Araştırma Makalesi
Estimation of Tensile Strength of PLA Based Material Produced by Additive Manufacturing Using Machine Learning Algorithms
Öz
Additive manufacturing and artificial intelligence techniques, which are important components of Industry 4.0, are frequently used in many areas today. Additive manufacturing methods are divided into seven classes within themselves. The fused deposition method is one of the most preferred methods of additive manufacturing. The part is produced by the layer-by-layer combination of the filament material used on the fused deposition method (FDM) manufacturing table. In the study, tensile samples were produced by using different processing parameters in the FDM method. Tensile samples were tested according to ASTM standards, and a data set was created with the values of tensile strength. The tensile strength values of the material produced using the data set on temperature, velocity, layer properties collected during the material production process were estimated using three different machine learning models. The results showed that using machine learning algorithms, the tensile strength can be predicted with an accuracy of 98,3% by the Partial Least Squares algorithm.
Anahtar Kelimeler
Additive manufacturing Machine learning Fused deposition modelling
Kaynakça
- [1] A. Erçetin, K. Aslantaş and Ö. Özgün, “Micro-end milling of biomedical TZ54 magnesium alloy produced through powder metallurgy,” Machining Science and Technology, vol. 24, no. 6, pp. 924-947, 2020.
- [2] A. Erçetin, “Sıcak presleme yöntemiyle üretilen Nb takviyeli Mg matrisli kompozitlerin mikroyapı ve mekanik özellikleri,” Düzce Üniversitesi Bilim ve Teknoloji Dergisi, c. 9, s. 5, ss. 2116-2127, 2021.
- [3] W. Wu, J. Jiang, H. Jiang, W. Liu, G. Li, B. Wang, M. Tang and J. Zhao, “Improving bending and dynamic mechanics performance of 3D printing through ultrasonic strengthening,” Materials Letters, vol. 220, pp. 317–320, 2018.
- [4] O.A. Mohamed, S.H. Masood, J.L. Bhowmik and A.E Somers, “Investigation on the tribological behavior and wear mechanism of parts processed by fused deposition additive manufacturing process,” Journal Manufacturing Process, vol. 29, pp. 149–159, 2017.
- [5] E. Karaman ve O. Çolak, “Eriyik biriktirme yönteminde farklı üretim parametrelerinin mekanik özelliklere etkisi,” ALKÜ Fen Bilimleri Dergisi, c. 1, s. 2, ss. 90-99, 2019.
- [6] J. Zhang, P. Wang and R.X. Gao, “Deep learning-based tensile strength prediction in fused deposition modeling,” Computers in Industry, vol. 107, pp. 11-21, 2019.
- [7] H. K. Dave, N.H. Patadiya, A.R. Prajapati and S.R. Rajpurohit, “Effect of ınfill pattern and ınfill density at varying part orientation on tensile properties of fused deposition modeling-printed poly-lactic acid part,” Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, vol. 235, no. 10, pp. 1811-1827, 2021.
- [8] F.G. Aytekin, “Fotolitografi işleminde uv sertleştirme parametrelerinin deney tasarımı ile eniyilenmesi,” Yüksek Lisans tezi, Fen Bilimleri Enstitüsü, Kocaeli Üniversitesi, Kocaeli, Türkiye, 2014.
- [9] G. Zhiqiang, S. Zhihuan, X.D. Steven and H. Biao, “Data mining and analytics in the process ındustry: the role of machine learning,” IEEE Access, vol. 5, pp. 20590–20616, 2017.
- [10] N.M. Mehat, S.M. Kassim and S. Kamaruddin, “Investigation on the effects of processing parameters on shrinkage behaviour and tensile properties of injection moulded plastic gear via the taguchi method,” In Journal of Physics: Conference Series, vol. 908, no. 1, pp. 12-49, 2017.
- [11] B. Aksoy and M. Koru, “Estimation of casting mold ınterfacial heat transfer coefficient in pressure die casting process by artificial ıntelligence methods,” Arabian Journal for Science and Engineering, vol. 45, pp. 8969-8980, 2020.
- [12] M.I. Jordan and T.M. Mitchell, “Machine learning: Trends, perspectives, and prospects,” Science, vol. 349, no. 6245, pp. 255-260, 2015.
