上海交通大学学报 ›› 2024, Vol. 58 ›› Issue (4): 534-544.doi: 10.16183/j.cnki.jsjtu.2023.011

• 电子信息与电气工程 • 上一篇    下一篇

不完备数据下的聚酯熔体特性黏度预测方法

毕金茂1, 张朋2(), 张洁2, 赵春财3, 崔利3   

  1. 1.东华大学 机械工程学院,上海 201620
    2.东华大学 人工智能研究院,上海 201620
    3.新凤鸣集团湖州中石科技有限公司,浙江 湖州 313000
  • 收稿日期:2023-01-10 修回日期:2023-05-22 接受日期:2023-06-01 出版日期:2024-04-28 发布日期:2024-04-30
  • 通讯作者: 张 朋,讲师;E-mail: zhangp88@dhu.edu.cn.
  • 作者简介:毕金茂(1999-),硕士生,从事聚酯熔体质量预测与优化研究.
  • 基金资助:
    国家自然科学基金资助项目(52005099);中央高校基本科研业务费专项(223202100044)

Polyester Melt Characteristic Viscosity Prediction Method Under Incomplete Data

BI Jinmao1, ZHANG Peng2(), ZHANG Jie2, ZHAO Chuncai3, CUI Li3   

  1. 1. College of Mechanical Engineering, Donghua University, Shanghai 201620, China
    2. Institute of Artificial Intelligence, Donghua University, Shanghai 201620, China
    3. Xinfengming Group Huzhou Zhongshi Technology Co., Ltd., Huzhou 313000, Zhejiang, China
  • Received:2023-01-10 Revised:2023-05-22 Accepted:2023-06-01 Online:2024-04-28 Published:2024-04-30

摘要:

特性黏度是衡量聚酯熔体质量的关键指标,对其进行精准预测有利于提前发现聚酯熔体潜在的质量问题,及时调整工艺参数,减少企业损失.考虑到聚酯熔体生产过程的数据不完备性、数据时序性以及高维冗余性,提出了不完备数据下聚酯熔体的特性黏度预测方法.针对聚酯熔体极端生产环境造成的数据不完备问题,设计了以卷积神经网络判别器和注意力长短期记忆神经网络生成器为架构的缺失数据生成对抗网络(MDGAN),通过对抗生成机制实现了缺失数据的填充.针对聚酯熔体生产过程中高维冗余和时序双向因果特性,设计了基于极端梯度提升双向门控循环单元(XGBoost-BiGRU)的特性黏度预测模型,通过极端梯度提升算法进行特征筛选,获取预测模型输入变量,再利用双向门控循环单元捕捉数据的时序双向因果关系,实现特性黏度的精准预测.浙江某聚酯纤维生产企业的实际数据测试结果表明,MDGAN算法在不同缺失率数据集下的填充精度均优于KNN、RF、MICE、GAIN数据填充算法,XGBoost-BiGRU特性黏度预测方法较STL-GPR、CAGRU、BiGRU算法优势显著,结合MDGAN的特性黏度预测方法能有效解决数据不完备下的聚酯熔体特性黏度预测问题.

关键词: 特性黏度预测, 不完备数据, 生成对抗网络, 循环神经网络

Abstract:

Characteristic viscosity is a key indicator of the quality of polyester melts, whose accurate prediction can help to identify potential quality problems of polyester melts in advance, adjust the process parameters in time and reduce enterprise losses. Considering the data incompleteness, data time series and high dimensional redundancy of the polyester melt production process, a method is proposed to predict the characteristic viscosity of polyester melt under incomplete data. A missing data generative adversarial nets (MDGAN) with a convolutional neural network discriminator and an attention long short-term memory neural network generator is designed to address the data incompleteness problem caused by the extreme production environment of polyester melts, and the missing data is filled by the adversarial generation mechanism. The extreme gradient boosting-bidirectional gated recurrent unit (XGBoost-BiGRU) is designed to predict the viscosity of polyester melts based on high dimensional redundancy and temporal characteristics prediction. The actual data test results of a polyester fiber manufacturer in Zhejiang show that the filling accuracy of the MDGAN algorithm at different missing rate data sets is better than that of data filling algorithms such as KNN,RF,MICE,and GAIN. The XGBoost-BiGRU characteristic viscosity prediction method has significant advantages over STL-GPR, CAGRU, BiGRU. In combination of MDGAN characteristic viscosity prediction, the method proposed can effectively solve the problem of predicting the characteristic viscosity of polyester melts under incomplete data.

Key words: intrinsic viscosity prediction, incomplete data, generative adversarial networks (GAN), recurrent neural networks (RNN)

中图分类号: