The Study of an Optimal Robust Design and Adjustable Ordering Strategies in the HSCM

Table 3

The neural networks for the model.

Structures (input nodes-hidden nodes-output nodes)	RMSE
	Training	Testing
4-6-1	0.03116	0.02824
4-5-1	0.02998	0.02755
4-4-1	0.02633	0.02463
4-3-1	0.02254	0.02092
4-2-1	0.02761	0.02537
4-1-1	0.02993	0.02495

Note. The learning rate was set to autoadjust to value between 0.01 and 0.3; the momentum coefficient is 0.80; and the number of iterations is 15,000.