Adaptive soft sensor ensemble for selecting both process variables and dynamics for multiple process states

被引:5
|
作者
Yamada, Nobuhito [1 ]
Kaneko, Hiromasa [1 ]
机构
[1] Meiji Univ, Sch Sci & Technol, Dept Appl Chem, Tama Ku, 1-1-1 Higashi Mini, Kawasaki, Kanagawa 2148571, Japan
基金
日本学术振兴会; 日本科学技术振兴机构;
关键词
Adaptive soft sensor; Variable selection; Process dynamics; Multiple process states; Ensemble learning;
D O I
10.1016/j.chemolab.2021.104443
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
To improve the predictive ability of soft sensors in chemical and industrial plants, the selection of process variables and consideration of dynamics in the processes have been studied. When multiple process states exist in plants, process variables that are related to an objective variable (y) and their corresponding time delays can be different in each process state. In this paper, we propose a method to optimize process variables and dynamics for each process state, and predict the objective variable values using multiple adaptive soft sensors according to process states. First, a dataset is clustered using Gaussian mixture models; then, time-delayed process variables are selected as explanatory variables (x) for each cluster using genetic algorithm-based process variable and dynamics selection. For each set of explanatory variables, a nonlinear adaptive soft sensor is constructed. An ensemble prediction is performed by assigning a weight to each locally weighted partial least squares (LWPLS) model according to its predictive ability. The novelty of the proposed method is the construction of adaptive soft sensors that are optimized for each process state in a plant where multiple process states exist, and the accurate prediction of objective variable values through integrating the constructed adaptive soft sensors as the process state changes. The effectiveness of the proposed method was tested using two datasets from actual plants, and we confirmed that it could accurately predict the objective variable values in each process state.
引用
收藏
页数:6
相关论文
共 50 条
  • [1] Adaptive soft sensor based on transfer learning and ensemble learning for multiple process states
    Yamada, Nobuhito
    Kaneko, Hiromasa
    [J]. ANALYTICAL SCIENCE ADVANCES, 2022, 3 (5-6): : 205 - 211
  • [2] Adaptive soft sensor considering process state in film manufacturing process and identification of critical process variables
    Shiraki, Yuya
    Nakayama, Yuki
    Natori, Satoshi
    Suda, Kazuya
    Ono, Yuki
    Kaneko, Hiromasa
    [J]. RESULTS IN CHEMISTRY, 2024, 9
  • [3] A Novel Adaptive Soft Sensor Using Multiple Heterogeneous Model Ensemble Learning
    Xiao, Hongjun
    Huang, Daoping
    Liu, Yiqi
    [J]. 2015 4TH INTERNATIONAL CONFERENCE ON ENERGY AND ENVIRONMENTAL PROTECTION (ICEEP 2015), 2015, : 2762 - 2769
  • [4] Adaptive Soft Sensor based on Moving Gaussian Process Window
    Abusnina, Ali
    Kudenko, Daniel
    [J]. 2013 IEEE INTERNATIONAL CONFERENCE ON INDUSTRIAL TECHNOLOGY (ICIT), 2013, : 1051 - 1056
  • [5] Soft Sensor Modeling for Identifying Significant Process Variables with Time Delays
    Hikosaka, Tatsuya
    Aoshima, Shinichiro
    Miyao, Tomoyuki
    Funatsu, Kimito
    [J]. INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 2020, 59 (26) : 12156 - 12163
  • [6] Adaptive soft sensor for online prediction and process monitoring based on a mixture of Gaussian process models
    Grbic, Ratko
    Sliskovic, Drazen
    Kadlec, Petr
    [J]. COMPUTERS & CHEMICAL ENGINEERING, 2013, 58 : 84 - 97
  • [7] Adaptive soft sensor method based on online selective ensemble of partial least squares for quality prediction of chemical process
    Cang, Wentao
    Yang, Huizhong
    [J]. ASIA-PACIFIC JOURNAL OF CHEMICAL ENGINEERING, 2019, 14 (05)
  • [8] Developing an Adaptive Soft Sensor Using a Predictive Filter for a Nonstationary Process
    Klimchenko, V. V.
    Snegirev, O. Yu.
    Shevlyagina, S. A.
    Torgashov, A. Yu.
    [J]. AUTOMATION AND REMOTE CONTROL, 2022, 83 (12) : 1984 - 1994
  • [9] Developing an Adaptive Soft Sensor Using a Predictive Filter for a Nonstationary Process
    V. V. Klimchenko
    O. Yu. Snegirev
    S. A. Shevlyagina
    A. Yu. Torgashov
    [J]. Automation and Remote Control, 2022, 83 : 1984 - 1994
  • [10] Maintenance-free soft sensor models with time difference of process variables
    Kaneko, Hiromasa
    Funatsu, Kimito
    [J]. CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2011, 107 (02) : 312 - 317