Research Article
A Machine Learning Approach to Optimize, Model, and Predict the Machining Factors in Dry Drilling of Nimonic C263
Table 8
FFNN model results for test dataset using the LM algorithm.
| Exp. no. | Inputs | Predicted output | N (rev/min) | f (mm/rev) | 2ρ (degree) | Fz (N) | Ra (μm) |
| 7 | 1250 | 0.198 | 120 | 787.1942 | 0.600289 | 8 | 1250 | 0.198 | 140 | 1086.899 | 0.681932 | 9 | 1250 | 0.198 | 145 | 1153.774 | 0.651407 | 16 | 1500 | 0.198 | 120 | 737.7439 | 0.597503 | 17 | 1500 | 0.198 | 140 | 1090.856 | 0.649399 | 18 | 1500 | 0.198 | 145 | 1106.866 | 0.681351 | 25 | 1750 | 0.198 | 120 | 738.4216 | 0.596766 | 26 | 1750 | 0.198 | 140 | 1135.186 | 0.555578 | 27 | 1750 | 0.198 | 145 | 1159.582 | 0.582648 |
|
|