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5 机器学习模型预测结果对比 (a) RMSE results with the training data divided randomly at the ratio of 30%~90% (b) evaluation results of Bootstrap random sampling model (histogram) and model performance with 80% training data split ratio (point and line plot)

Fig.5 Comparisons among machine learning models