A multi-fidelity latent modelling framework for predicting wall thickness distributions in stretch blow moulded PET bottles

Abstract The production of a bottle through Stretch Blow Moulding depends on several process parameters; both in temperature settings and in blowing process parameters. For a given preform and bottle, the final thickness distributions can vary greatly. Such variations impact the mechanical performance of bottles and ultimately plastic waste. From this study, the relationship between the process parameters and the thickness distribution was investigated. Appropriate dimensionality reduction techniques were applied to efficiently represent both the process parameters and the thickness profiles, forming the inputs and outputs of a regression model. This framework was further enhanced through the incorporation of multiple data sources (virtual and experimental), leading to improved predictive modelling via multi-fidelity regression. Visualisation of the preprocessing steps aided interpretability and provided physical insight into how the process parameters influence the thickness distribution. This research presents a unified workflow, termed PROPEL (PROcess–Property Exploration via Latent modelling), to accurately predict process-property relationships, with potential applications that could advance the production efficiency of the Stretch Blow Moulding process.

Authors

Institutions

Publication Details

Journal
The International Journal of Advanced Manufacturing Technology
Published
2026-11-17
DOI
https://doi.org/10.1007/s00170-026-19430-6
Primary Topic
Injection Molding Process and Properties
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

A multi-fidelity latent modelling framework for predicting wall thickness distributions in stretch blow moulded PET bottles

Declan Nolan, Gary Menary, Liam; id_orcid 0009-0007-0562-6757 McGovern, Shiyong Yan
1 links
The International Journal of Advanced Manufacturing Technology
Injection Molding Process and Properties
article

A multi-fidelity latent modelling framework for predicting wall thickness distributions in stretch blow moulded PET bottles

Declan Nolan, Gary Menary, Liam; id_orcid 0009-0007-0562-6757 McGovern, Shiyong Yan
article en

Abstract

Abstract The production of a bottle through Stretch Blow Moulding depends on several process parameters; both in temperature settings and in blowing process parameters. For a given preform and bottle, the final thickness distributions can vary greatly. Such variations impact the mechanical performance of bottles and ultimately plastic waste. From this study, the relationship between the process parameters and the thickness distribution was investigated. Appropriate dimensionality reduction techniques were applied to efficiently represent both the process parameters and the thickness profiles, forming the inputs and outputs of a regression model. This framework was further enhanced through the incorporation of multiple data sources (virtual and experimental), leading to improved predictive modelling via multi-fidelity regression. Visualisation of the preprocessing steps aided interpretability and provided physical insight into how the process parameters influence the thickness distribution. This research presents a unified workflow, termed PROPEL (PROcess–Property Exploration via Latent modelling), to accurately predict process-property relationships, with potential applications that could advance the production efficiency of the Stretch Blow Moulding process.

The International Journal of Advanced Manufacturing Technology
Queen's University Belfast (GB)
Injection Molding Process and Properties
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon