CIESC Journal ›› 2019, Vol. 70 ›› Issue (2): 475-480.DOI: 10.11949/j.issn.0438-1157.20181355

• Process system engineering • Previous Articles     Next Articles

Research on principal components extraction based robust extreme learning machine(PCE-RELM) and its application to modeling chemical processes

Xiaohan ZHANG1,2(),Pingjiang WANG1,2,Xiangbai GU1,3,Yuan XU1,2,Yanlin HE1,2(),Qunxiong ZHU1,2()   

  1. 1. College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China
    2. Engineering Research Center of Ministry of Education, Beijing 100029, China
    3. Sinopec Engineering Group Co., Ltd., Beijing 100101, China
  • Received:2018-11-16 Revised:2018-11-26 Online:2019-02-05 Published:2019-02-05
  • Contact: Yanlin HE,Qunxiong ZHU

基于主元提取的鲁棒极限学习机研究及其化工建模应用

张晓晗1,2(),汪平江1,2,顾祥柏1,3,徐圆1,2,贺彦林1,2(),朱群雄1,2()   

  1. 1. 北京化工大学信息科学与技术学院,北京100029
    2. 智能过程系统工程教育部工程研究中心,北京100029
    3. 中石化炼化工程(集团)股份有限公司,北京100101
  • 通讯作者: 贺彦林,朱群雄
  • 作者简介:<named-content content-type="corresp-name">张晓晗</named-content>(1995—),女,博士研究生,<email>xiao.han_zhang@qq.com</email>|贺彦林(1987—),男,博士,副教授,<email>heyl@mail.buct.edu.cn</email>|朱群雄(1960—),男,博士,教授,<email>zhuqx@mail.buct.edu.cn</email>
  • 基金资助:
    国家自然科学基金青年项目(61703027);国家自然科学基金重点项目(61533003);中央高校基本科研业务费专项资金(JD1808, XK1802-4)

Abstract:

The chemical production processes are increasingly complex and the traditional extreme learning machine (ELM) cannot effectively model the chemical processes data. To tackle this problem, a novel PCE-RELM model based on principal components extraction (PCE) is proposed. Through principal component analysis of the ELM hidden layer, the principal component features of the data are extracted, the linear correlation between variables is removed, and the research problem is simplified. The influence of the number of hidden layer nodes on the accuracy of the model can be reduced, the number of hidden layer nodes in the ELM can be quickly and randomly selected, and the ELM model becomes robust. To verify the effectiveness of the proposed method, the PCE-RELM model was applied to modeling the purified terephthalic acid (PTA) production process. The simulation results show that, compared with the traditional ELM, the PCE-RELM model has the advantages of simple design, good robustness and high accuracy, which can guide the chemical process control and analysis.

Key words: extreme learning machine, neural network, principal components analysis, processes modeling, chemical production, process control

摘要:

化工生产过程日益复杂,传统极限学习机(extreme learning machine, ELM)无法有效地对化工过程数据建模。针对该问题,提出一种基于主元提取(principal components extraction, PCE)的鲁棒极限学习机(PCE-RELM)。通过对ELM隐含层进行主元分析,提取数据的主元特征,去除变量间的线性相关性,简化研究问题。可以减小隐含层节点数对模型精度的影响,实现对ELM隐含层节点数的快速随机选取,同时使ELM具有鲁棒性。为验证提出方法的有效性,将PCE-RELM模型应用于精对苯二甲酸(purified terephthalic acid,PTA)生产过程建模。仿真结果显示,相比传统的ELM,PCE-RELM模型具有设计简单、鲁棒性好、精度高等优势,可以对化工过程控制、分析起到指导作用。

关键词: 极限学习机, 神经网络, 主元分析, 过程建模, 化工生产, 过程控制

CLC Number: