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6 以人工经验采样数据填充的机器学习模型(mME)和以Bayesian优化采样数据填充的机器学习模型(mBO)建模结果对比

Fig.6 Prediction results of mME and mBO models in the first iteration (sBO—sampling based on BO, sME—sampling based on ME) (a), second iteration (b), third iteration (c), and comparisons of model error RMSE (The error bars are the mean standard deviation of the experiments) (d)