Machine Learning for Identifying Damage and Predicting Properties in 3D-Printed PLA/Lygeum Spartum Biocomposites
This paper offers an experimental approach that integrates acoustic emission (AE) monitoring with machine learning (ML) to identify damage mechanisms and predict the mechanical properties of 3D-printed biocomposites. Specimens were fabricated using a bio-filament composed of a PLA matrix reinforced...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Fibers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-6439/13/4/38 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850183468712984576 |
|---|---|
| author | Khalil Benabderazag Moussa Guebailia Zouheyr Belouadah Lotfi Toubal Salah Eddine Tachi |
| author_facet | Khalil Benabderazag Moussa Guebailia Zouheyr Belouadah Lotfi Toubal Salah Eddine Tachi |
| author_sort | Khalil Benabderazag |
| collection | DOAJ |
| description | This paper offers an experimental approach that integrates acoustic emission (AE) monitoring with machine learning (ML) to identify damage mechanisms and predict the mechanical properties of 3D-printed biocomposites. Specimens were fabricated using a bio-filament composed of a PLA matrix reinforced with 10% wt. of Lygeum spartum fibers and were subjected to tensile and flexural tests. The processed dataset, comprising six normalized features (cumulative rise, duration, count, frequency, energy, and amplitude) was used to train four ML models: Random Forest Regression (RFR), Support Vector Regression (SVR), Artificial Neural Networks (ANN), and Decision Trees (DT) implemented in Python using libraries such as scikit-learn, pandas, and numpy. The prediction models were developed using an 80/20 train–test split and further validated by 5-fold cross-validation, with performance evaluated by R-squared (<i>R</i><sup>2</sup>) and Mean Squared Error (<i>MSE</i>) metrics. Our results demonstrate robust prediction capabilities, with the RFR model achieving the highest accuracy (<i>R</i><sup>2</sup> > 0.98 and <i>MSE</i> as low as 0.013 for tensile stress prediction). Additionally, unsupervised clustering using K-means was applied to group AE signals into distinct clusters corresponding to different damage modes. This comprehensive methodology not only enhances our understanding of damage evolution in composite materials but also establishes a data-driven framework for non-destructive evaluation and structural health monitoring. |
| format | Article |
| id | doaj-art-c92f4fe646a4425abffeafc1e8a2eb92 |
| institution | OA Journals |
| issn | 2079-6439 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Fibers |
| spelling | doaj-art-c92f4fe646a4425abffeafc1e8a2eb922025-08-20T02:17:20ZengMDPI AGFibers2079-64392025-03-011343810.3390/fib13040038Machine Learning for Identifying Damage and Predicting Properties in 3D-Printed PLA/Lygeum Spartum BiocompositesKhalil Benabderazag0Moussa Guebailia1Zouheyr Belouadah2Lotfi Toubal3Salah Eddine Tachi4Applied Mechanic and Energy Systems Laboratory (LMASE), Kasdi Merbah University of Ouargla, BP 511, Ouargla 30000, AlgeriaApplied Mechanic and Energy Systems Laboratory (LMASE), Kasdi Merbah University of Ouargla, BP 511, Ouargla 30000, AlgeriaLaboratoire des Sciences et Techniques de l’Environnement, Ecole Nationale Polytechnique, 10 Avenue des Frères Oudek, BP 182, El-Harrach, Alger 16200, AlgeriaLaboratory of Mechanics and Eco-Materials, Mechanical Engineering Department, Université du Quebec à Trois-Rivières, 3351 Boul. des Forges, Trois Rivières, QC G9A 5H7, CanadaLaboratoire de Recherche des Sciences de l’Eau, Ecole Nationale Polytechnique, 10 Avenue des Frères Oudek, BP 182, El-Harrach, Alger 16200, AlgeriaThis paper offers an experimental approach that integrates acoustic emission (AE) monitoring with machine learning (ML) to identify damage mechanisms and predict the mechanical properties of 3D-printed biocomposites. Specimens were fabricated using a bio-filament composed of a PLA matrix reinforced with 10% wt. of Lygeum spartum fibers and were subjected to tensile and flexural tests. The processed dataset, comprising six normalized features (cumulative rise, duration, count, frequency, energy, and amplitude) was used to train four ML models: Random Forest Regression (RFR), Support Vector Regression (SVR), Artificial Neural Networks (ANN), and Decision Trees (DT) implemented in Python using libraries such as scikit-learn, pandas, and numpy. The prediction models were developed using an 80/20 train–test split and further validated by 5-fold cross-validation, with performance evaluated by R-squared (<i>R</i><sup>2</sup>) and Mean Squared Error (<i>MSE</i>) metrics. Our results demonstrate robust prediction capabilities, with the RFR model achieving the highest accuracy (<i>R</i><sup>2</sup> > 0.98 and <i>MSE</i> as low as 0.013 for tensile stress prediction). Additionally, unsupervised clustering using K-means was applied to group AE signals into distinct clusters corresponding to different damage modes. This comprehensive methodology not only enhances our understanding of damage evolution in composite materials but also establishes a data-driven framework for non-destructive evaluation and structural health monitoring.https://www.mdpi.com/2079-6439/13/4/383D printingbiocompositematerial behavioracoustic emissionmachine learning prediction |
| spellingShingle | Khalil Benabderazag Moussa Guebailia Zouheyr Belouadah Lotfi Toubal Salah Eddine Tachi Machine Learning for Identifying Damage and Predicting Properties in 3D-Printed PLA/Lygeum Spartum Biocomposites Fibers 3D printing biocomposite material behavior acoustic emission machine learning prediction |
| title | Machine Learning for Identifying Damage and Predicting Properties in 3D-Printed PLA/Lygeum Spartum Biocomposites |
| title_full | Machine Learning for Identifying Damage and Predicting Properties in 3D-Printed PLA/Lygeum Spartum Biocomposites |
| title_fullStr | Machine Learning for Identifying Damage and Predicting Properties in 3D-Printed PLA/Lygeum Spartum Biocomposites |
| title_full_unstemmed | Machine Learning for Identifying Damage and Predicting Properties in 3D-Printed PLA/Lygeum Spartum Biocomposites |
| title_short | Machine Learning for Identifying Damage and Predicting Properties in 3D-Printed PLA/Lygeum Spartum Biocomposites |
| title_sort | machine learning for identifying damage and predicting properties in 3d printed pla lygeum spartum biocomposites |
| topic | 3D printing biocomposite material behavior acoustic emission machine learning prediction |
| url | https://www.mdpi.com/2079-6439/13/4/38 |
| work_keys_str_mv | AT khalilbenabderazag machinelearningforidentifyingdamageandpredictingpropertiesin3dprintedplalygeumspartumbiocomposites AT moussaguebailia machinelearningforidentifyingdamageandpredictingpropertiesin3dprintedplalygeumspartumbiocomposites AT zouheyrbelouadah machinelearningforidentifyingdamageandpredictingpropertiesin3dprintedplalygeumspartumbiocomposites AT lotfitoubal machinelearningforidentifyingdamageandpredictingpropertiesin3dprintedplalygeumspartumbiocomposites AT salaheddinetachi machinelearningforidentifyingdamageandpredictingpropertiesin3dprintedplalygeumspartumbiocomposites |