A review of physics-informed and data-driven approaches for manufacturing process optimization in polymer matrix composites

<p>Machine learning approaches that integrate physical laws with data-driven models are transforming process optimization and quality assurance in polymer matrix composite manufacturing. This review synthesizes recent developments in neural metamodels for injection molding, spatio-temporal dig...

Full description

Saved in:
Bibliographic Details
Main Author: Ivan P. Malashin (22113739) (author)
Other Authors: Dmitry Martysyuk (22113742) (author), Vladimir Nelyub (22113745) (author), Aleksei Borodulin (22113748) (author), Andrei Gantimurov (22113751) (author), Vadim Tynchenko (22113754) (author)
Published: 2025
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1852017338814038016
author Ivan P. Malashin (22113739)
author2 Dmitry Martysyuk (22113742)
Vladimir Nelyub (22113745)
Aleksei Borodulin (22113748)
Andrei Gantimurov (22113751)
Vadim Tynchenko (22113754)
author2_role author
author
author
author
author
author_facet Ivan P. Malashin (22113739)
Dmitry Martysyuk (22113742)
Vladimir Nelyub (22113745)
Aleksei Borodulin (22113748)
Andrei Gantimurov (22113751)
Vadim Tynchenko (22113754)
author_role author
dc.creator.none.fl_str_mv Ivan P. Malashin (22113739)
Dmitry Martysyuk (22113742)
Vladimir Nelyub (22113745)
Aleksei Borodulin (22113748)
Andrei Gantimurov (22113751)
Vadim Tynchenko (22113754)
dc.date.none.fl_str_mv 2025-08-23T19:20:08Z
dc.identifier.none.fl_str_mv 10.6084/m9.figshare.29974102.v1
dc.relation.none.fl_str_mv https://figshare.com/articles/dataset/A_review_of_physics-informed_and_data-driven_approaches_for_manufacturing_process_optimization_in_polymer_matrix_composites/29974102
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Medicine
Space Science
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
Polymer matrix composites
pressure molding
vacuum infusion
physics-informed machine learning
dc.title.none.fl_str_mv A review of physics-informed and data-driven approaches for manufacturing process optimization in polymer matrix composites
dc.type.none.fl_str_mv Dataset
info:eu-repo/semantics/publishedVersion
dataset
description <p>Machine learning approaches that integrate physical laws with data-driven models are transforming process optimization and quality assurance in polymer matrix composite manufacturing. This review synthesizes recent developments in neural metamodels for injection molding, spatio-temporal digital twins for resin infusion, and symbolic-regression surrogates for vacuum networks. Article identifies remaining challenges—such as extension to semicrystalline systems, uncertainty quantification under real-world noise, and deployment on industrial platforms—and outline strategies for addressing them. Building on these insights, a unified physics-informed surrogate concept is proposed that leverages temporal encoders, recurrent propagation, and multi-output decoders with embedded conservation constraints. This model is designed for rapid prediction of part quality metrics, cure state, flow front progression, and temperature fields, and supports gradient-based inversion for closed-loop control in advanced composite processing.</p>
eu_rights_str_mv openAccess
id Manara_7ecbcb2c8b0efacdcb99a84d442b7d09
identifier_str_mv 10.6084/m9.figshare.29974102.v1
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/29974102
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling A review of physics-informed and data-driven approaches for manufacturing process optimization in polymer matrix compositesIvan P. Malashin (22113739)Dmitry Martysyuk (22113742)Vladimir Nelyub (22113745)Aleksei Borodulin (22113748)Andrei Gantimurov (22113751)Vadim Tynchenko (22113754)MedicineSpace ScienceBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedPolymer matrix compositespressure moldingvacuum infusionphysics-informed machine learning<p>Machine learning approaches that integrate physical laws with data-driven models are transforming process optimization and quality assurance in polymer matrix composite manufacturing. This review synthesizes recent developments in neural metamodels for injection molding, spatio-temporal digital twins for resin infusion, and symbolic-regression surrogates for vacuum networks. Article identifies remaining challenges—such as extension to semicrystalline systems, uncertainty quantification under real-world noise, and deployment on industrial platforms—and outline strategies for addressing them. Building on these insights, a unified physics-informed surrogate concept is proposed that leverages temporal encoders, recurrent propagation, and multi-output decoders with embedded conservation constraints. This model is designed for rapid prediction of part quality metrics, cure state, flow front progression, and temperature fields, and supports gradient-based inversion for closed-loop control in advanced composite processing.</p>2025-08-23T19:20:08ZDatasetinfo:eu-repo/semantics/publishedVersiondataset10.6084/m9.figshare.29974102.v1https://figshare.com/articles/dataset/A_review_of_physics-informed_and_data-driven_approaches_for_manufacturing_process_optimization_in_polymer_matrix_composites/29974102CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/299741022025-08-23T19:20:08Z
spellingShingle A review of physics-informed and data-driven approaches for manufacturing process optimization in polymer matrix composites
Ivan P. Malashin (22113739)
Medicine
Space Science
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
Polymer matrix composites
pressure molding
vacuum infusion
physics-informed machine learning
status_str publishedVersion
title A review of physics-informed and data-driven approaches for manufacturing process optimization in polymer matrix composites
title_full A review of physics-informed and data-driven approaches for manufacturing process optimization in polymer matrix composites
title_fullStr A review of physics-informed and data-driven approaches for manufacturing process optimization in polymer matrix composites
title_full_unstemmed A review of physics-informed and data-driven approaches for manufacturing process optimization in polymer matrix composites
title_short A review of physics-informed and data-driven approaches for manufacturing process optimization in polymer matrix composites
title_sort A review of physics-informed and data-driven approaches for manufacturing process optimization in polymer matrix composites
topic Medicine
Space Science
Biological Sciences not elsewhere classified
Information Systems not elsewhere classified
Polymer matrix composites
pressure molding
vacuum infusion
physics-informed machine learning