Double-Objective Optimization for a Pulp Washing Process Based on Neural Network

For a countercurrent paper pulp washing system, the requirements of craft to residual soda in the final washed pulp and Baume degree in the first stage filtrate tank are usually inconsistent. To compromise this pair of contradiction, a neural network (NN) based two-objective optimization algorithm is proposed. In terms of a two-step identification method, the NN dynamic and steady models on the residual soda in the final washed pulp and the Baume degree in the first stage filtrate tank are identified, respectively. A double-objective optimization algorithm on the hot clean water input and the final washed pulp output is proposed by an external penalty function method. This control strategy has been imbedded into a pulp washing process DCS running in two paper mills in China and resulted in notable profits.