Multi-model predictive control method for component content in process of extracting rare earth

Abstract

The invention relates to a multi-model predictive control method for component content in the process of extracting rare earth. The method comprises the following steps of: establishing a multi-linear model with concentration extraction series of 1 at the component content detection point in the process of extracting and separating the rare earth; converting the established multi-linear model into a controlled autoregressive integral moving average (CARIMA) model by a generalized predictive control algorithm; and calculating to obtain the change of controlled quantity (flow quantity of an extracting agent or acid liquid) according to the deviation between a component content on-line estimated value and a preset value. The method is suitable for on-line detection and automatic control of the component content in the process of extracting and separating the rare earth.

Description

technical field [0001] The invention relates to a multi-model predictive control method for component content in a rare earth extraction and separation process, and belongs to the technical field of on-line monitoring and automatic control of component content in the rare earth extraction process. Background technique [0002] Rare earth elements are indispensable and important raw materials in many industrial fields, from traditional industries such as metallurgy, machinery, petroleum, and chemical industry to high-tech fields such as communications and aerospace. In recent years, my country's rare earth separation industry has developed rapidly, especially the rare earth separation process by solvent extraction has reached the international leading level under the guidance of cascade extraction theory and its new development. There are many types of rare earth elements, similar chemical properties, and small mutual separation coefficients. This makes the extraction and sep...

AI Technical Summary

Problems solved by technology

There are many forms of mathematical models for the rare earth extraction process, but some models initially established are based on traditional process models, which are static in nature and cannot reflect the dynamic changes of the extraction process, or some models are too complex to be suitable as a group. A Soft-Sensor Model for On-line Estimation of Fraction Content

The emergence and development of various algorithms have provided conditions for the establishment of a soft sensor model for the component content of the rare earth extraction process. Some people use neural networks to model the extraction process, which has become a new way for online detection of component content. However, due to the collection of data limited, the training results of the neural network cannot cover the entire working condition, and have a great impact on the prediction accuracy and network training effect. However, some people have proposed multi-model soft-sensing technology, but the number of models is large and the amount of calculation is large

At the same time, even though the model established above can realize the on-line detection of component content, it does not give the control amount when the component content of the monitoring point is not within the empirical range.

Images