A Robust Intelligent Framework for Multiple Response Statistical Optimization Problems Based on Artificial Neural Network and Taguchi Method

Table 3

Signal-to-noise ratios and normalized values of them.

Experimental number	Control variable					SN ratio		NSN ratio
	𝑥1	𝑥2	𝑥3	𝑥4	𝑥5	SN1	SN2	NSN1	NSN2
1	−1	−1	−1	−1	−1	−23.11	12.04	0.375513	0.156322
2	−1	0	0	0	0	−23.92	12.67	0.320109	0.301149
3	−1	1	1	1	1	−27.31	14.96	0.088235	0.827586
4	0	−1	0	0	0	−21.66	11.36	0.474692	0
5	0	0	1	1	1	−18.79	13.8	0.670999	0.56092
6	0	1	−1	−1	−1	−16.26	15.71	0.844049	1
7	1	−1	0	−1	1	−19.08	12.46	0.651163	0.252874
8	1	0	1	0	−1	−21.44	12.67	0.48974	0.301149
9	1	1	−1	1	0	−21.87	14.49	0.460328	0.71954
10	−1	−1	1	1	0	−24.19	13.26	0.301642	0.436782
11	−1	0	−1	−1	1	−28.6	12.26	0	0.206897
12	−1	1	0	0	−1	−20.42	14.49	0.559508	0.71954
13	0	−1	0	1	−1	−24.56	11.82	0.276334	0.105747
14	0	0	1	−1	0	−14.08	13.44	0.99316	0.478161
15	0	1	−1	0	1	−17	14.65	0.793434	0.756322
16	1	−1	1	0	1	−18.85	14.32	0.666895	0.68046
17	1	0	−1	1	−1	−23.58	13.26	0.343365	0.436782
18	1	1	0	−1	0	−13.98	15.27	1	0.898851