Single and multi-objective real-time optimisation of an industrial injection moulding process via a Bayesian adaptive design of experiment approach

Abstract Minimising cycle time without inducing quality defects is a major challenge in injection moulding (IM). Design of Experiment methods (DoE) have been widely studied for optimisation of injection moulding, however existing methods have limitations, including the need for a large number of exp...

Full description

Saved in:
Bibliographic Details
Main Authors: Mandana Kariminejad, David Tormey, Caitríona Ryan, Christopher O’Hara, Albert Weinert, Marion McAfee
Format: Article
Language:English
Published: Nature Portfolio 2024-11-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-80405-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850216090255228928
author Mandana Kariminejad
David Tormey
Caitríona Ryan
Christopher O’Hara
Albert Weinert
Marion McAfee
author_facet Mandana Kariminejad
David Tormey
Caitríona Ryan
Christopher O’Hara
Albert Weinert
Marion McAfee
author_sort Mandana Kariminejad
collection DOAJ
description Abstract Minimising cycle time without inducing quality defects is a major challenge in injection moulding (IM). Design of Experiment methods (DoE) have been widely studied for optimisation of injection moulding, however existing methods have limitations, including the need for a large number of experiments within a pre-determined search space. Bayesian adaptive design of experiment (ADoE) is an iterative process where the results of the previous experiments are used to make an informed selection for the next design. In this study, an experimental ADoE approach based on Bayesian optimisation was developed for injection moulding using process and sensor data to optimise the quality and cycle time in real-time. A novel approach for the real-time characterisation of post-production shrinkage was introduced, utilising in-mould sensor data on temperature differential during part cooling. This characterisation approach was verified by post-production metrology results. A single and multi-objective optimisation of the cycle time and temperature differential ( $$\Delta T$$ ) in an injection moulded component is proposed. The multi-objective optimisation techniques, composite desirability function and Nondominated Sorting Genetic Algorithm (NSGA-II) using the Response Surface Methodology (RSM) model, are compared with the real-time novel ADoE approach. ADoE achieved almost a 50 $$\%$$ reduction in the number of experiments required for the single optimisation of $$\Delta T$$ , and an almost 30 $$\%$$ decrease for the optimisation of $$\Delta T$$ and cycle time together compared to composite desirability function and NSGA-II. The optimal settings identified by ADoE for multiobjective optimisation were similar to the selected Pareto optimal solution found by NSGA-II.
format Article
id doaj-art-b0b8d0d39ef848fe97aac707e8a9d91a
institution OA Journals
issn 2045-2322
language English
publishDate 2024-11-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-b0b8d0d39ef848fe97aac707e8a9d91a2025-08-20T02:08:24ZengNature PortfolioScientific Reports2045-23222024-11-0114111910.1038/s41598-024-80405-2Single and multi-objective real-time optimisation of an industrial injection moulding process via a Bayesian adaptive design of experiment approachMandana Kariminejad0David Tormey1Caitríona Ryan2Christopher O’Hara3Albert Weinert4Marion McAfee5Centre for Precision Engineering, Materials and Manufacturing Research (PEM Centre), Atlantic Technological University SligoCentre for Precision Engineering, Materials and Manufacturing Research (PEM Centre), Atlantic Technological University SligoI-Form, Research Centre for Advanced Manufacturing, John Hume Institute, University College DublinCentre for Precision Engineering, Materials and Manufacturing Research (PEM Centre), Atlantic Technological University SligoCentre for Precision Engineering, Materials and Manufacturing Research (PEM Centre), Atlantic Technological University SligoCentre for Precision Engineering, Materials and Manufacturing Research (PEM Centre), Atlantic Technological University SligoAbstract Minimising cycle time without inducing quality defects is a major challenge in injection moulding (IM). Design of Experiment methods (DoE) have been widely studied for optimisation of injection moulding, however existing methods have limitations, including the need for a large number of experiments within a pre-determined search space. Bayesian adaptive design of experiment (ADoE) is an iterative process where the results of the previous experiments are used to make an informed selection for the next design. In this study, an experimental ADoE approach based on Bayesian optimisation was developed for injection moulding using process and sensor data to optimise the quality and cycle time in real-time. A novel approach for the real-time characterisation of post-production shrinkage was introduced, utilising in-mould sensor data on temperature differential during part cooling. This characterisation approach was verified by post-production metrology results. A single and multi-objective optimisation of the cycle time and temperature differential ( $$\Delta T$$ ) in an injection moulded component is proposed. The multi-objective optimisation techniques, composite desirability function and Nondominated Sorting Genetic Algorithm (NSGA-II) using the Response Surface Methodology (RSM) model, are compared with the real-time novel ADoE approach. ADoE achieved almost a 50 $$\%$$ reduction in the number of experiments required for the single optimisation of $$\Delta T$$ , and an almost 30 $$\%$$ decrease for the optimisation of $$\Delta T$$ and cycle time together compared to composite desirability function and NSGA-II. The optimal settings identified by ADoE for multiobjective optimisation were similar to the selected Pareto optimal solution found by NSGA-II.https://doi.org/10.1038/s41598-024-80405-2Injection mouldingGaussian processBayesian adaptive design of experimentsMulti-objective optimisationNondominated sorting genetic algorithm
spellingShingle Mandana Kariminejad
David Tormey
Caitríona Ryan
Christopher O’Hara
Albert Weinert
Marion McAfee
Single and multi-objective real-time optimisation of an industrial injection moulding process via a Bayesian adaptive design of experiment approach
Scientific Reports
Injection moulding
Gaussian process
Bayesian adaptive design of experiments
Multi-objective optimisation
Nondominated sorting genetic algorithm
title Single and multi-objective real-time optimisation of an industrial injection moulding process via a Bayesian adaptive design of experiment approach
title_full Single and multi-objective real-time optimisation of an industrial injection moulding process via a Bayesian adaptive design of experiment approach
title_fullStr Single and multi-objective real-time optimisation of an industrial injection moulding process via a Bayesian adaptive design of experiment approach
title_full_unstemmed Single and multi-objective real-time optimisation of an industrial injection moulding process via a Bayesian adaptive design of experiment approach
title_short Single and multi-objective real-time optimisation of an industrial injection moulding process via a Bayesian adaptive design of experiment approach
title_sort single and multi objective real time optimisation of an industrial injection moulding process via a bayesian adaptive design of experiment approach
topic Injection moulding
Gaussian process
Bayesian adaptive design of experiments
Multi-objective optimisation
Nondominated sorting genetic algorithm
url https://doi.org/10.1038/s41598-024-80405-2
work_keys_str_mv AT mandanakariminejad singleandmultiobjectiverealtimeoptimisationofanindustrialinjectionmouldingprocessviaabayesianadaptivedesignofexperimentapproach
AT davidtormey singleandmultiobjectiverealtimeoptimisationofanindustrialinjectionmouldingprocessviaabayesianadaptivedesignofexperimentapproach
AT caitrionaryan singleandmultiobjectiverealtimeoptimisationofanindustrialinjectionmouldingprocessviaabayesianadaptivedesignofexperimentapproach
AT christopherohara singleandmultiobjectiverealtimeoptimisationofanindustrialinjectionmouldingprocessviaabayesianadaptivedesignofexperimentapproach
AT albertweinert singleandmultiobjectiverealtimeoptimisationofanindustrialinjectionmouldingprocessviaabayesianadaptivedesignofexperimentapproach
AT marionmcafee singleandmultiobjectiverealtimeoptimisationofanindustrialinjectionmouldingprocessviaabayesianadaptivedesignofexperimentapproach