Prediction and Uncertainty Propagation for Completion Time of Batch Processes Based on Data-Driven Modeling

被引:6
|
作者
Zhou, Le [1 ]
Chuang, Yao-Chen [2 ]
Hsu, Shao-Heng [2 ]
Yao, Yuan [2 ]
Chen, Tao [3 ]
机构
[1] Zhejiang Univ Sci & Technol, Sch Automat & Elect Engn, Hangzhou 310023, Zhejiang, Peoples R China
[2] Natl Tsing Hua Univ, Dept Chem Engn, Hsinchu 30013, Taiwan
[3] Univ Surrey, Dept Chem & Proc Engn, Guildford GU2 7XH, Surrey, England
基金
中国国家自然科学基金; 英国生物技术与生命科学研究理事会;
关键词
LATENT VARIABLE MODELS; QUALITY PREDICTION; REGRESSION; FERMENTATION; ANALYTICS; KNOWLEDGE; VALUES; ERRORS; PCA;
D O I
10.1021/acs.iecr.0c01236
中图分类号
TQ [化学工业];
学科分类号
0817 ;
摘要
Batch processes have been playing a crucial role for the flexibility in producing low-volume and high-value-added products. Due to the fluctuations of raw materials and operation conditions, the batch duration often varies. Prediction of batch completion time is important for the purpose of process scheduling and optimization. Existing studies of this subject have focused on the prediction accuracy, while the importance of the prediction uncertainty has been under-explored. When the key variable defining the completion time changes slowly toward the end of a batch, the prediction uncertainty tends to be large. Under such situations, we argue that the uncertainty should always be considered along with the mean prediction for practical use. To this end, two data-driven prediction methods using probabilistic principal component analysis and bootstrapping case-based reasoning are developed, followed by the uncertainty quantification in the probabilistic framework. Finally, two batch processes are used to demonstrate the importance of prediction uncertainty and the efficiency of the proposed schemes.
引用
收藏
页码:14374 / 14384
页数:11
相关论文
共 50 条
  • [21] Data-Driven Surrogate Model and Admissible-Region-Based Orbital Uncertainty Propagation
    Jia, Bin
    Xin, Ming
    JOURNAL OF AEROSPACE INFORMATION SYSTEMS, 2022, 19 (12): : 753 - 770
  • [22] Knowledge-based and data-driven fuzzy modeling for rockburst prediction
    Adoko, Amoussou Coffi
    Gokceoglu, Candan
    Wu, Li
    Zuo, Qing Jun
    INTERNATIONAL JOURNAL OF ROCK MECHANICS AND MINING SCIENCES, 2013, 61 : 86 - 95
  • [23] An Improved Data-Driven Modeling Method for Aircraft Based on Prediction and Optimization
    Su, Shihong
    Xiao, Bing
    Li, Lingwei
    Luo, Jinfeng
    Zhao, Hui
    2023 35TH CHINESE CONTROL AND DECISION CONFERENCE, CCDC, 2023, : 2560 - 2565
  • [24] Data-Driven Batch Scheduling
    Bent, John
    Denehy, Timothy E.
    Livny, Miron
    Arpaci-Dusseau, Andrea C.
    Arpaci-Dusseau, Remzi H.
    DADC 2009: SECOND INTERNATIONAL WORKSHOP ON DATA AWARE DISTRIBUTED COMPUTING, 2009, : 1 - 10
  • [25] Data-Driven Quality Prediction of Batch Processes Based on Minimal-Redundancy-Maximal-Relevance Integrated Convolutional Neural Network
    Dong, Yufeng
    Zhuang, Yingping
    Yan, Xuefeng
    MATHEMATICAL PROBLEMS IN ENGINEERING, 2021, 2021
  • [26] A Data-Driven Approach to Control of Batch Processes With an Application to a Gravimetric Blender
    Formentin, Simone
    Cologni, Alberto L.
    Previdi, Fabio
    Savaresi, Sergio M.
    IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2014, 61 (11) : 6383 - 6390
  • [27] Observational data-driven modeling and optimization of manufacturing processes
    Sadati, Najibesadat
    Chinnam, Ratna Babu
    Nezhad, Milad Zafar
    EXPERT SYSTEMS WITH APPLICATIONS, 2018, 93 : 456 - 464
  • [28] Data-driven Quality Control of Batch Processes via Subspace Identification
    Corbett, Brandon
    Mhaskar, Prashant
    2016 AMERICAN CONTROL CONFERENCE (ACC), 2016, : 4163 - 4168
  • [29] Data-Driven Modeling Methods and Techniques for Pharmaceutical Processes
    Dong, Yachao
    Yang, Ting
    Xing, Yafeng
    Du, Jian
    Meng, Qingwei
    PROCESSES, 2023, 11 (07)
  • [30] Integrated Process and Decision Modeling for Data-Driven Processes
    van der Aa, Han
    Leopold, Henrik
    Batoulis, Kimon
    Weske, Mathias
    Reijers, Hajo A.
    BUSINESS PROCESS MANAGEMENT WORKSHOPS, (BPM 2015), 2016, 256 : 405 - 417