Development of robust machine learning models for predicting flexural strengths of fiber-reinforced polymeric composites
Fiber-reinforced composites are widely used in engineering applications due to their excellent physical and chemical properties. However, evaluating their flexural properties using conventional experimental techniques is time-consuming, costly, and limited by material and fabrication variations. Thi...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Hybrid Advances |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2773207X25000090 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589951210881024 |
|---|---|
| author | Abdulhammed K. Hamzat Umar T. Salman Md Shafinur Murad Ozkan Altay Ersin Bahceci Eylem Asmatulu Mete Bakir Ramazan Asmatulu |
| author_facet | Abdulhammed K. Hamzat Umar T. Salman Md Shafinur Murad Ozkan Altay Ersin Bahceci Eylem Asmatulu Mete Bakir Ramazan Asmatulu |
| author_sort | Abdulhammed K. Hamzat |
| collection | DOAJ |
| description | Fiber-reinforced composites are widely used in engineering applications due to their excellent physical and chemical properties. However, evaluating their flexural properties using conventional experimental techniques is time-consuming, costly, and limited by material and fabrication variations. This study investigates the potential of machine learning (ML) techniques to predict the flexural properties of fiber-reinforced composites accurately and efficiently. Five ML algorithms—Light gradient boosting regressor (LGBR), Extra tree regressor (ETR), Decision tree regressor (DTR), Histogram-based gradient boosting regressor (HGBR), and Adaptive boosting regressor (ABR)—were employed to predict the flexural strengths using both experimental data generated in-house and data collected from open literature. Including heterogeneous data from both sources enhances the robustness and generalizability of the developed models. The results demonstrate that the extra trees regressor (ETR) achieves excellent accuracy when applied to the heterogeneous dataset, with a coefficient of determination (R2) value of 0.94, MAE of 31.97, and RMSE of 47.64, outperforming the other three models. Furthermore, the in-house experimental data yields even higher prediction accuracy, with the best-performing model achieving an impressive R2 value of 0.99, MAE of 9.53, and RMSE of 13.15. The high prediction accuracy achieved, despite the slight variability in data obtained from the literature, highlights the potential use of ML techniques to streamline the development process and reduce the reliance on extensive experimental testing. These robust models take into consideration important composite production parameters to provide design engineers and research scientists with versatile and efficient tools for the prediction of flexural properties of fiber-reinforced composites and related materials for various industries, including aerospace, defense, energy, biomedical and automotive. |
| format | Article |
| id | doaj-art-f6167e724545443e8a87021e2e04eefb |
| institution | Kabale University |
| issn | 2773-207X |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Hybrid Advances |
| spelling | doaj-art-f6167e724545443e8a87021e2e04eefb2025-01-24T04:46:06ZengElsevierHybrid Advances2773-207X2025-03-018100385Development of robust machine learning models for predicting flexural strengths of fiber-reinforced polymeric compositesAbdulhammed K. Hamzat0Umar T. Salman1Md Shafinur Murad2Ozkan Altay3Ersin Bahceci4Eylem Asmatulu5Mete Bakir6Ramazan Asmatulu7Department of Mechanical Engineering, Wichita State University, 1845 Fairmount, Wichita, KS, 67260, USAFU Foundation School of Engineering and Applied Science, Columbia University, New York City, NY, USADepartment of Mechanical Engineering, Wichita State University, 1845 Fairmount, Wichita, KS, 67260, USATurkish Aerospace Industries, Inc. Fethiye Mah., Havacilik Bulvari, Kahramankazan, Ankara, TurkeyTurkish Aerospace Industries, Inc. Fethiye Mah., Havacilik Bulvari, Kahramankazan, Ankara, Turkey; Department of Metallurgical and Materials Engineering, Iskenderun Technical University, İskenderun, Hatay, 31200, TurkeyDepartment of Mechanical Engineering, Wichita State University, 1845 Fairmount, Wichita, KS, 67260, USATurkish Aerospace Industries, Inc. Fethiye Mah., Havacilik Bulvari, Kahramankazan, Ankara, Turkey; Department of Mechanical Engineering, Ankara Yildirim Beyazit University, Ankara, TurkeyDepartment of Mechanical Engineering, Wichita State University, 1845 Fairmount, Wichita, KS, 