基于Bayesian采样主动机器学习模型的6061铝合金成分精细优化

赵婉辰, 郑晨, 肖斌, 刘行, 刘璐, 余童昕, 刘艳洁, 董自强, 刘轶, 周策, 吴洪盛, 路宝坤

Composition Refinement of 6061 Aluminum Alloy Using Active Machine Learning Model Based on Bayesian Optimization Sampling

ZHAO Wanchen, ZHENG Chen, XIAO Bin, LIU Xing, LIU Lu, YU Tongxin, LIU Yanjie, DONG Ziqiang, LIU Yi, ZHOU Ce, WU Hongsheng, LU Baokun

表1 22个重要性质特征描述符的索引及对应含义

Table 1 Features indexes and implication of 22 important property features

Feature index Feature name Feature index Feature name F_0 Ave: electron_affinity F_1 Ave: hhi_r F_2 Var: covalent_radius F_3 Sum: atomic_weight F_4 Var: gs_est_fcc_latcnt F_5 Var: atomic_radius F_6 Modulus mismatch F_7 Var: atomic_radius_rahm F_8 Shear modulus F_9 Lattice distortion energy F_10 Mixing enthalpy F_11 Parameter omiga F_12 Ave: dipole_polarizability F_13 Sum: c6_gb F_14 Cohesive energy F_15 Var: molar_volume F_16 Var: first_ion_en F_17 Ave: covalent_radius_pykko_triple F_18 Ave: boiling_point F_19 Sum: heat_of_formation F_20 Configurational entropy F_21 Ave: electron_negativity