A machine learning approach for the design of hyperbranched polymeric dispersing agents based on aliphatic polyesters for radiation-curable inks

Danny E.P. Vanpoucke; Marie A.F. Delgove; Jules Stouten; Jurrie Noordijk; Nils De Vos; Kamiel Matthysen; Geert G.P. Deroover; Siamak Mehrkanoon; Katrien V. Bernaerts

doi:10.1002/pi.6378

A machine learning approach for the design of hyperbranched polymeric dispersing agents based on aliphatic polyesters for radiation-curable inks

Danny E.P. Vanpoucke, Marie A.F. Delgove, Jules Stouten, Jurrie Noordijk, Nils De Vos, Kamiel Matthysen, Geert G.P. Deroover, Siamak Mehrkanoon, Katrien V. Bernaerts^*

^*Corresponding author for this work

Sub Algorithmic Data Analysis

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

Abstract

Polymeric dispersing agents were prepared from aliphatic polyesters consisting of δ-undecalactone (UDL) and β,δ-trimethyl-ε-caprolactones (TMCL) as biobased monomers, which were polymerized in bulk via organocatalysts. Graft copolymers were obtained by coupling of the polyesters to poly(ethylene imine) (PEI) in the bulk without using solvents. Various parameters that influence the performance of the dispersing agents in pigment-based UV-curable matrices were investigated: chemistry of the polyester (UDL or TMCL), polyester/PEI weight ratio, molecular weight of the polyesters and of PEI. The performance of the dispersing agents was modelled using machine learning in order to increase the efficiency of the dispersant design. The resulting models were presented as analytical models for the individual polyesters and the synthesis conditions for optimally performing dispersing agents were indicated as a preference for high-molecular-weight polyesters and a polyester-dependent maximum polyester/PEI weight ratio.

Original language	English
Pages (from-to)	966-975
Number of pages	10
Journal	Polymer International
Volume	71
Issue number	8
DOIs	https://doi.org/10.1002/pi.6378
Publication status	Published - Aug 2022

Bibliographical note

Funding Information:
MD, KB, ND, KM and GD received funding from the European Union (EU) project ROBOX (grant agreement no. 635734) under the EU's Horizon 2020 Programme Research and Innovation actions H2020-LEIT BIO-2014-1. The views and opinions expressed in this article are only those of the authors, and do not necessarily reflect those of the European Union Research Agency. The European Union is not liable for any use that may be made of the information contained herein. DV, JS and KB acknowledge the project D-NL-HIT carried out in the framework of INTERREG-Program Deutschland-Nederland, which is co-financed by the European Union, the MWIDE NRW, the Ministerie van Economische Zaken en Klimaat and the provinces of Limburg, Gelderland, Noord-Brabant and Overijssel.

Funding Information:
MD, KB, ND, KM and GD received funding from the European Union (EU) project ROBOX (grant agreement no. 635734) under the EU’s Horizon 2020 Programme Research and Innovation actions H2020‐LEIT BIO‐2014‐1. The views and opinions expressed in this article are only those of the authors, and do not necessarily reflect those of the European Union Research Agency. The European Union is not liable for any use that may be made of the information contained herein. DV, JS and KB acknowledge the project D‐NL‐HIT carried out in the framework of INTERREG‐Program Deutschland‐Nederland, which is co‐financed by the European Union, the MWIDE NRW, the Ministerie van Economische Zaken en Klimaat and the provinces of Limburg, Gelderland, Noord‐Brabant and Overijssel.

Publisher Copyright:
© 2022 The Authors. Polymer International published by John Wiley & Sons Ltd on behalf of Society of Industrial Chemistry.

Funding

MD, KB, ND, KM and GD received funding from the European Union (EU) project ROBOX (grant agreement no. 635734) under the EU’s Horizon 2020 Programme Research and Innovation actions H2020‐LEIT BIO‐2014‐1. The views and opinions expressed in this article are only those of the authors, and do not necessarily reflect those of the European Union Research Agency. The European Union is not liable for any use that may be made of the information contained herein. DV, JS and KB acknowledge the project D‐NL‐HIT carried out in the framework of INTERREG‐Program Deutschland‐Nederland, which is co‐financed by the European Union, the MWIDE NRW, the Ministerie van Economische Zaken en Klimaat and the provinces of Limburg, Gelderland, Noord‐Brabant and Overijssel.

