A two-layer optimization and control strategy for zinc hydrometallurgy process based on RBF neural network soft-sensor
Shiwen Xie, Jinjing Yu, Yongfang Xie, Zhaohui Jiang, Weihua Gui · 2019
Zinc hydrometallurgy technique is an important method to produce zinc metal. The control of the zinc hydrometallurgy process is related to the quality of the zinc product. Due to the presence of the unmodeled dynamics, low- frequency disturbances, and high-frequency disturbances, it is a challenge to maintain the production indices within the desired ranges while minimizing the process cost. In this study, a two-layer optimization and control strategy is proposed for the zinc hydrometallurgy process. In the upper layer, an optimal setting module is established to determine the set-points of production indices. A radial basis function (RBF) neural network is constructed to estimate the production indices on-line. An optimal control scheme with fuzzy-logic-based compensator is developed in the lower layer. The proposed strategy is applied to the iron removal process of zinc hydrometallurgy process. Experiments show the effectiveness of our proposed strategy.