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2 回归模型评估结果

Table 2 Evaluation results of the regression models

Round EVS MAE / HV MSE / HV RMSE / HV MedAE / HV First round -0.10 14.60 301.80 17.31 0.09 The second round of mME -0.11 10.06 138.10 11.75 0.04 The second round of mBO 0.31 5.57 38.56 6.21 0.01 The third round of mME 0.16 7.79 94.59 9.73 0.03 The third round of mBO 0.50 2.88 20.13 4.49 < 0.01 The third round of mBOe -0.06 4.85 42.41 6.51 0.01