Keywords

dispersant
machine learning
poly(ethylene imine)
polyester
structure–property relationships

Access to Document

10.1002/pi.6378Licence: CC BY-NC-ND

Polymer International - 2022 - Vanpoucke - A machine learning approach for the design of hyperbranched polymeric dispersingFinal published version, 2.08 MBLicence: CC BY-NC-ND

Cite this

Vanpoucke, D. E. P., Delgove, M. A. F., Stouten, J., Noordijk, J., De Vos, N., Matthysen, K., Deroover, G. G. P., Mehrkanoon, S., & Bernaerts, K. V. (2022). A machine learning approach for the design of hyperbranched polymeric dispersing agents based on aliphatic polyesters for radiation-curable inks. Polymer International, 71(8), 966-975. https://doi.org/10.1002/pi.6378

@article{ab3ff050a84b4dfb88566f1392a0d66d,

title = "A machine learning approach for the design of hyperbranched polymeric dispersing agents based on aliphatic polyesters for radiation-curable inks",

abstract = "Polymeric dispersing agents were prepared from aliphatic polyesters consisting of δ-undecalactone (UDL) and β,δ-trimethyl-ε-caprolactones (TMCL) as biobased monomers, which were polymerized in bulk via organocatalysts. Graft copolymers were obtained by coupling of the polyesters to poly(ethylene imine) (PEI) in the bulk without using solvents. Various parameters that influence the performance of the dispersing agents in pigment-based UV-curable matrices were investigated: chemistry of the polyester (UDL or TMCL), polyester/PEI weight ratio, molecular weight of the polyesters and of PEI. The performance of the dispersing agents was modelled using machine learning in order to increase the efficiency of the dispersant design. The resulting models were presented as analytical models for the individual polyesters and the synthesis conditions for optimally performing dispersing agents were indicated as a preference for high-molecular-weight polyesters and a polyester-dependent maximum polyester/PEI weight ratio.",

keywords = "dispersant, machine learning, poly(ethylene imine), polyester, structure–property relationships",

author = "Vanpoucke, {Danny E.P.} and Delgove, {Marie A.F.} and Jules Stouten and Jurrie Noordijk and {De Vos}, Nils and Kamiel Matthysen and Deroover, {Geert G.P.} and Siamak Mehrkanoon and Bernaerts, {Katrien V.}",

note = "Funding Information: MD, KB, ND, KM and GD received funding from the European Union (EU) project ROBOX (grant agreement no. 635734) under the EU's Horizon 2020 Programme Research and Innovation actions H2020-LEIT BIO-2014-1. The views and opinions expressed in this article are only those of the authors, and do not necessarily reflect those of the European Union Research Agency. The European Union is not liable for any use that may be made of the information contained herein. DV, JS and KB acknowledge the project D-NL-HIT carried out in the framework of INTERREG-Program Deutschland-Nederland, which is co-financed by the European Union, the MWIDE NRW, the Ministerie van Economische Zaken en Klimaat and the provinces of Limburg, Gelderland, Noord-Brabant and Overijssel. Funding Information: MD, KB, ND, KM and GD received funding from the European Union (EU) project ROBOX (grant agreement no. 635734) under the EU{\textquoteright}s Horizon 2020 Programme Research and Innovation actions H2020‐LEIT BIO‐2014‐1. The views and opinions expressed in this article are only those of the authors, and do not necessarily reflect those of the European Union Research Agency. The European Union is not liable for any use that may be made of the information contained herein. DV, JS and KB acknowledge the project D‐NL‐HIT carried out in the framework of INTERREG‐Program Deutschland‐Nederland, which is co‐financed by the European Union, the MWIDE NRW, the Ministerie van Economische Zaken en Klimaat and the provinces of Limburg, Gelderland, Noord‐Brabant and Overijssel. Publisher Copyright: {\textcopyright} 2022 The Authors. Polymer International published by John Wiley & Sons Ltd on behalf of Society of Industrial Chemistry.",

year = "2022",

month = aug,

doi = "10.1002/pi.6378",

language = "English",

volume = "71",

pages = "966--975",

journal = "Polymer International",

issn = "0959-8103",

publisher = "John Wiley and Sons Ltd",

number = "8",

}

TY - JOUR

T1 - A machine learning approach for the design of hyperbranched polymeric dispersing agents based on aliphatic polyesters for radiation-curable inks

AU - Vanpoucke, Danny E.P.

