The mechanical properties of a directionally solidified (DS) TiAl alloy were predicted through a random forest regression (RFR) machine learning algorithm. The prediction results were evaluated using ...the R2 value. As a result, the R2 values of prediction for the tensile strength, elongation, nanoindentation hardness, and interlamellar space were 0.9336, 0.9902, 0.8104, and 0.9810, respectively. To observe the correlation between the microstructure and mechanical properties, RFR prediction was conducted with a double input variable. This yielded a R2 value of tensile strength of 0.9856, which was higher than the tensile strength derived with a single input variable. The R2 value of nanoindentation hardness increased to 0.9902, which was higher than the nanoindentation hardness value with a single input variable. Through the use of the double input variables, the relationships among tensile strength and elongation, nanoindentation hardness, and interlamellar space were observed. Using feature importance, which could not be obtained in a previous study using the MLR algorithm, it was possible to determine which input variable had the most efficiency with respect to the output variable. Based on these research results, the speed and accuracy of new alloy development specifically in the design and processing, can be increased. In addition, metallurgical research on the relationship between the interlamellar space and mechanical properties was conducted, and the relationship was verified through the results of machine learning training.
Low Cu and Ag additions (≤0.10at%) were found to strongly affect the age-hardening behavior in AlMgSi alloys with Mg+Si>1.5at%. The hardness increased during aging at 170°C and the formation of β″ ...precipitates was kinetically accelerated. The activation energy of the formation of the β″ phase was calculated to 127, 105, 108 and 99KJmol−1 in the base, Cu-added, Ag-added and CuAg-added alloys, respectively using the Kissinger method. The negative effect of two-step aging caused by the formation of Cluster (1) during natural aging was not overcome by the addition of microalloying elements. However, it was suppressed by the formation of Cluster (2) through a pre-aging at 100°C. Quantitative analysis of the precipitate microstructure was performed using a transmission electron microscope equipped with a parallel electron energy loss spectrometer for the determination of specimen thickness. The formation of Cluster (2) was found to increase the number density of β″ precipitates, whereas the formation of Cluster (1) decreased the number density and increased the needle length. The effects of low Cu and Ag additions in combination with multi-step aging are discussed based on microstructure observations and hardness and resistivity measurements.
The effect of Cu contents on nanocluster formation and the two-step aging behavior of Al–Mg–Si alloys was studied based on hardness, DSC and TEM results. The activation energies for the formation of ...Cluster (1) were 61.6, 70.3 and 92.9 kJ/mol for Cu-free, 1Cu (0.1 mass% Cu-added) and 3Cu (0.3 mass% Cu-added), respectively. It was confirmed that hardness increased slowly with increasing Cu content during natural aging for 3.6 ks. These results suggest that the formation kinetics of Cluster (1) decrease due to the vacancy trapping phenomenon, because of the strong interactions of the Cu-vacancies. Meanwhile, the effect of the formation of nanoclusters by Cu addition on the two-step aging behavior at 170 °C during natural aging was analyzed. Hardness at the initial stage of the two-step aging increased with increasing Cu contents. This was caused by the suppression of Cluster (1) formation during natural aging by the Cu additions. Based on TEM results, at the peak hardness of the two-step aging, the number density of precipitates was increased by increasing Cu contents, due to the suppression of nanocluster formation during natural aging.
Graphic Abstract
Nanocluster formation behavior by DSC, two-step aging behavior based on hardness results and precipitation observation at the peak hardness using TEM. Two types of nanoclusters were analyzed using DSC based on Gaussian function method in Al–Mg–Si alloys. The formation of nanoclusters is suppressed during natural aging by Cu additions. Also, the hardness is clearly increased by Cu addition at the initial stage of two-step aging at 170 °C after natural aging for 3.6 ks. Based on TEM results, the number density of precipitates was increased by increasing Cu contents at the peak hardness of the two-step aging due to the suppression of nanocluster formation during natural aging.
Al-4.5Si-1Cu-0.3Mg(-1Fe) (wt%) alloys fabricated by a deformation-semisolid extrusion (D-SSE) process have been investigated by transmission electron microscopy, down to the atomic level. T5 and T6 ...heat treatments were conducted to understand the age-hardening behavior of the alloys. Disordered Mg-Si(-Cu) precipitates with strong Cu enrichments at their interfaces with the Al matrix have been observed in the overaged conditions of both heat treatments and in the peak hardness of the T6 condition, but only Cu-containing atomic clusters were detected in the peak hardness of the T5 heat treatment. Despite having a lower bulk precipitate number density at comparable precipitate size and volume fraction, hardness in the T6 condition was higher in the alloy with highest Fe content due to the extra contribution from the precipitates nucleated on fragmented β-Al5FeSi particles and grain boundaries. Many of these precipitates were Q'-phase, and two new coherent interfaces with the Al matrix are reported for this phase.
