Control Method of Rare Earth Extraction Process Based on Optimization Setting

Abstract

Aiming at the problems of complex working conditions, large error of empirical control and low efficiency of manual adjustment in rare earth extraction process, a predictive control method based on particle swarm optimization (PSO) was proposed to reduce economic cost. Firstly, wavelet neural network (WNN) for rare earth extraction process was described. Secondly, using particle swarm optimization (PSO) to obtain the economic costs of minimum flow control value and monitoring level components in the optimal value, according to the objective function of extraction production conditions set economic cost. And then using the method of generalized predictive control (GPC) to achieve the optimal value of components in tracking control. Finally, based on the actual operation data of the extraction process of cerium, praseodymium and neodymium (CePr/Nd), the experiment results show that the proposed method can adjust and control the flow value in time when the extraction process is disturbed by the external environment, so that the content distribution of components is stable at the optimal value, which can meet the requirements of stable, accurate, rapid and economic rare earth extraction.