Data-Driven Optimal Control for Pulp Washing Process Based on Neural Network

Table 2

Neural network dynamic model training parameters of residual soda and Baume degree.

Dynamic model	Learning rate	Initial value of	Increment of	Decrement of	Learning epochs	Error
RS	0.3	0.001	10	0.1	56	0.0019
BD	0.11	0.001	10	0.1	67	0.002