•Fragmented β-Al5FeSi particles and grain boundaries act as nucleation sites for the Q' phase.•Two new types of interfaces along the coherent Al direction of the Q' phases have been found.•Cu-containing atomic clusters have been found in the peak hardness of an artificially aged T5 condition.
Compressive strength and compressive strain, which are important mechanical properties of directionally solidified TiAl alloy, were predicted using machine learning algorithms, specifically Multiple ...Linear Regression (MLR), and Random Forest Regression (RFR). The input variables for the machine learning model were designated as the composition of the directionally solidified TiAl alloy, experimental parameters (pulling velocity, input power), and compression test parameters (strain rate, compression temperature). Compressive strength and compressive strain were designated as the output variables. Although the typical ratio of training and test data is 8:2, this study used different ratios of 9:1, 7:3, and 6:4 for machine learning, and excellent R2 values were obtained for all ratios. The feature importance, which can identify the factor that has the most influence on the output variables, was obtained through the RFR algorithm. According to the feature importance, temperature was found to have the greatest influence on compressive strength, while the Erbium (Er) element had the most significant influence on compressive strain. Through the results of feature importance, it was possible to quantitatively investigate the relationship between the Er element, a microalloying element that affects the microstructure of TiAl alloy, and the compressive properties. Furthermore, the study was conducted on which data ratio between training and test data is most suitable for predicting the compressive strength and strain of TiAl alloy.
•The compressive strength and strain of directionally solidified (DS) TiAl alloy were predicted using the random forest regression (RFR) and multiple linear regression (MLR) algorithms.•The predicted values were observed by changing the machine learning training and test size ratio to 9:1, 8:2, 7:3, and 6:4.•Through the feature importance of RFR, the input variable values that have the most influence on the compressive strength and strain results were obtained, and as a result, the correlation between mechanical properties and microstructure was observed.•It was obtained that the 8:2 ratio was most suitable for predicting the compressive strength and strain of DS TiAl alloy.
As the environmental pollution issue has recently become significant, environmental regulations in Europe and the United States are being strengthened. Thus, there is a demand for the quality ...improvement of emission after-treatment systems to satisfy the strengthened environmental regulations. Reducing the amount of welding heat distortion by optimization of the welding order of each part could be a solution for quality improvement since the emission after-treatment system consists of many parts and each assembly is produced by welding individual ones. In this research, a method to derive a welding sequence that effectively minimizes welding deformation was proposed. A two-stage simulation was performed to obtain the optimal welding sequence. In the first stage, the welding sequence was derived by analyzing the number of welding groups in each assembly of a structure. The derived welding sequence was verified by performing a thermal elasto-plastic analysis and comparing it with the experimental results.
Defect-free T-joints of Al–Mg–Si plates were successively welded using a friction stir welding (FSW) process. Multi-scale microstructure analysis was performed to investigate the metallography of FSW ...T-joints and comprehend the clustering behavior of base metals (BM) and stir zones (SZ). The mechanical properties of T-joints were evaluated during post–weld heat treatment (PWHT) using tensile tests.
BM with a 47.3 μm average grain size was transformed into approximately 2.6 μm fine equiaxed grains in the SZ. Simultaneously, dissolution of clusters and/or precipitates in the SZ was related to the decrement of the mechanical properties of the joints. Softening was confirmed in the SZ due to the peak-heat by friction stirring of the FSW tool. Thinning of the plate on the advancing side (AS), which was affected by the shoulder zone of the FSW tool, acts as a weak spot for crack initiation. There was a cup and cone fracture on heat affected zones (HAZ) of the plate in the AS.
Nanocluster formation was quantitatively analyzed during PWHT using a three-dimensional atom probe (3DAP). Small nanoclusters with approximately 0.6 nm were dominantly formed in the SZ than the BM. Nanoclusters with higher Mg/(Mg + Si) were predominantly generated in the BM. The number densities of the clusters in the BM and SZ were 15.10 × 1023 m−3 and 38.60 × 1023 m−3, respectively. This study confirmed that FSW facilitates better the formation of refined nanoclusters and precipitates in the SZ with smaller size and higher number density compared to BM.