Optimization and Prediction of Mechanical and Thermal Properties of Graphene/LLDPE Nanocomposites by Using Artificial Neural Networks

Table 3

Experimental data set.

Sample number	% of graphene	Speed	Tensile strength; (MPa)	Thermal conductivity (w/m·K)	Degradation temperature (°C)	Crystallization temperature (°C)	Data partition
1	0	50	21.5	0.37	476.12	109.18	Validation
2	0	100	23.27	0.37	476.72	109.43	Training
3	0	150	22.49	0.35	477	109.53	Training
4	1	50	22.4	0.38	479.36	112.13	Testing
5	1	100	23.05	0.37	479.73	112.88	Testing
6	1	150	23.7	0.41	480.2	113.05	Testing
7	2	50	23.7	0.39	480.7	112.43	Training
8	2	100	24.87	0.39	480.7	113.1	Validation
9	2	150	26.26	0.43	481.7	113.55	Training
10	4	50	25.86	0.39	481.73	112.95	Training
11	4	100	22.7	0.4	482.4	113.26	Training
12	4	150	33.13	0.437	483.7	113.54	Training
13	6	50	23.66	0.4	481.76	113.6	Training
14	6	100	22	0.41	483.11	113.8	Training
15	6	150	23.63	0.47	485.62	113.55	Validation
16	8	50	21.44	0.42	483.66	113.95	Training
17	8	100	20.52	0.42	485.42	114.1	Testing
18	8	150	21.47	0.477	486.64	114.5	Training
19	10	50	19.38	0.47	488.09	114.81	Validation
20	10	100	18.8	0.472	489.28	114.17	Validation
21	10	150	19.65	0.5	490	115	Testing