67260, USA; Corresponding author.Fiber-reinforced composites are widely used in engineering applications due to their excellent physical and chemical properties. However, evaluating their flexural properties using conventional experimental techniques is time-consuming, costly, and limited by material and fabrication variations. This study investigates the potential of machine learning (ML) techniques to predict the flexural properties of fiber-reinforced composites accurately and efficiently. Five ML algorithms—Light gradient boosting regressor (LGBR), Extra tree regressor (ETR), Decision tree regressor (DTR), Histogram-based gradient boosting regressor (HGBR), and Adaptive boosting regressor (ABR)—were employed to predict the flexural strengths using both experimental data generated in-house and data collected from open literature. Including heterogeneous data from both sources enhances the robustness and generalizability of the developed models. The results demonstrate that the extra trees regressor (ETR) achieves excellent accuracy when applied to the heterogeneous dataset, with a coefficient of determination (R2) value of 0.94, MAE of 31.97, and RMSE of 47.64, outperforming the other three models. Furthermore, the in-house experimental data yields even higher prediction accuracy, with the best-performing model achieving an impressive R2 value of 0.99, MAE of 9.53, and RMSE of 13.15. The high prediction accuracy achieved, despite the slight variability in data obtained from the literature, highlights the potential use of ML techniques to streamline the development process and reduce the reliance on extensive experimental testing. These robust models take into consideration important composite production parameters to provide design engineers and research scientists with versatile and efficient tools for the prediction of flexural properties of fiber-reinforced composites and related materials for various industries, including aerospace, defense, energy, biomedical and automotive.http://www.sciencedirect.com/science/article/pii/S2773207X25000090Machine learningFiber-reinforced polymer compositesFlexural strengthEnsembles methods |
| spellingShingle | Abdulhammed K. Hamzat Umar T. Salman Md Shafinur Murad Ozkan Altay Ersin Bahceci Eylem Asmatulu Mete Bakir Ramazan Asmatulu Development of robust machine learning models for predicting flexural strengths of fiber-reinforced polymeric composites Hybrid Advances Machine learning Fiber-reinforced polymer composites Flexural strength Ensembles methods |
| title | Development of robust machine learning models for predicting flexural strengths of fiber-reinforced polymeric composites |
| title_full | Development of robust machine learning models for predicting flexural strengths of fiber-reinforced polymeric composites |
| title_fullStr | Development of robust machine learning models for predicting flexural strengths of fiber-reinforced polymeric composites |
| title_full_unstemmed | Development of robust machine learning models for predicting flexural strengths of fiber-reinforced polymeric composites |
| title_short | Development of robust machine learning models for predicting flexural strengths of fiber-reinforced polymeric composites |
| title_sort | development of robust machine learning models for predicting flexural strengths of fiber reinforced polymeric composites |
| topic | Machine learning Fiber-reinforced polymer composites Flexural strength Ensembles methods |
| url | http://www.sciencedirect.com/science/article/pii/S2773207X25000090 |
| work_keys_str_mv | AT abdulhammedkhamzat developmentofrobustmachinelearningmodelsforpredictingflexuralstrengthsoffiberreinforcedpolymericcomposites AT umartsalman developmentofrobustmachinelearningmodelsforpredictingflexuralstrengthsoffiberreinforcedpolymericcomposites AT mdshafinurmurad developmentofrobustmachinelearningmodelsforpredictingflexuralstrengthsoffiberreinforcedpolymericcomposites AT ozkanaltay developmentofrobustmachinelearningmodelsforpredictingflexuralstrengthsoffiberreinforcedpolymericcomposites AT ersinbahceci developmentofrobustmachinelearningmodelsforpredictingflexuralstrengthsoffiberreinforcedpolymericcomposites AT eylemasmatulu developmentofrobustmachinelearningmodelsforpredictingflexuralstrengthsoffiberreinforcedpolymericcomposites AT metebakir developmentofrobustmachinelearningmodelsforpredictingflexuralstrengthsoffiberreinforcedpolymericcomposites AT ramazanasmatulu developmentofrobustmachinelearningmodelsforpredictingflexuralstrengthsoffiberreinforcedpolymericcomposites |