical properties of L-PBFed Ti-6Al-4V alloys, two types of samples are fabricated using L-PBF: thick and thin samples. The thick sample exhibits lower strength and higher ductility than the thin sample owing to the larger grain size and lower residual dislocation density of the thick sample because of the heat input during the L-PBF process.

In this study, a graphite block is fabricated using artificial graphite processing byproduct and phenolic resin as raw materials. Mechanical and electrical property changes are confirmed due to the preforming method. After fabricating preforms at 50, 100, and 150 MPa, CIP molding at 150 MPa is followed by heat treatment to prepare a graphite block. 150UP-CIP shows a 12.9% reduction in porosity compared with the 150 MPa preform. As the porosity is decreased, the bulk density, flexural strength, and shore hardness are increased by 14.9%, 102.4%, and 13.7%, respectively; and the deviation of density and electrical resistivity are decreased by 51.9% and 34.1%, respectively. Therefore, as the preforming pressure increases, the porosity decreases, and the electrical and mechanical properties improve.

Tungsten disulfide (WS2) nanosheets have attracted considerable attention because of their unique optical and electrical properties. Several methods for fabrication of WS2 nanosheets have been developed. However, methods for mass production of high-quality WS2 nanosheets remain challenging. In this study, WS2 nanosheets were fabricated using mechano-chemical ball milling based on the synergetic effects of chemical intercalation and mechanical exfoliation. The ball-milling time was set as a variable for the optimized fabricating process of WS2 nanosheets. Under the optimized conditions, the WS2 nanosheets had lateral sizes of 500–600 nm with either a monolayer or bilayer. They also exhibited high crystallinity in the 2H semiconducting phase. Thus, the proposed method can be applied to the exfoliation of other transition metal dichalcogenides using suitable chemical intercalants. It can also be used with highperformance WS2-based photodiodes and transistors used in practical semiconductor applications.

In this study, additive manufacturing of a functionally graded material (FGM) as an alternative to joining dissimilar metals is investigated using directed energy deposition (DED). FGM consists of five different layers, which are mixtures of austenitic stainless steel (type 316 L) and low-alloy steel (LAS, ferritic steel) at ratios of 100:0 (A layer), 75:25 (B layer), 50:50 (C layer), 25:75 (D layer), and 0:100 (E layer), respectively, in each deposition layer. The FGM samples are successfully fabricated without cracks or delamination using the DED method, and specimens are characterized using optical and scanning electron microscopy to monitor their microstructures. In layers C and D of the sample, the tensile strength is determined to be very high owing to the formation of ferrite and martensite structures. However, the elongation is high in layers A and B, which contain a large fraction of austenite.

A Cu-15Ag-5P filler metal (BCuP-5) is fabricated on a Ag substrate using a high-velocity oxygen fuel (HVOF) thermal spray process, followed by post-heat treatment (300oC for 1 h and 400oC for 1 h) of the HVOF coating layers to control its microstructure and mechanical properties. Additionally, the microstructure and mechanical properties are evaluated according to the post-heat treatment conditions. The porosity of the heat-treated coating layers are significantly reduced to less than half those of the as-sprayed coating layer, and the pore shape changes to a spherical shape. The constituent phases of the coating layers are Cu, Ag, and Cu-Ag-Cu3P eutectic, which is identical to the initial powder feedstock. A more uniform microstructure is obtained as the heat-treatment temperature increases. The hardness of the coating layer is 154.6 Hv (as-sprayed), 161.2 Hv (300oC for 1 h), and 167.0 Hv (400oC for 1 h), which increases with increasing heat-treatment temperature, and is 2.35 times higher than that of the conventional cast alloy. As a result of the pull-out test, loss or separation of the coating layer rarely occurs in the heat-treated coating layer.

