The flow stress behavior of Mg-3Sn-1Mn alloy during thermal compression deformation was systematically studied. The thermal compression simulation experiment was carried out at different deformation temperatures and different strain rates in the range of 523-673K and 0.001-1s-1, respectively. It is found that at low temperature and high strain rate, a large number of twins generated at the early stage of thermal deformation, causing an increase in the corresponding flow stress level, which makes the traditional constitutive relation model insensitive to predicting the thermal deformation behavior of Mg alloys with twinning effect. To better evaluate the rheological behavior of Mg alloys, an artificial neural network model based on feedforward and backpropagation algorithm was developed to predict the thermal deformation behavior of Mg-3Sn-1Mn alloy affected by twinning phenomena. The inputs of the model were deformation temperature, strain rate, and strain, and the output was flow stress. The comparative evaluation of the obtained results using statistical standard R2 and relative error [[EQUATION]] . The correlation coefficient of constitutive model prediction was 0.964 and 0.869 respectively at low stress and high stress, and the correlation coefficient of neural network prediction was 0.992. The result shows that the trained ANN is more accurate than the traditional constitutive relation model in predicting the thermal deformation behavior with twinning effect.
The flow stress behavior of Mg–3Sn–1Mn alloy during thermal compression deformation was systematically studied. The thermal compression simulation experiment was carried out at different deformation temperatures and different strain rates in the range of 523–673 K and 0.001-1s−1, respectively. It is found that at low temperatures and high strain rates, a large number of twins were generated at the initial stage of thermal deformation, causing an increase in the corresponding flow stress, which makes the traditional constitutive relation model insensitive to predicting the thermal deformation behavior of Magnesium (Mg) alloys with twinning effect. To better evaluate the rheological behavior of Mg alloys, an artificial neural network (ANN) model based on a feedforward and back-propagation algorithm was developed to predict the thermal deformation behavior of Mg–3Sn–1Mn alloy affected by twinning phenomena. The inputs of the model were deformation temperature, strain rate and strain, the output was the flow stress. The comparative evaluation of the obtained results using statistical standard R2 and relative error R¯. The correlation coefficients predicted by the constitutive model were 0.964 and 0.869 at low and high stress levels, respectively. And the correlation coefficient of the neural network predictive model was 0.992. The result shows that the trained ANN is more accurate than the traditional constitutive relation model in predicting the thermal deformation behavior with the twinning effect.
Abstract AE44-2 magnesium (Mg) alloys were fabricated by gravity casting (GC), high pressure die casting (HPDC), and high vacuum assisted high pressure die casting (HVHPDC). The effect of these three different casting techniques on the microstructure evolution, texture, and mechanical properties of the AE44-2 alloy was investigated. The results showed that the different cooling rates in these three different casting techniques led to the different distribution and morphology of the precipitated phases, and rapid cooling contributed to a dense network distribution of the phases as well as grain refinement. In addition, the faster cooling rate resulted in a decrease of the dislocation accumulation. The addition of vacuum assistance in the HPDC process increased texture strength. The average grain size of the HPDC alloy was reduced by 90.4% compared to the GC alloy and the yield strength increased by 85.7 MPa due to rapid cooling. The elongation of the HVHPDC alloy increased by 2.3% compared to the HPDC alloy due to vacuum assistance. Moreover, the mechanical properties improved for the alloys in the order of GC < HPDC < HVHPDC because of gran refinement caused by the faster cooling rate. Based on the analysis of the strengthening mechanisms, the rapid cooling process of the HPDC alloy led to better strengthening compared to the GC alloy. In addition, grain refinement contributed to 82.1% of the strengthening mechanism.
Abstract Accelerating the discovery of advanced materials is crucial for modern industries, aerospace, biomedicine, and energy. Nevertheless, only a small fraction of materials are currently under experimental investigation within the vast chemical space. Materials scientists are plagued by time-consuming and labor-intensive experiments due to lacking efficient material discovery strategies. Artificial intelligence (AI) has emerged as a promising instrument to bridge this gap. Although numerous AI toolkits or platforms for material science have been developed, they suffer from many shortcomings. These include primarily focusing on material property prediction and being unfriendly to material scientists lacking programming experience, especially performing poorly with limited data. Here, we developed MLMD, an AI platform for materials design. It is capable of effectively discovering novel materials with high-potential advanced properties end-to-end, utilizing model inference, surrogate optimization, and even working in situations of data scarcity based on active learning. Additionally, it integrates data analysis, descriptor refactoring, hyper-parameters auto-optimizing, and properties prediction. It also provides a web-based friendly interface without need programming and can be used anywhere, anytime. MLMD is dedicated to the integration of material experiment/computation and design, and accelerate the new material discovery with desired one or multiple properties. It demonstrates the strong power to direct experiments on various materials (perovskites, steel, high-entropy alloy, etc). MLMD will be an essential tool for materials scientists and facilitate the advancement of materials informatics.
Abstract An Mg-3Al-1Zn- x Sn (x = 0, 3, 6, 9) alloy was prepared by die-casting and analyzed by XRD, SEM, and EBSD. The microstructure, second phase, and grain orientation of the AZT31 x alloy were characterized. As the Sn content increased from 3 wt.% to 9 wt.%, the tensile and yield strength of the alloy were effectively improved. With the addition of Sn, the grain size of alloys decreases gradually blocking the dislocation by the grain boundary and the dispersion of the Mg 2 Sn second phase in the AZT31 x ( x = 3, 6, 9) alloys contributes to the strength via grain boundary pinning. According to theoretical analysis and calculation, the high strength of AZT319 alloy is partly attributed to the grain fine strengthening σHP=13.76Mpa ) and second phase strengthening Δσ=9.27∼12.67MPa. The total increased strengthening value is lower than experimental value ( Δσ=31.82MPa ). The ratio about τprism / τbasal and τc+a / τbasal in die-cast alloys tensioned to 0.08 deformation gradually decrease, which can reflect that high-Sn content contributes to the strain hardening behavior. The ductility of AZT313 alloy was lightly improved due to the {10-12} tensile twins. When excessive Sn was added, the Mg 2 Sn second phase coarsened and acted as the nucleus of micro-cracks during the stretching process, thereby reducing the ductility of the alloy.
The temperature damping capacities of Mg-3Al-1Zn-xSn (x=3, 6, 9) alloys were investigated using a Dynamic Mechanical Thermal Analyzer (DMA) under varying loading frequencies and Sn concentrations. The addition of Sn resulted in a leftward shift of the P1 dislocation damping peak around 80 °C and a rightward shift of the P3 peak around 220 °C, which were attributed to the second phases in the vicinity of grain boundaries. By combining the Granato-Lücke model and the Peguin model, the damping curves were analyzed, and the temperature damping mechanism of Mg-3Al-1Zn-xSn alloy was summarized. Before 220 °C, the addition of Sn significantly enhanced the damping capacity at different frequencies, which was attributed to the elevated quantity of point defects and second phase precipitates. The damping mechanism was dominated by microplastic internal friction in the later part of the test. There is a negative correlation between frequency and damping. The observation of microstructures suggested that dynamic recrystallization, twins, and the increasing in Schmid factors values of non-basal slip systems were the sources of the microplastic damping capacity. The dynamic recrystallization mechanism was analyzed and it was identified that the main type of recrystallization at high temperatures is continuous dynamic recrystallization caused by cyclic loading.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
