Process PLS: Incorporating substantive knowledge into the predictive modelling of multiblock, multistep, multidimensional and multicollinear process data

Geert van Kollenburg; Roel Bouman; Tim Offermans; Jan Gerretzen; Lutgarde Buydens; Henk-Jan van Manen; Jeroen Jansen

doi:10.1016/j.compchemeng.2021.107466

Process PLS: Incorporating substantive knowledge into the predictive modelling of multiblock, multistep, multidimensional and multicollinear process data

Geert van Kollenburg (Corresponding author), Roel Bouman, Tim Offermans, Jan Gerretzen, Lutgarde Buydens, Henk-Jan van Manen, Jeroen Jansen

Research output: Contribution to journal › Article › Academic › peer-review

11 Citations (Scopus)

145 Downloads (Pure)

Abstract

Chemical production processes benefit from intelligent data analysis. Previous work showed how process knowledge can be included in a structural equation modelling framework. While predictive models increase process value, currently available methods have limitations that hinder applicability to many (industrial) processes. This paper describes the Process PLS algorithm which can analyze multi-block, multistep and/or multidimensional processes. Process PLS was benchmarked on a simulated crude oil distillation process. Analysis of 22 empirical data sets from a production process at Nouryon illustrated how Process PLS solves limitations of PLS path modelling. In the analysis of the benchmark Val de Loire data, Process PLS revealed substantially meaningful effects which the recently proposed Sequential Orthogonalized PLS path modelling completely missed. Process PLS is a promising approach that enables data-driven analysis of process data using information on the complex process structure, to demonstrably increase insight in the underlying system, making model-based predictions much more valuable.

Original language	English
Article number	107466
Number of pages	15
Journal	Computers and Chemical Engineering
Volume	154
DOIs	https://doi.org/10.1016/j.compchemeng.2021.107466
Publication status	Published - Nov 2021

Funding

This research was supported by the Dutch Research Council (NWO) and by TKI-E&I with the supplementary grant 'TKI-Toeslag' for Topconsortia for Knowledge and Innovation (TKI's) of the Ministry of Economic Affairs and Climate Policy. Part of the work presented in this paper was done through funding from the ECSEL Joint Undertaking (JU) under grant agreement No 826589. The JU receives support from the European Union's Horizon 2020 research and innovation programme and Netherlands, Belgium, Germany, France, Italy, Austria, Hungary, Romania, Sweden and Israel. The authors thank all partners within the ?Outfitting the Factory of the Future with Online analysis (OFF/On)? consortium, managed by Comprehensive Analytical Science and Technology (COAST) in Amsterdam, The Netherlands, and partners within the ?Integrating Sensor Based Process Monitoring and Advanced Process Control (INSPEC)? project, managed by the Institute for Sustainable Process Technology (ISPT) in Amersfoort, The Netherlands. The authors would like to thank Vladimir Obradovic for providing the benchmarking data. This research was supported by the Dutch Research Council (NWO) and by TKI-E&I with the supplementary grant 'TKI-Toeslag' for Topconsortia for Knowledge and Innovation (TKI's) of the Ministry of Economic Affairs and Climate Policy. Part of the work presented in this paper was done through funding from the ECSEL Joint Undertaking (JU) under grant agreement No 826589. The JU receives support from the European Union’s Horizon 2020 research and innovation programme and Netherlands, Belgium, Germany, France, Italy, Austria, Hungary, Romania, Sweden and Israel. The authors thank all partners within the ‘Outfitting the Factory of the Future with Online analysis (OFF/On)’ consortium, managed by Comprehensive Analytical Science and Technology (COAST) in Amsterdam, The Netherlands, and partners within the ‘Integrating Sensor Based Process Monitoring and Advanced Process Control (INSPEC)’ project, managed by the Institute for Sustainable Process Technology (ISPT) in Amersfoort, The Netherlands. The authors would like to thank Vladimir Obradovic for providing the benchmarking data.

Access to Document

10.1016/j.compchemeng.2021.107466

published versionFinal published version, 3.18 MBLicence: CC BY

Cite this

van Kollenburg, G., Bouman, R., Offermans, T., Gerretzen, J., Buydens, L., van Manen, H.-J., & Jansen, J. (2021). Process PLS: Incorporating substantive knowledge into the predictive modelling of multiblock, multistep, multidimensional and multicollinear process data. Computers and Chemical Engineering, 154, Article 107466. https://doi.org/10.1016/j.compchemeng.2021.107466

