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

图8 基于Shapley解释法(SHAP)的特征重要性分析及Mg和Si相互作用关系依赖图 (a) feature importance sorting (b) basic dependence plot of Mg (c) basic dependence plot of Si

Fig.8 Features importance analyses and relational dependence plots of Mg and Si based on Shapley additive explanations (SHAP)