Modeling of adaptive multi-output soft-sensors with applications in wastewater treatments

Jing Wu, Hongchao Cheng, Yiqi Liu, Bin Liu, Daoping Huang

Research output: Contribution to journalArticle

Abstract

Given the multivariable coupling, strong nonlinearity and time-varying features in the wastewater treatment processes, adaptive strategies, including just-in-time learning (JITL), time difference (TD), and moving window (MW) methods have been chosen in this paper to enhance multi-output soft-sensor models to ensure online prediction for a variety of hard-to-measure variables simultaneously. In the proposed adaptive multi-output soft-sensors, multi-output partial least squares (MPLS), multi-output relevant vector machine (MRVM) and multi-output Gaussian process regression (MGPR) served as the multi-output models. The integration of adaptive strategies and multi-output models not only provides a solution for multi-output prediction, but also offers a potential to alleviate the degradation of multi-output soft-sensors. To further improve the adaptive ability, four adaptive soft-sensors, termed TD-MW, TD-JIT, JIT-MW, and TD-JIT-MW, have been proposed by mixing the three aforementioned adaptive strategies to upgrade multi-output softsensors. All the adaptive multi-output soft-sensors are analyzed and compared in terms of simulation data and practical industrial data, which exhibit stationary and nonstationary behaviors, respectively.
LanguageEnglish
Pages161887-161898
Number of pages12
JournalIEEE Access
Volume7
DOIs
Publication statusPublished - 29 Oct 2019

Fingerprint

Wastewater treatment
Sensors
Sensor
Modeling
Degradation
Just-in-time

Keywords

  • adaptive soft sensor
  • multiple-output
  • wastewater treatment plants
  • multiple adaptive mechanisms

Cite this

Wu, Jing ; Cheng, Hongchao ; Liu, Yiqi ; Liu, Bin ; Huang, Daoping. / Modeling of adaptive multi-output soft-sensors with applications in wastewater treatments. In: IEEE Access. 2019 ; Vol. 7. pp. 161887-161898.
@article{710330461f6647a8a23bfb99d6f18d29,
title = "Modeling of adaptive multi-output soft-sensors with applications in wastewater treatments",
abstract = "Given the multivariable coupling, strong nonlinearity and time-varying features in the wastewater treatment processes, adaptive strategies, including just-in-time learning (JITL), time difference (TD), and moving window (MW) methods have been chosen in this paper to enhance multi-output soft-sensor models to ensure online prediction for a variety of hard-to-measure variables simultaneously. In the proposed adaptive multi-output soft-sensors, multi-output partial least squares (MPLS), multi-output relevant vector machine (MRVM) and multi-output Gaussian process regression (MGPR) served as the multi-output models. The integration of adaptive strategies and multi-output models not only provides a solution for multi-output prediction, but also offers a potential to alleviate the degradation of multi-output soft-sensors. To further improve the adaptive ability, four adaptive soft-sensors, termed TD-MW, TD-JIT, JIT-MW, and TD-JIT-MW, have been proposed by mixing the three aforementioned adaptive strategies to upgrade multi-output softsensors. All the adaptive multi-output soft-sensors are analyzed and compared in terms of simulation data and practical industrial data, which exhibit stationary and nonstationary behaviors, respectively.",
keywords = "adaptive soft sensor, multiple-output, wastewater treatment plants, multiple adaptive mechanisms",
author = "Jing Wu and Hongchao Cheng and Yiqi Liu and Bin Liu and Daoping Huang",
year = "2019",
month = "10",
day = "29",
doi = "10.1109/ACCESS.2019.2950034",
language = "English",
volume = "7",
pages = "161887--161898",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "IEEE",

}

Modeling of adaptive multi-output soft-sensors with applications in wastewater treatments. / Wu, Jing ; Cheng, Hongchao ; Liu, Yiqi; Liu, Bin; Huang, Daoping.

In: IEEE Access, Vol. 7, 29.10.2019, p. 161887-161898.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Modeling of adaptive multi-output soft-sensors with applications in wastewater treatments

AU - Wu, Jing

AU - Cheng, Hongchao

AU - Liu, Yiqi

AU - Liu, Bin

AU - Huang, Daoping

PY - 2019/10/29

Y1 - 2019/10/29

N2 - Given the multivariable coupling, strong nonlinearity and time-varying features in the wastewater treatment processes, adaptive strategies, including just-in-time learning (JITL), time difference (TD), and moving window (MW) methods have been chosen in this paper to enhance multi-output soft-sensor models to ensure online prediction for a variety of hard-to-measure variables simultaneously. In the proposed adaptive multi-output soft-sensors, multi-output partial least squares (MPLS), multi-output relevant vector machine (MRVM) and multi-output Gaussian process regression (MGPR) served as the multi-output models. The integration of adaptive strategies and multi-output models not only provides a solution for multi-output prediction, but also offers a potential to alleviate the degradation of multi-output soft-sensors. To further improve the adaptive ability, four adaptive soft-sensors, termed TD-MW, TD-JIT, JIT-MW, and TD-JIT-MW, have been proposed by mixing the three aforementioned adaptive strategies to upgrade multi-output softsensors. All the adaptive multi-output soft-sensors are analyzed and compared in terms of simulation data and practical industrial data, which exhibit stationary and nonstationary behaviors, respectively.

AB - Given the multivariable coupling, strong nonlinearity and time-varying features in the wastewater treatment processes, adaptive strategies, including just-in-time learning (JITL), time difference (TD), and moving window (MW) methods have been chosen in this paper to enhance multi-output soft-sensor models to ensure online prediction for a variety of hard-to-measure variables simultaneously. In the proposed adaptive multi-output soft-sensors, multi-output partial least squares (MPLS), multi-output relevant vector machine (MRVM) and multi-output Gaussian process regression (MGPR) served as the multi-output models. The integration of adaptive strategies and multi-output models not only provides a solution for multi-output prediction, but also offers a potential to alleviate the degradation of multi-output soft-sensors. To further improve the adaptive ability, four adaptive soft-sensors, termed TD-MW, TD-JIT, JIT-MW, and TD-JIT-MW, have been proposed by mixing the three aforementioned adaptive strategies to upgrade multi-output softsensors. All the adaptive multi-output soft-sensors are analyzed and compared in terms of simulation data and practical industrial data, which exhibit stationary and nonstationary behaviors, respectively.

KW - adaptive soft sensor

KW - multiple-output

KW - wastewater treatment plants

KW - multiple adaptive mechanisms

U2 - 10.1109/ACCESS.2019.2950034

DO - 10.1109/ACCESS.2019.2950034

M3 - Article

VL - 7

SP - 161887

EP - 161898

JO - IEEE Access

T2 - IEEE Access

JF - IEEE Access

SN - 2169-3536

ER -