The CoCrFeMnNi high-entropy alloy (HEA), which is the most widely known HEA with a single facecentered cubic structure, has attracted significant academic attention over the past decade owing to its outstanding multifunctional performance. Recent studies have suggested that CoCrFeMnNi-type HEAs exhibit excellent printability for selective laser melting (SLM) under a wide range of process conditions. Moreover, it has been suggested that SLM can not only provide great topological freedom of design but also exhibit excellent mechanical properties by overcoming the strength–ductility trade-off via producing a hierarchical heterogeneous microstructure. In this regard, the SLM-processed CoCrFeMnNi HEA has been extensively studied to comprehensively understand the mechanisms of microstructural evolution and resulting changes in mechanical properties. In this review, recent studies on CoCrFeMnNi-type HEAs produced using SLM are discussed with respect to process-induced microstructural evolution and the relationship between hierarchical heterogeneous microstructure and mechanical properties.

Oxide dispersion-strengthened (ODS) steel has excellent high-temperature properties, corrosion resistance, and oxidation resistance, and is expected to be applicable in various fields. Recently, various studies on mechanical alloying (MA) have been conducted for the dispersion of oxide particles in ODS steel with a high number density. In this study, ODS steel is manufactured by introducing a complex milling process in which planetary ball milling, cryogenic ball milling, and drum ball milling are sequentially performed, and the microstructure and high-temperature mechanical properties of the ODS steel are investigated. The microstructure observation revealed that the structure is stretched in the extrusion direction, even after the heat treatment. In addition, transmission electron microscopy (TEM) analysis confirmed the presence of oxide particles in the range of 5 to 10 nm. As a result of the room-temperature and high-temperature compression tests, the yield strengths were measured as 1430, 1388, 418, and 163 MPa at 25, 500, 700, and 900oC, respectively. Based on these results, the correlation between the microstructure and mechanical properties of ODS steel manufactured using the composite milling process is also discussed.

In this study, a nanocrystalline FeNiCrMoMnSiC alloy was fabricated, and its austenite stability, microstructure, and mechanical properties were investigated. A sintered FeNiCrMoMnSiC alloy sample with nanosized crystal was obtained by high-energy ball milling and spark plasma sintering. The sintering behavior was investigated by measuring the displacement according to the temperature of the sintered body. Through microstructural analysis, it was confirmed that a compact sintered body with few pores was produced, and cementite was formed. The stability of the austenite phase in the sintered samples was evaluated by X-ray diffraction analysis and electron backscatter diffraction. Results revealed a measured value of 51.6% and that the alloy had seven times more austenite stability than AISI 4340 wrought steel. The hardness of the sintered alloy was 60.4 HRC, which was up to 2.4 times higher than that of wrought steel.

The effects of different spray angles (90°, 85°, 80°) on the microstructure and mechanical properties of a Y2O3 coating layer prepared using the atmospheric plasma spray (APS) process were studied. The powders employed in this study had a spherical shape and included a cubic Y2O3 phase. The APS coating layer exhibited the same phase as the powders. Thickness values of the coating layers were 90°: 203.7 ± 8.5 μm, 85°: 196.4 ± 9.6 μm, and 80°: 208.8 ± 10.2 μm, and it was confirmed that the effect of the spray angle on the thickness was insignificant. The porosities were measured as 90°: 3.9 ± 0.85%, 85°: 11.4 ± 2.3%, and 80°: 12.7 ± 0.5%, and the surface roughness values were 90°: 5.9 ± 0.3 μm, 85°: 8.5 ± 1.1 μm, and 80°: 8.5 ± 0.4 μm. As the spray angle decreased, the porosity increased, but the surface roughness did not show a significant difference. Vickers hardness measurements revealed values of 90°: 369.2 ± 22.3, 85°: 315.8 ± 31.4, and 80°: 267.1 ± 45.1 HV. It was found that under the condition of a 90° angle with the lowest porosity exhibited the best hardness value. Based on the aforementioned results, an improved method for the APS Y2O3 coating layer was also discussed.