Superconductive properties for oxides were predicted by artificial neural network (ANN) method with structural and chemical parameters as inputs. The predicted properties include superconductivity for oxides, distribu...Superconductive properties for oxides were predicted by artificial neural network (ANN) method with structural and chemical parameters as inputs. The predicted properties include superconductivity for oxides, distributed ranges of the superconductive transition temperature (Tc) for complex oxides, and Tc values for cuprate superconductors. The calculated results indicated that the adjusted ANN can be used to predict superconductive properties for unknown oxides.展开更多
The properties of superconductivity of some oxides were investigated by structural parametric diagrams or pattern recognition with structural chemical parameters. The essential criteria of superconductivity for some o...The properties of superconductivity of some oxides were investigated by structural parametric diagrams or pattern recognition with structural chemical parameters. The essential criteria of superconductivity for some oxides have been obtained by using 109 oxides as the training set and seven parameters as features; the results illustrated that the electronegativity difference is the most important factor among seven parameters. Moreover, the regularity of superconductive transition temperature Tc for complex oxides is discussed by partial least squares (PLS) method.展开更多
文摘Superconductive properties for oxides were predicted by artificial neural network (ANN) method with structural and chemical parameters as inputs. The predicted properties include superconductivity for oxides, distributed ranges of the superconductive transition temperature (Tc) for complex oxides, and Tc values for cuprate superconductors. The calculated results indicated that the adjusted ANN can be used to predict superconductive properties for unknown oxides.
文摘The properties of superconductivity of some oxides were investigated by structural parametric diagrams or pattern recognition with structural chemical parameters. The essential criteria of superconductivity for some oxides have been obtained by using 109 oxides as the training set and seven parameters as features; the results illustrated that the electronegativity difference is the most important factor among seven parameters. Moreover, the regularity of superconductive transition temperature Tc for complex oxides is discussed by partial least squares (PLS) method.