基于机器学习的混凝土3D打印沉积线状态优化

马宗方,戴溢阳,贺静,宋琳,刘超

Machine learning-based optimization of deposition line state in concrete 3D printing

Zongfang MA,Yiyang DAI,Jing HE,Lin SONG,Chao LIU

表4 不同机器学习模型的分类预测性能比较

Table 4 Comparison of classification prediction performance of different machine learning models

模型 平均准确率/平均召回率/平均F1值 精度/% 类别0 类别1 类别2 类别3 类别4 BWO-SVM 0.95/0.87/0.90 0.75/0.88/0.83 0.93/0.90/0.91 0.88/0.90/0.89 0.87/0.89/0.97 91.12 BWO-SVM-AdaBoost 1.00/0.98/0.99 0.79/0.92/0.85 0.94/0.89/0.92 1.00/0.96/0.98 0.89/1.00/0.94 95.19 SVM 0.90/0.85/0.87 0.73/0.84/0.82 0.86/0.81/0.84 0.82/0.89/0.85 0.87/0.89/0.84 85.57 DNN1 0.81/0.94/0.84 0.70/0.70/0.70 0.81/0.72/0.76 0.79/1.00/0.88 1.00/0.94/0.97 88.25 DNN2 0.83/0.88/0.86 0.71/0.62/0.67 0.82/0.75/0.78 0.70/0.75/0.71 0.93/0.95/0.94 83.25 LR 0.85/0.98/0.91 0.50/0.57/0.55 0.70/0.83/0.75 0.50/0.12/0.25 0.83/0.83/0.83 73.10 DT 0.79/0.92/0.85 0.47/0.39/0.42 0.74/0.65/0.69 0.64/0.60/0.62 0.67/0.75/0.71 70.19 RF 0.88/0.94/0.92 0.67/0.57/0.63 0.77/0.76/0.76 0.63/0.69/0.65 0.90/0.82/0.85 80.12