Table 3 Outcomes of RNN-BRO for variants of DFPG-CNTs model.

From: Numerical treatment for Darcy–Forchheimer flow of propylene glycol with carbon nanotubes under the impacts of MHD and activation energy

Scenario	Nano particles	Training	Performance	Grad	Mu	Sum of square parameter	Effective parameter	Epoch	Time (s)
1	SWCNT	1.30E−13	1.30E−13	2.2E−08	500,000	6.68	22.78	267	48
1	MWCNT	1.30E−13	1.30E−13	2.3E−08	500,000	6.69	22.65	251	42
2	SWCNT	3.24E−12	3.24E−12	8.0E−08	5000	3.37	18.61	87	23
2	MWCNT	2.45E−12	2.45E−12	2.9E−08	50,000	2.94	18.94	39	6
3	SWCNT	1.41E−12	1.41E−12	4.2E−08	50,000	4.03	20.71	68	11
3	MWCNT	2.51E−13	2.51E−13	7.6E−08	5000	3.41	21.34	86	22
4	SWCNT	2.39E−13	2.39E−13	5.8E−08	500,000	3.61	20.61	228	42
4	MWCNT	3.92E−13	3.92E−13	9.8E−08	50,000	4.29	21.64	323	52
5	SWCNT	2.16E−13	2.16E−13	6.7E−09	50,000	3.81	20.65	66	10
5	MWCNT	2.08E−13	2.08E−13	4.7E−08	500,000	4.16	16.67	669	78
6	SWCNT	5.45E−14	5.45E−14	9.9E−08	50,000	4.63	22.97	434	61
6	MWCNT	4.58E−12	4.58E−12	9.2E−08	50,000	3.81	19.93	139	28
7	SWCNT	2.53E−13	2.53E−13	6.8E−08	500,000	4.01	20.25	960	125
7	MWCNT	6.87E−13	6.87E−13	7.4E−08	50,000	4.25	21.75	165	32
8	SWCNT	1.19E−12	1.19E−12	4.8E−08	50,000	5.01	23.45	254	43
8	MWCNT	3.14E−13	3.14E−13	9.9E−08	50,000	4.68	22.49	229	40
9	SWCNT	1.41E−13	1.41E−13	4.6E−08	500,000	3.81	20.49	671	81
9	MWCNT	6.51E−14	6.51E−14	5.1E−09	50,000	4.12	23.46	258	48
10	SWCNT	1.29E−13	1.29E−13	3.6E−08	50,000	3.34	19.71	52	8
10	MWCNT	2.69E−12	2.69E−12	6.1E−08	50,000	2.45	17.71	25	5
11	SWCNT	4.05E−13	4.05E−13	2.5E−08	50,000	2.97	19.38	82	21
11	MWCNT	3.03E−12	3.03E−12	6.1E−08	50,000	3.20	18.10	36	5
12	SWCNT	4.06E−14	4.06E−14	7.8E−09	50,000	3.70	20.27	191	34
12	MWCNT	5.94E−12	5.94E−12	7.1E−08	5000	3.28	17.89	80	19
13	SWCNT	8.48E−14	8.48E−14	9.3E−09	50,000	2.75	18.10	142	29
13	MWCNT	1.16E−11	1.16E−11	9.1E−08	5000	2.92	16.50	29	3

Back to article page

Quick links

Search

Quick links