A Machine Learning Approach to Optimize, Model, and Predict the Machining Factors in Dry Drilling of Nimonic C263

Table 9

Percentage prediction errors for test dataset.

S. no.	Measured output		Predicted output		% prediction error
	Fz (N)	Ra (μm)	Fz (N)	Ra (μm)	Fz (N)	Ra (μm)
1	1385	0.595	1387.194	0.600289	0.158178	0.881158
2	1400	0.622	1386.899	0.681932	0.944626	8.788583
3	1430	0.641	1453.774	0.651407	1.635319	1.597572
4	1060	0.552	997.7439	0.597503	6.239689	7.615499
5	1120	0.672	1090.856	0.649399	2.671686	3.480324
6	1175	0.695	1106.866	0.681351	6.155621	2.003201
7	975	0.569	938.4216	0.596766	3.897863	4.652757
8	990	0.589	987.186	0.555578	0.285049	6.015688
9	1030	0.612	1159.582	0.582648	11.1749	5.037642
Average prediction error					4.453%	3.685%