Table 1.
Machine learning algorithms used in metal additive manufacturing processes.
Fig 1.
(a) Specimen drawing as per ASTM E8 [29], (b) CM247 printed specimen (c) CM247 specimen after failure (d) Load versus displacement graph.
Table 2.
Chemical composition of CM 247LC powder.
Table 3.
Experimental layout and corresponding volumetric energy density.
Fig 2.
(a) kNN Classification Algorithm workflow (b) Naïve Bayes classification algorithm workflow (c) SVM classification algorithm workflow (d) XGBoost algorithm workflow (e) AdaBoost algorithm workflow (f) Decision Tree classification algorithm workflow (g) Random Forest classification workflow (h) Logistic Regression classifier workflow (i) Pearson’s heatmap workflow.
Table 4.
Observed values along with experimental design layout.
Fig 3.
(a) ANOVA feature importance plot (b) Pearson’s heatmap (c) Confusion matrix for kNN (d) Confusion matrix for Naïve Bayes (e) Confusion matrix for SVM (f) Confusion matrix for XGBoost (g) Confusion matrix for ADABoost (h) Confusion matrix for decision tree (i) Confusion matrix for random forest (j) Confusion matrix for logistic regression classifier.
Table 5.
Classification report kNN.
Table 6.
Classification report for Naïve Bayes.
Table 7.
Classification report for SVM.
Table 8.
Classification report for XGBoost.
Table 9.
Classification report for AdaBoost.
Table 10.
Classification report for decision tree.
Table 11.
Classification report for random forest.
Table 12.
Classification report for logistic regression classifier.
Fig 4.
AUC-ROC curve.
Table 13.
AUC-ROC values.