Optimization of Residual Wall Thickness Uniformity in Short-Fiber-Reinforced Composites Water-Assisted Injection Molding Using Response Surface Methodology and Artificial Neural Network-Genetic Algorithm

Table 4

Optimal weights and bias for ANN-GA model.

Hidden layer						Output layer
Weights					Bias	Weights	Bias
−0.045	0.411	−0.219	0.327	−0.389	−0.209	0.307	−0.243
0.426	0.463	0.239	−0.256	−0.302	−0.058	−0.240
0.358	0.336	−0.062	0.349	−0.042	−0.381	0.065
0.419	−0.104	0.147	0.428	−0.221	−0.220	−0.480
−0.007	0.348	−0.322	−0.248	0.489	0.188	−0.187
0.229	0.316	0.388	0.454	0.258	0.113	−0.141
0.439	−0.174	−0.413	−0.289	0.171	−0.002	−0.411
0.414	0.471	−0.374	0.078	0.055	0.286	0.075
−0.166	0.453	0.077	0.004	0.491	−0.454	0.002
0.471	0.452	0.362	−0.397	−0.316	−0.403	0.285
−0.074	−0.175	−0.020	0.394	0.271	0.035	−0.088