@article{dd41ac03cd764d189c8d356a2d761572,

title = "Process PLS: Incorporating substantive knowledge into the predictive modelling of multiblock, multistep, multidimensional and multicollinear process data",

abstract = "Chemical production processes benefit from intelligent data analysis. Previous work showed how process knowledge can be included in a structural equation modelling framework. While predictive models increase process value, currently available methods have limitations that hinder applicability to many (industrial) processes. This paper describes the Process PLS algorithm which can analyze multi-block, multistep and/or multidimensional processes. Process PLS was benchmarked on a simulated crude oil distillation process. Analysis of 22 empirical data sets from a production process at Nouryon illustrated how Process PLS solves limitations of PLS path modelling. In the analysis of the benchmark Val de Loire data, Process PLS revealed substantially meaningful effects which the recently proposed Sequential Orthogonalized PLS path modelling completely missed. Process PLS is a promising approach that enables data-driven analysis of process data using information on the complex process structure, to demonstrably increase insight in the underlying system, making model-based predictions much more valuable.",

author = "{van Kollenburg}, Geert and Roel Bouman and Tim Offermans and Jan Gerretzen and Lutgarde Buydens and {van Manen}, Henk-Jan and Jeroen Jansen",

note = "Funding Information: This research was supported by the Dutch Research Council (NWO) and by TKI-E&I with the supplementary grant 'TKI-Toeslag' for Topconsortia for Knowledge and Innovation (TKI's) of the Ministry of Economic Affairs and Climate Policy. Part of the work presented in this paper was done through funding from the ECSEL Joint Undertaking (JU) under grant agreement No 826589. The JU receives support from the European Union's Horizon 2020 research and innovation programme and Netherlands, Belgium, Germany, France, Italy, Austria, Hungary, Romania, Sweden and Israel. The authors thank all partners within the ?Outfitting the Factory of the Future with Online analysis (OFF/On)? consortium, managed by Comprehensive Analytical Science and Technology (COAST) in Amsterdam, The Netherlands, and partners within the ?Integrating Sensor Based Process Monitoring and Advanced Process Control (INSPEC)? project, managed by the Institute for Sustainable Process Technology (ISPT) in Amersfoort, The Netherlands. The authors would like to thank Vladimir Obradovic for providing the benchmarking data. Funding Information: This research was supported by the Dutch Research Council (NWO) and by TKI-E&I with the supplementary grant 'TKI-Toeslag' for Topconsortia for Knowledge and Innovation (TKI's) of the Ministry of Economic Affairs and Climate Policy. Part of the work presented in this paper was done through funding from the ECSEL Joint Undertaking (JU) under grant agreement No 826589. The JU receives support from the European Union{\textquoteright}s Horizon 2020 research and innovation programme and Netherlands, Belgium, Germany, France, Italy, Austria, Hungary, Romania, Sweden and Israel. The authors thank all partners within the {\textquoteleft}Outfitting the Factory of the Future with Online analysis (OFF/On){\textquoteright} consortium, managed by Comprehensive Analytical Science and Technology (COAST) in Amsterdam, The Netherlands, and partners within the {\textquoteleft}Integrating Sensor Based Process Monitoring and Advanced Process Control (INSPEC){\textquoteright} project, managed by the Institute for Sustainable Process Technology (ISPT) in Amersfoort, The Netherlands. The authors would like to thank Vladimir Obradovic for providing the benchmarking data. Publisher Copyright: {\textcopyright} 2021 The Author(s)",

year = "2021",

month = nov,

doi = "10.1016/j.compchemeng.2021.107466",

language = "English",

volume = "154",

journal = "Computers and Chemical Engineering",

issn = "0098-1354",

publisher = "Elsevier B.V.",

}

Process PLS: Incorporating substantive knowledge into the predictive modelling of multiblock, multistep, multidimensional and multicollinear process data. / van Kollenburg, Geert (Corresponding author); Bouman, Roel; Offermans, Tim et al.
In: Computers and Chemical Engineering, Vol. 154, 107466, 11.2021.

Research output: Contribution to journal › Article › Academic › peer-review

TY - JOUR

T1 - Process PLS: Incorporating substantive knowledge into the predictive modelling of multiblock, multistep, multidimensional and multicollinear process data

