Due to the large unexplored compositional space,long development cycle,and high cost of traditional trial-anderror experiments,designing high strength aluminum-lithium alloys is a great challenge.This work establishes...Due to the large unexplored compositional space,long development cycle,and high cost of traditional trial-anderror experiments,designing high strength aluminum-lithium alloys is a great challenge.This work establishes a performance-oriented machine learning design strategy for aluminum-lithium alloys to simplify and shorten the development cycle.The calculation results indicate that radial basis function(RBF)neural networks exhibit better predictive ability than back propagation(BP)neural networks.The RBF neural network predicted tensile and yield strengths with determination coefficients of 0.90 and 0.96,root mean square errors of 30.68 and 25.30,and mean absolute errors of 28.15 and 19.08,respectively.In the validation experiment,the comparison between experimental data and predicted data demonstrated the robustness of the two neural network models.The tensile and yield strengths of Al-2Li-1Cu-3Mg-0.2Zr(wt.%)alloy are 17.8 and 3.5 MPa higher than those of the Al-1Li4.5Cu-0.2Zr(wt.%)alloy,which has the best overall performance,respectively.It demonstrates the reliability of the neural network model in designing high strength aluminum-lithium alloys,which provides a way to improve research and development efficiency.展开更多
The corrosion behaviors of 1420 and 2195 Al-Li alloys under 308 and 490 MPa tensile stress respectively in neutral 3.5% NaCl solution were investigated using electrochemical impedance spectroscopy(EIS) and scanning el...The corrosion behaviors of 1420 and 2195 Al-Li alloys under 308 and 490 MPa tensile stress respectively in neutral 3.5% NaCl solution were investigated using electrochemical impedance spectroscopy(EIS) and scanning electron microscope(SEM). It is found that the unstressed 1420 alloy is featured with large and discrete pits, while general corrosion and localized corrosion including intergranular corrosion and pitting corrosion occur on the unstressed 2195 alloy. As stress is applied to 1420 alloy, the pit becomes denser and its size is decreased. While, for the stressed 2195 alloy, intergranular corrosion is greatly aggravated and severe general corrosion is developed from connected pits. The EIS analysis shows that more severe general corrosion and localized corrosion occur on the stressed 2195 Al-Li alloy than on 1420 Al-Li alloy. It is suggested that tensile stress has greater effect on the corrosion of 2195 Al-Li alloy than on 1420 Al-Li alloy.展开更多
基金supported by the National Natural Science Foundation of China(Nos.52074246,52275390,52205429,52201146)National Defense Basic Scientific Research Program of China(JCKY2020408B002)Key Research and Development Program of Shanxi Province(202102050201011,202202050201014).
文摘Due to the large unexplored compositional space,long development cycle,and high cost of traditional trial-anderror experiments,designing high strength aluminum-lithium alloys is a great challenge.This work establishes a performance-oriented machine learning design strategy for aluminum-lithium alloys to simplify and shorten the development cycle.The calculation results indicate that radial basis function(RBF)neural networks exhibit better predictive ability than back propagation(BP)neural networks.The RBF neural network predicted tensile and yield strengths with determination coefficients of 0.90 and 0.96,root mean square errors of 30.68 and 25.30,and mean absolute errors of 28.15 and 19.08,respectively.In the validation experiment,the comparison between experimental data and predicted data demonstrated the robustness of the two neural network models.The tensile and yield strengths of Al-2Li-1Cu-3Mg-0.2Zr(wt.%)alloy are 17.8 and 3.5 MPa higher than those of the Al-1Li4.5Cu-0.2Zr(wt.%)alloy,which has the best overall performance,respectively.It demonstrates the reliability of the neural network model in designing high strength aluminum-lithium alloys,which provides a way to improve research and development efficiency.
基金Project(50401012) supported by the National Natural Science Foundation of China
文摘The corrosion behaviors of 1420 and 2195 Al-Li alloys under 308 and 490 MPa tensile stress respectively in neutral 3.5% NaCl solution were investigated using electrochemical impedance spectroscopy(EIS) and scanning electron microscope(SEM). It is found that the unstressed 1420 alloy is featured with large and discrete pits, while general corrosion and localized corrosion including intergranular corrosion and pitting corrosion occur on the unstressed 2195 alloy. As stress is applied to 1420 alloy, the pit becomes denser and its size is decreased. While, for the stressed 2195 alloy, intergranular corrosion is greatly aggravated and severe general corrosion is developed from connected pits. The EIS analysis shows that more severe general corrosion and localized corrosion occur on the stressed 2195 Al-Li alloy than on 1420 Al-Li alloy. It is suggested that tensile stress has greater effect on the corrosion of 2195 Al-Li alloy than on 1420 Al-Li alloy.
