A Comparative Study of Different Kernel Functions Applied to LW-KPLS Model for Nonlinear Processes

Soft sensors are inferential estimators when the employment of hardware sensors is inapplicable, expensive, or difficult in industrial plant processes. Currently, a simple soft sensor, namely locally weighted partial least squares (LW-PLS), which can cope with the nonlinearity of the process, has...

Full description

Bibliographic Details
Main Authors: Ngu, Joyce Chen Yen, Yeo, Christine
Format: Journal Article
Published: Comporter SRL 2022
Online Access:http://hdl.handle.net/20.500.11937/88287
_version_ 1848765000166932480
author Ngu, Joyce Chen Yen
Yeo, Christine
author_facet Ngu, Joyce Chen Yen
Yeo, Christine
author_sort Ngu, Joyce Chen Yen
building Curtin Institutional Repository
collection Online Access
description Soft sensors are inferential estimators when the employment of hardware sensors is inapplicable, expensive, or difficult in industrial plant processes. Currently, a simple soft sensor, namely locally weighted partial least squares (LW-PLS), which can cope with the nonlinearity of the process, has been developed. However, LW-PLS exhibits the disadvantages of handling strong nonlinear process data. To address this problem, Kernel functions are integrated into LW-PLS to form locally weighted Kernel partial least squares (LW-KPLS). Notice that a minimal study was carried out on the impact of different kernel functions that have not been integrated with the LW-KPLS, in which this model has the potential to be applied to different chemical-related nonlinear processes. Thus, this study investigates the predictive performance of LW-KPLS with several different Kernel functions using three nonlinear case studies. As the results, the predictive performances of LW-KPLS with Polynomial Kernel are better than other Kernel functions. The values of root-mean-square errors (RMSE) and error of approximation (Ea) for the training and testing dataset by utilizing this Kernel function are the lowest in their respective case studies, which are 34.60% to 95.39% lower for RMSEs values and 68.20% to 95.49% smaller for Ea values.
first_indexed 2025-11-14T11:28:17Z
format Journal Article
id curtin-20.500.11937-88287
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T11:28:17Z
publishDate 2022
publisher Comporter SRL
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-882872022-05-06T08:05:18Z A Comparative Study of Different Kernel Functions Applied to LW-KPLS Model for Nonlinear Processes Ngu, Joyce Chen Yen Yeo, Christine Soft sensors are inferential estimators when the employment of hardware sensors is inapplicable, expensive, or difficult in industrial plant processes. Currently, a simple soft sensor, namely locally weighted partial least squares (LW-PLS), which can cope with the nonlinearity of the process, has been developed. However, LW-PLS exhibits the disadvantages of handling strong nonlinear process data. To address this problem, Kernel functions are integrated into LW-PLS to form locally weighted Kernel partial least squares (LW-KPLS). Notice that a minimal study was carried out on the impact of different kernel functions that have not been integrated with the LW-KPLS, in which this model has the potential to be applied to different chemical-related nonlinear processes. Thus, this study investigates the predictive performance of LW-KPLS with several different Kernel functions using three nonlinear case studies. As the results, the predictive performances of LW-KPLS with Polynomial Kernel are better than other Kernel functions. The values of root-mean-square errors (RMSE) and error of approximation (Ea) for the training and testing dataset by utilizing this Kernel function are the lowest in their respective case studies, which are 34.60% to 95.39% lower for RMSEs values and 68.20% to 95.49% smaller for Ea values. 2022 Journal Article http://hdl.handle.net/20.500.11937/88287 10.33263/BRIAC132.184 http://creativecommons.org/licenses/by/4.0/ Comporter SRL fulltext
spellingShingle Ngu, Joyce Chen Yen
Yeo, Christine
A Comparative Study of Different Kernel Functions Applied to LW-KPLS Model for Nonlinear Processes
title A Comparative Study of Different Kernel Functions Applied to LW-KPLS Model for Nonlinear Processes
title_full A Comparative Study of Different Kernel Functions Applied to LW-KPLS Model for Nonlinear Processes
title_fullStr A Comparative Study of Different Kernel Functions Applied to LW-KPLS Model for Nonlinear Processes
title_full_unstemmed A Comparative Study of Different Kernel Functions Applied to LW-KPLS Model for Nonlinear Processes
title_short A Comparative Study of Different Kernel Functions Applied to LW-KPLS Model for Nonlinear Processes
title_sort comparative study of different kernel functions applied to lw-kpls model for nonlinear processes
url http://hdl.handle.net/20.500.11937/88287