AU - Delgove, Marie A.F.

AU - Stouten, Jules

AU - Noordijk, Jurrie

AU - De Vos, Nils

AU - Matthysen, Kamiel

AU - Deroover, Geert G.P.

AU - Mehrkanoon, Siamak

AU - Bernaerts, Katrien V.

N1 - Funding Information: MD, KB, ND, KM and GD received funding from the European Union (EU) project ROBOX (grant agreement no. 635734) under the EU's Horizon 2020 Programme Research and Innovation actions H2020-LEIT BIO-2014-1. The views and opinions expressed in this article are only those of the authors, and do not necessarily reflect those of the European Union Research Agency. The European Union is not liable for any use that may be made of the information contained herein. DV, JS and KB acknowledge the project D-NL-HIT carried out in the framework of INTERREG-Program Deutschland-Nederland, which is co-financed by the European Union, the MWIDE NRW, the Ministerie van Economische Zaken en Klimaat and the provinces of Limburg, Gelderland, Noord-Brabant and Overijssel. Funding Information: MD, KB, ND, KM and GD received funding from the European Union (EU) project ROBOX (grant agreement no. 635734) under the EU’s Horizon 2020 Programme Research and Innovation actions H2020‐LEIT BIO‐2014‐1. The views and opinions expressed in this article are only those of the authors, and do not necessarily reflect those of the European Union Research Agency. The European Union is not liable for any use that may be made of the information contained herein. DV, JS and KB acknowledge the project D‐NL‐HIT carried out in the framework of INTERREG‐Program Deutschland‐Nederland, which is co‐financed by the European Union, the MWIDE NRW, the Ministerie van Economische Zaken en Klimaat and the provinces of Limburg, Gelderland, Noord‐Brabant and Overijssel. Publisher Copyright: © 2022 The Authors. Polymer International published by John Wiley & Sons Ltd on behalf of Society of Industrial Chemistry.

PY - 2022/8

Y1 - 2022/8

N2 - Polymeric dispersing agents were prepared from aliphatic polyesters consisting of δ-undecalactone (UDL) and β,δ-trimethyl-ε-caprolactones (TMCL) as biobased monomers, which were polymerized in bulk via organocatalysts. Graft copolymers were obtained by coupling of the polyesters to poly(ethylene imine) (PEI) in the bulk without using solvents. Various parameters that influence the performance of the dispersing agents in pigment-based UV-curable matrices were investigated: chemistry of the polyester (UDL or TMCL), polyester/PEI weight ratio, molecular weight of the polyesters and of PEI. The performance of the dispersing agents was modelled using machine learning in order to increase the efficiency of the dispersant design. The resulting models were presented as analytical models for the individual polyesters and the synthesis conditions for optimally performing dispersing agents were indicated as a preference for high-molecular-weight polyesters and a polyester-dependent maximum polyester/PEI weight ratio.

AB - Polymeric dispersing agents were prepared from aliphatic polyesters consisting of δ-undecalactone (UDL) and β,δ-trimethyl-ε-caprolactones (TMCL) as biobased monomers, which were polymerized in bulk via organocatalysts. Graft copolymers were obtained by coupling of the polyesters to poly(ethylene imine) (PEI) in the bulk without using solvents. Various parameters that influence the performance of the dispersing agents in pigment-based UV-curable matrices were investigated: chemistry of the polyester (UDL or TMCL), polyester/PEI weight ratio, molecular weight of the polyesters and of PEI. The performance of the dispersing agents was modelled using machine learning in order to increase the efficiency of the dispersant design. The resulting models were presented as analytical models for the individual polyesters and the synthesis conditions for optimally performing dispersing agents were indicated as a preference for high-molecular-weight polyesters and a polyester-dependent maximum polyester/PEI weight ratio.

KW - dispersant

KW - machine learning

KW - poly(ethylene imine)

KW - polyester

KW - structure–property relationships

UR - http://www.scopus.com/inward/record.url?scp=85125138707&partnerID=8YFLogxK

U2 - 10.1002/pi.6378

DO - 10.1002/pi.6378

M3 - Article

AN - SCOPUS:85125138707

SN - 0959-8103

VL - 71

SP - 966

EP - 975

JO - Polymer International

JF - Polymer International

IS - 8

ER -

A machine learning approach for the design of hyperbranched polymeric dispersing agents based on aliphatic polyesters for radiation-curable inks

Abstract

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this