Soft sensor modeling of cement clinker quality: a novel timing matching technique and data decoupling approach

被引:1
作者
Zhao, Yantao [1 ]
Wu, Ruteng [1 ]
Zhang, Shanshan [1 ]
Qu, Hong [1 ]
Hao, Xiaochen [1 ]
机构
[1] Yanshan Univ, Sch Elect Engn, 438 Hebei Ave, Qinhuangdao 066004, Peoples R China
关键词
attention mechanism; data decoupling; window selection mechanism; soft sensor; TIME-SERIES; TEMPERATURE;
D O I
10.1088/1361-6501/acea9d
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Clinker free calcium oxide (f-CaO) content is an important indicator of cement quality. Considering the production characteristics (strong coupling, time-varying delay) in the cement process industry, a soft sensor model was developed by combining various methods. First, a new decoupling method is proposed to deal with the strong coupling between variables, which achieves data decoupling between process variables through the attention mechanism and the long short-term memory network. Second, a novel time-series matching technique is proposed to handle the time-varying delays, which utilizes a window selection mechanism to adaptively select the time period in which each process variable influences the target variable. Third, the critical features of the variables are extracted by a one-dimensional convolution network (1D-CNN). Last, a combination of the data decoupling method, window selection mechanism, and 1D-CNN is applied to develop a soft sensor model (ADM-WGM-CNN), which implements the measurement of f-CaO content. The experimental results demonstrate that the ADM-WGM-CNN model has better measurement performance.
引用
收藏
页数:11
相关论文
共 35 条
  • [1] Co-training partial least squares model for semi-supervised soft sensor development
    Bao, Liang
    Yuan, Xiaofeng
    Ge, Zhiqiang
    [J]. CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2015, 147 : 75 - 85
  • [2] Choomkasien P, 2017, INT C CONTR AUTOMAT, P625, DOI 10.23919/ICCAS.2017.8204305
  • [3] Investigation on the ignition delay prediction model of multi-component surrogates based on back propagation (BP) neural network
    Cui, Yanqing
    Liu, Haifeng
    Wang, Qianlong
    Zheng, Zunqing
    Wang, Hu
    Yue, Zongyu
    Ming, Zhenyang
    Wen, Mingsheng
    Feng, Lei
    Yao, Mingfa
    [J]. COMBUSTION AND FLAME, 2022, 237
  • [4] Soft Sensor Transferability: A Survey
    Curreri, Francesco
    Patane, Luca
    Xibilia, Maria Gabriella
    [J]. APPLIED SCIENCES-BASEL, 2021, 11 (16):
  • [5] DiPietro R., 2020, Handbook of Medical Image Computing and Computer Assisted Intervention, P503, DOI https://doi.org/10.1016/B978-0-12-816176-0.00026-0
  • [6] Augmented Multidimensional Convolutional Neural Network for Industrial Soft Sensing
    Jiang, Xiaoyu
    Ge, Zhiqiang
    [J]. IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2021, 70
  • [7] Jinghui Qiao, 2010, 2010 International Conference on Measuring Technology and Mechatronics Automation (ICMTMA 2010), P591, DOI 10.1109/ICMTMA.2010.503
  • [8] Fault Diagnosis Method Based on Encoding Time Series and Convolutional Neural Network
    Li, Chunlin
    Xiong, Jianbin
    Zhu, Xingtong
    Zhang, Qinghua
    Wang, Shuize
    [J]. IEEE ACCESS, 2020, 8 : 165232 - 165246
  • [9] An improved multi-source based soft sensor for measuring cement free lime content
    Li, Weitao
    Wang, Dianhui
    Zhou, Xiaojie
    Chai, Tianyou
    [J]. INFORMATION SCIENCES, 2015, 323 : 94 - 105
  • [10] Multisource Data Ensemble Modeling for Clinker Free Lime Content Estimate in Rotary Kiln Sintering Processes
    Li, Weitao
    Wang, Dianhui
    Chai, Tianyou
    [J]. IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2015, 45 (02): : 303 - 314