Content and concentration of rare earth element components based on multi-task learning multi-objective optimization multidimensional soft measurement

被引：0
|
作者：
Zhang S.-P. [1 ]
Zhang Q.-H. [1 ]
Wang B. [1 ]
机构：
[1] School of Information Engineering, Jiangxi University of Science and Technology, Jiangxi, Ganzhou
来源：
Kongzhi Lilun Yu Yingyong/Control Theory and Applications | 2024年 / 41卷 / 03期
基金：
中国国家自然科学基金;
关键词：
component content; deep learning; machine learning; multi-objective optimization; multi-task learning; Pareto; rare earth extraction;
D O I：
10.7641/CTA.2023.20871
中图分类号：
学科分类号：
摘要：
Online soft measurement of the component content of each element in a mixed rare earth extraction solution is a prerequisite for optimizing the continuous extraction production process and ensuring high purity of the product. Existing soft measurement methods can solve for individual rare earth element fractions independently, but ignore the commonality between multi-element fractions or between fractions and other relevant factors (e.g. concentration). A multi-task learning approach is used to explore the commonality between the component content of multiple rare earth elements and between the component content and concentration in soft measurements of rare earth elements. Firstly, a multi-task deep neural network is constructed to improve the generalization ability and robustness of the model. Secondly, a multi-objective optimization algorithm is proposed to improve the prediction accuracy of each task by searching the Pareto optimum. After several sets of comparison experimental results, it is shown that the method has the best performance when the multi-element component content or multi-element component content and concentration are trained at the same time, which can meet the accuracy and real-time performance of online detection of rare earth elemental component content. © 2024 South China University of Technology. All rights reserved.
引用
收藏
页码：454 / 467
页数：13
相关论文
共 31 条
  • [1] FENG Zongyu, WANG Meng, ZHAO Longsheng, Et al., Current status and outlook of the development of rare earth element extraction and separation purification technology, Chinese Journal of Rare Earths, 39, 3, pp. 469-478, (2021)
  • [2] ZENG Xiaoqin, CHEN Yiwen, WANG Jingya, Et al., New advances in the research of high performance rare earth magnesium alloys, Chinese Journal of Nonferrous Metals, 31, 11, pp. 2963-2975, (2021)
  • [3] LIU T, CHEN J., Extraction and separation of heavy rare earth elements: A review, Separation and Purification Technology, 276, (2021)
  • [4] ASADOLLAHZADEH M, TORKAMAN R, TORAB-MOSTAEDI M., Extraction and separation of rare earth elements by adsorption approaches: Current status and future trends, Separation & Purification Reviews, 50, 4, pp. 417-444, (2021)
  • [5] DEBLONDE G J P, MATTOCKS J A, PARK D M, Et al., Selective and efficient biomacromolecular extraction of rare-earth elements using lanmodulin, Inorganic Chemistry, 59, 17, pp. 11855-11867, (2020)
  • [6] LIAO Chunsheng, CHENG Fuxiang, WU Sheng, Et al., Development trends and related advances in string-level extraction theory and rare earth separation technology, Chinese Science: Chemistry, 50, 11, pp. 1730-1736, (2020)
  • [7] CHAI Tianyou, YANG Hui, Research status and development trend of automatic control of rare earth extraction and separation process, Chinese Journal of Rare Earths, 22, 4, pp. 427-433, (2004)
  • [8] YANG H, XU Y, WANG X., Component content soft-sensor based on RBF neural network in rare earth countercurrent extraction process, The 6th World Congress on Intelligent Control and Automation, 1, pp. 4909-4912, (2006)
  • [9] LU Rongxiu, HE Quanheng, YANG Hui, Et al., Multi-component content prediction of rare earth mixed solutions based on GA-ELM, Computer Engineering, 47, 1, pp. 284-290, (2021)
  • [10] LU Rongxiu, RAO Yunchun, YANG Hui, Et al., Prediction of praseodymium/neodymium component content based on improved instantaneous learning algorithm, Control Theory & Applications, 37, 8, pp. 1846-1854, (2020)
1234