Temporally Validated and Laboratory-Reconciled Soft Sensing of Xylene-Soluble Fraction in Industrial Polypropylene Manufacturing
4 affiliations
- 1Chemistry Program, Department of Natural and Exact Sciences, University of Cartagena, San Pablo Campus, Cartagena de Indias 130015, Colombia
- 2Department of Natural and Exact Science, Universidad de la Costa, Barranquilla 080002, Colombia
- 3Institute of Materials Technology (ITM), Universitat Politecnica de Valencia (UPV), Plaza Ferrandiz and Carbonell s/n, 03801 Alcoy, Spain
- 4Grupo de Investigación GIA, Fundacion Universitaria Tecnologico Comfenalco, Cr 44 D N 30A, 91, Cartagena 130015, Colombia
Abstract
The xylene-soluble fraction (XS) is a critical quality attribute in polypropylene manufacturing because it is associated with polymer architecture, catalyst stereoselectivity, comonomer incorporation, and polymerization conditions. Its conventional determination by ASTM D5492 is laboratory-based and cannot provide continuous information on the evolving quality state of an industrial reactor. This study addresses how much XS predictability originates from the previously known analytical state and how much is attributable to the contemporaneous reactor state. Of the 425 original industrial records included, one physically invalid feed condition was excluded, leaving 425 curated observations. These observations were evaluated chronologically rather than via random row-wise partitioning, and product code and downstream quality descriptors that were unavailable at prediction time were excluded from the primary formulation. The process-only model achieved a final temporal-test R2 of 0.666, whereas historical analytical/recipe information alone yielded R2 = 0.843. Integration of both information sources increased performance to R2 = 0.902, RMSE = 0.640 wt.%, and MAE = 0.306 wt.%. Expanding-window temporal validation yielded a mean R2 of 0.875 ± 0.115. The strongest independently supported domain was Family H, for which 50 future observations were predicted with R2 = 0.930, RMSE = 0.304 wt.%, and MAE = 0.188 wt.%. The results support a laboratory-reconciled soft-sensor architecture in which ASTM D5492 serves as the certification reference, while the model provides intermediate estimates between laboratory measurements.
Related
- Upcycling Secondary Cellulosic Fibres and Post-Industrial Recycled Polypropylene from Household Appliance Manufacturing into Circular Composites with Enhanced Dimensional Stability
- Physics-Guided Soft Sensing under Sparse Laboratory Measurements and Temporal Regime Shifts in Industrial Monoammonium Phosphate Production
- Laboratory-to-Industrial Translation in Plant-Derived Bioproduct Valorization: A Critical Integrative Review and Proposed Framework for Route-Level Evidence Assessment
- Using Polypropylene-Based End-of-Life Vehicle (ELV) Recyclates in Practice: Contaminant and Composition Effects on Performance
- Relationships of Multiphase Structure with Flexibility and DC Insulation Performance in Impact-Resistant Polypropylene Copolymers
BibTeX
@article{hernandezfernandez2026temporally,
title = {{Temporally Validated and Laboratory-Reconciled Soft Sensing of Xylene-Soluble Fraction in Industrial Polypropylene Manufacturing}},
author = {Joaquín Hernández-Fernández},
journal = {Polymers},
year = {2026},
month = oct,
doi = {10.3390/polym18192401},
url = {https://europepmc.org/article/PMC/PMC13667117},
note = {CC BY},
}
RIS
TY - JOUR
TI - Temporally Validated and Laboratory-Reconciled Soft Sensing of Xylene-Soluble Fraction in Industrial Polypropylene Manufacturing
AU - Joaquín Hernández-Fernández
PY - 2026
DA - 2026/10/01
JO - Polymers
DO - 10.3390/polym18192401
UR - https://europepmc.org/article/PMC/PMC13667117
AB - The xylene-soluble fraction (XS) is a critical quality attribute in polypropylene manufacturing because it is associated with polymer architecture, catalyst stereoselectivity, comonomer incorporation, and polymerization conditions. Its conventional determination by ASTM D5492 is laboratory-based and cannot provide continuous information on the evolving quality state of an industrial reactor. This study addresses how much XS predictability originates from the previously known analytical state and how much is attributable to the contemporaneous reactor state. Of the 425 original industrial records included, one physically invalid feed condition was excluded, leaving 425 curated observations. These observations were evaluated chronologically rather than via random row-wise partitioning, and product code and downstream quality descriptors that were unavailable at prediction time were excluded from the primary formulation. The process-only model achieved a final temporal-test R2 of 0.666, whereas historical analytical/recipe information alone yielded R2 = 0.843. Integration of both information sources increased performance to R2 = 0.902, RMSE = 0.640 wt.%, and MAE = 0.306 wt.%. Expanding-window temporal validation yielded a mean R2 of 0.875 ± 0.115. The strongest independently supported domain was Family H, for which 50 future observations were predicted with R2 = 0.930, RMSE = 0.304 wt.%, and MAE = 0.188 wt.%. The results support a laboratory-reconciled soft-sensor architecture in which ASTM D5492 serves as the certification reference, while the model provides intermediate estimates between laboratory measurements.
SN - 2073-4360
ER -