CIESC Journal ›› 2018, Vol. 69 ›› Issue (3): 907-912.DOI: 10.11949/j.issn.0438-1157.20171416

Previous Articles     Next Articles

Research and application of feature extraction derived functional link neural network

ZHU Qunxiong1,2, ZHANG Xiaohan1,2, GU Xiangbai1,3, XU Yuan1,2, HE Yanlin1,2   

  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:2017-10-24 Revised:2017-11-07 Online:2018-03-05 Published:2018-03-05
  • Supported by:

    supported by the National Natural Science Foundation of China (61533003, 61703027) and the Fundamental Research Funds for the Central Universities (ZY1704, JD1708).

基于特征提取的函数连接神经网络研究及其化工过程建模应用

朱群雄1,2, 张晓晗1,2, 顾祥柏1,3, 徐圆1,2, 贺彦林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
  • 基金资助:

    国家自然科学基金重点基金项目(61533003);国家自然科学基金青年基金项目(61703027);中央高校基本科研业务费专项资金(ZY1704,JD1708)。

Abstract:

Traditional functional link neural network (FLNN) cannot effectively model multi-dimensional, noisy and strongly coupled data in chemical process. A principal component analysis based FLNN (PCA-FLNN) model was proposed to improve modeling effectiveness. Feature extraction of FLNN function extension block not only removed linear correlations between variables but also selected main components of data, which complexity of FLNN learning data was alleviated. The proposed PCA-FLNN model was used to simulate an UCI Airfoil Self-Noise data and purified terephthalic acid (PTA) production process. Simulation results indicated that PCA-FLNN can achieve faster convergence speed with higher modeling accuracy than traditional FLNN.

Key words: functional link artificial neural network, feature extraction, process modeling, purified terephthalic acid

摘要:

对于化工过程中带噪声、强耦合的高维数据建模问题,常规的函数连接神经网络(functional link neural networks,FLNN)无法有效地进行处理。为解决该问题,提出一种基于主元分析(principal components analysis,PCA)的函数连接神经网络(PCA-FLNN)。通过对FLNN的函数扩展层进行特征提取,不仅去除变量间的线性相关关系,而且提取数据的主成分,进而简化FLNN学习数据的复杂度。为验证所提方法的有效性,首先采用UCI数据Airfoil Self-Noise对其性能进行验证;随后将所提的方法应用于精对苯二甲酸(purified terephthalic acid,PTA)生产过程建模;与传统FLNN进行对比,标准数据和工业数据的仿真结果表明,PCA-FLNN在处理复杂化工过程数据时具有收敛速度快和建模精度高的特点。

关键词: 函数连接神经网络, 特征提取, 过程建模, 精对苯二甲酸

CLC Number: