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

Table 2

The neural networks for the model.

Structures (input nodes-hidden nodes-output nodes)	RMSE
	Training	Testing
4-6-1	0.02982	0.02634
4-5-1	0.02632	0.02471
4-4-1	0.02444	0.02170
4-3-1	0.02321	0.02018
4-2-1	0.02651	0.02485
4-1-1	0.03145	0.03059

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.