AU - van Kollenburg, Geert

AU - Bouman, Roel

AU - Offermans, Tim

AU - Gerretzen, Jan

AU - Buydens, Lutgarde

AU - van Manen, Henk-Jan

AU - Jansen, Jeroen

N1 - Funding Information: This research was supported by the Dutch Research Council (NWO) and by TKI-E&I with the supplementary grant 'TKI-Toeslag' for Topconsortia for Knowledge and Innovation (TKI's) of the Ministry of Economic Affairs and Climate Policy. Part of the work presented in this paper was done through funding from the ECSEL Joint Undertaking (JU) under grant agreement No 826589. The JU receives support from the European Union's Horizon 2020 research and innovation programme and Netherlands, Belgium, Germany, France, Italy, Austria, Hungary, Romania, Sweden and Israel. The authors thank all partners within the ?Outfitting the Factory of the Future with Online analysis (OFF/On)? consortium, managed by Comprehensive Analytical Science and Technology (COAST) in Amsterdam, The Netherlands, and partners within the ?Integrating Sensor Based Process Monitoring and Advanced Process Control (INSPEC)? project, managed by the Institute for Sustainable Process Technology (ISPT) in Amersfoort, The Netherlands. The authors would like to thank Vladimir Obradovic for providing the benchmarking data. Funding Information: This research was supported by the Dutch Research Council (NWO) and by TKI-E&I with the supplementary grant 'TKI-Toeslag' for Topconsortia for Knowledge and Innovation (TKI's) of the Ministry of Economic Affairs and Climate Policy. Part of the work presented in this paper was done through funding from the ECSEL Joint Undertaking (JU) under grant agreement No 826589. The JU receives support from the European Union’s Horizon 2020 research and innovation programme and Netherlands, Belgium, Germany, France, Italy, Austria, Hungary, Romania, Sweden and Israel. The authors thank all partners within the ‘Outfitting the Factory of the Future with Online analysis (OFF/On)’ consortium, managed by Comprehensive Analytical Science and Technology (COAST) in Amsterdam, The Netherlands, and partners within the ‘Integrating Sensor Based Process Monitoring and Advanced Process Control (INSPEC)’ project, managed by the Institute for Sustainable Process Technology (ISPT) in Amersfoort, The Netherlands. The authors would like to thank Vladimir Obradovic for providing the benchmarking data. Publisher Copyright: © 2021 The Author(s)

PY - 2021/11

Y1 - 2021/11

N2 - Chemical production processes benefit from intelligent data analysis. Previous work showed how process knowledge can be included in a structural equation modelling framework. While predictive models increase process value, currently available methods have limitations that hinder applicability to many (industrial) processes. This paper describes the Process PLS algorithm which can analyze multi-block, multistep and/or multidimensional processes. Process PLS was benchmarked on a simulated crude oil distillation process. Analysis of 22 empirical data sets from a production process at Nouryon illustrated how Process PLS solves limitations of PLS path modelling. In the analysis of the benchmark Val de Loire data, Process PLS revealed substantially meaningful effects which the recently proposed Sequential Orthogonalized PLS path modelling completely missed. Process PLS is a promising approach that enables data-driven analysis of process data using information on the complex process structure, to demonstrably increase insight in the underlying system, making model-based predictions much more valuable.

AB - Chemical production processes benefit from intelligent data analysis. Previous work showed how process knowledge can be included in a structural equation modelling framework. While predictive models increase process value, currently available methods have limitations that hinder applicability to many (industrial) processes. This paper describes the Process PLS algorithm which can analyze multi-block, multistep and/or multidimensional processes. Process PLS was benchmarked on a simulated crude oil distillation process. Analysis of 22 empirical data sets from a production process at Nouryon illustrated how Process PLS solves limitations of PLS path modelling. In the analysis of the benchmark Val de Loire data, Process PLS revealed substantially meaningful effects which the recently proposed Sequential Orthogonalized PLS path modelling completely missed. Process PLS is a promising approach that enables data-driven analysis of process data using information on the complex process structure, to demonstrably increase insight in the underlying system, making model-based predictions much more valuable.

UR - http://www.scopus.com/inward/record.url?scp=85111826933&partnerID=8YFLogxK

U2 - 10.1016/j.compchemeng.2021.107466

DO - 10.1016/j.compchemeng.2021.107466

M3 - Article

AN - SCOPUS:85111826933

SN - 0098-1354

VL - 154

JO - Computers and Chemical Engineering

JF - Computers and Chemical Engineering

M1 - 107466

ER -

Process PLS: Incorporating substantive knowledge into the predictive modelling of multiblock, multistep, multidimensional and multicollinear process data

Abstract

Funding

Access to Document

Other files and links

Fingerprint

Improved understanding of industrial process relationships through conditional path modelling with Process PLS

Data, software and scripts related to the Process PLS methodology manuscript

Cite this

Process PLS: Incorporating substantive knowledge into the predictive modelling of multiblock, multistep, multidimensional and multicollinear process data

Abstract

Funding

Access to Document

Other files and links

Fingerprint

Research output

Improved understanding of industrial process relationships through conditional path modelling with Process PLS

Datasets

Data, software and scripts related to the Process PLS methodology manuscript

Cite this