Soft sensor development based on kernel dynamic time warping and a relevant vector machine for unequal-length batch processes

被引:18
|
作者
Qiu, Kepeng [1 ]
Wang, Jianlin [1 ]
Wang, Rutong [1 ]
Guo, Yongqi [1 ]
Zhao, Liqiang [1 ]
机构
[1] Beijing Univ Chem Technol, Coll Informat Sci & Technol, Beijing 100029, Peoples R China
基金
中国国家自然科学基金;
关键词
Batch processes; Unequal-length data; Soft sensor; Dynamic time warping; Trajectory synchronization; Relevant vector machine; REGRESSION-MODEL; EDIT DISTANCE; ALIGNMENT; TRAJECTORIES;
D O I
10.1016/j.eswa.2021.115223
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The unequal-length problem in batch process data directly affects the performance of data-driven soft sensors. Meanwhile, the nonlinearity and high dimensionality of batch process data make the unequal-length problem more serious, and the development of effective soft sensors for unequal-length batch processes has become a challenge. To fully address this challenge, an effective soft sensor based on kernel dynamic time warping and a relevant vector machine is proposed in this paper. The proposed soft sensor consists of trajectory synchronization and online prediction modeling. First, combining the kernel trick, we design a kernel DTW (KerDTW) algorithm to effectively solve the synchronization of unequal-length trajectories with high dimensionality and strong nonlinearity characteristics. Meanwhile, a novel synchronization performance combination index (SPCI) is proposed to realize adaptive selection of the optimal parameter of the KerDTW algorithm. Then, based on the synchronized batch trajectories using the KerDTW algorithm, an online prediction model is established using an RVM to achieve online quality prediction of nonlinear process data. The effectiveness of the proposed soft sensor is illustrated through a penicillin fermentation process.
引用
收藏
页数:15
相关论文
共 50 条
  • [1] Soft sensor development based on improved just-in-time learning and relevant vector machine for batch processes
    Wang, Jianlin
    Qiu, Kepeng
    Guo, Yongqi
    Wang, Rutong
    Zhou, Xinjie
    [J]. CANADIAN JOURNAL OF CHEMICAL ENGINEERING, 2021, 99 (01): : 334 - 344
  • [2] Development of Soft Sensor Based on Sequential Kernel Fuzzy Partitioning and Just-in-Time Relevance Vector Machine for Multiphase Batch Processes
    Wang, Jianlin
    Qiu, Kepeng
    Wang, Rutong
    Zhou, Xinjie
    Guo, Yongqi
    [J]. IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2021, 70
  • [3] Soft sensor development based on just-in-time learning and dynamic time warping for multi-grade processes
    Song, Min Jun
    Ju, Sung Hyun
    Lee, Jong Min
    [J]. KOREAN JOURNAL OF CHEMICAL ENGINEERING, 2023, 40 (05) : 1023 - 1036
  • [4] Soft sensor development based on just-in-time learning and dynamic time warping for multi-grade processes
    Min Jun Song
    Sung Hyun Ju
    Jong Min Lee
    [J]. Korean Journal of Chemical Engineering, 2023, 40 : 1023 - 1036
  • [5] Controller Performance Assessment of Batch Processes Based on Dynamic Time Warping
    Cai, Yijun
    Zhou, Mengfei
    Zou, Tao
    Xia, Luyue
    [J]. 2010 8TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION (WCICA), 2010, : 4165 - 4168
  • [6] Real-Time Fire Detection Algorithm Based on Support Vector Machine with Dynamic Time Warping Kernel Function
    Baek, Jaeseung
    Alhindi, Taha J.
    Jeong, Myong K.
    Jeong, Young-Seon
    Seo, Seongho
    Kang, Jongseok
    Choi, Jaekyung
    Chung, Hyunsang
    [J]. FIRE TECHNOLOGY, 2021, 57 (06) : 2929 - 2953
  • [7] Real-Time Fire Detection Algorithm Based on Support Vector Machine with Dynamic Time Warping Kernel Function
    Jaeseung Baek
    Taha J. Alhindi
    Young-Seon Jeong
    Myong K. Jeong
    Seongho Seo
    Jongseok Kang
    Jaekyung Choi
    Hyunsang Chung
    [J]. Fire Technology, 2021, 57 : 2929 - 2953
  • [8] Study on the soft sensor of multi-kernel relevance vector machine based on time difference
    Wu, Jing
    Liu, Yiqi
    Liu, Jian
    Huang, Daoping
    Qiu, Yu
    Yu, Guangping
    [J]. Huagong Xuebao/CIESC Journal, 2019, 70 (04): : 1472 - 1484
  • [9] On the time series support vector machine using dynamic time warping kernel for brain activity classification
    Chaovalitwongse W.A.
    Pardalos P.M.
    [J]. Cybernetics and Systems Analysis, 2008, 44 (01) : 125 - 138
  • [10] Clustering of interval-valued time series of unequal length based on improved dynamic time warping
    Wang, Xiao
    Yu, Fusheng
    Pedrycz, Witold
    Yu, Lian
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2019, 125 : 293 - 304