- [13] M.B. Tümer, “Üç boyutlu yazıcılar ve günümüz mimarisinde kullanımı,” Yüksek Lisans tezi, Fen Bilimleri Enstitüsü, Işık Üniversitesi, İstanbul, Türkiye, 2020.
- [14] M. Vohland, J. Besold, J. Hill and H.C. Fründ, “Comparing different multivariate calibration methods for the determination of soil organic carbon pools with visible to near ınfrared spectroscopy,” Geoderma, vol. 166, no. 1, pp. 198-205, 2011.
- [15] K. Kavaklioglu, “Robust modeling of heating and cooling loads using partial least squares towards efficient residential building design,” Journal of Building Engineering, vol. 18, pp. 469, 2018.
- [16] C. Summers and M.J. Dinneen, “Improved mixed-example data augmentation,” in 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), Waikoloa Village, Hawaii, 2019, pp. 1262-1270.
- [17] L. Breiman. “Random forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.
- [18] M.A. Pillai, A. Ghosh, J. Joy, S. Kamal, C.C. Satheesh, A.A. Balakrishnan and M.H. Supriya, “Acoustic source localization using random forest regressor,” in 2019 International Symposium on Ocean Technology (SYMPOL), 2019, pp. 191-199.
- [19] P.K. Sen, “The theil-sen estimator in genomic high dimensional measurement error models perspectives,” Calcutta Statistical Association Bulletin, vol. 63, pp. 37-50, 2011.
- [20] S.S. Hussain and P. Sprent, “Non‐parametric regression,” Journal of the Royal Statistical Society: Series A (General), vol. 146, no. 2, pp. 182-191,1983.
- [21] A. Zheng, Evaluating Machine Learning Models, Farnham, UK: O’Reilly Media, 2015, ch. 2, pp. 7-18.
- [22] N. Hooda, J. S. Chohan, R. Gupta, and R. Kumar, “Deposition angle prediction of Fused Deposition Modeling process using ensemble machine learning, ” ISA transactions, vol. 116, pp. 121-128, 2021.
- [23] R. V. Pazhamannil, P. Govindan and P. Sooraj, “Prediction of the tensile strength of polylactic acid fused deposition models using artificial neural network technique,” Materials Today: Proceedings, vol. 46, pp. 9187-9193, 2021.
- [24] M. Samykano, “Mechanical property and prediction model for FDM-3D printed polylactic acid (PLA),” Arabian Journal for Science and Engineering, vol. 46, pp. 7875–7892, 2021.
- [25] M. Goudswaard, B. Hicks and A. Nassehi, “The creation of a neural network based capability profile to enable generative design and the manufacture of functional FDM parts,” The International Journal of Advanced Manufacturing Technology, vol. 113, no. 9, pp. 2951-2968, 2021.
- [26] R. Srinivasan, T. Pridhar, L.S. Ramprasath, N.S. Charan and W. Ruban, “Prediction of tensile strength in FDM printed ABS parts using response surface methodology (RSM),” Materials Today: Proceedings, vol. 27, pp. 1827-1832, 2020.
- [27] B.N. Panda, M.R. Bahubalendruni and B.B. Biswal, “A general regression neural network approach for the evaluation of compressive strength of FDM prototypes,” Neural Computing and Applications, vol. 26, no. 5, pp. 1129-1136, 2015.
Eklemeli İmalat ile Üretilen PLA Esaslı Malzemenin Çekme Dayanımının Makine Öğrenmesi Algoritmaları Kullanarak Tahmini
Öz
Endüstri 4.0'ın önemli bileşenlerinden olan eklemeli imalat ve yapay zekâ tekniklikleri günümüzde birçok alanda sıklıkla kullanılmaktadır. Eklemeli imalat yöntemleri kendi içerisinde yedi sınıfa ayrılmaktadır. Eriyik yığma modelleme eklemeli imalat yönteminin sıklıkla tercih edilen yöntemlerinden birisidir. Eriyik yığma modelleme imalat tablası üzerinde kullanılan filament malzemenin katman katman birleşimi ile parça üretimi gerçekleştirilir. Çalışmada eriyik yığma modelleme yönteminde farklı işleme parametreleri kullanılarak çekme numuneleri üretilmiştir. Çekme numuneleri ASTM standartlarına göre çekme deneyi yapılarak, çekme dayanımına ait değerler ile veri seti oluşturulmuştur. Malzeme üretim sürecinde toplanan sıcaklık, hız, katman özelliklerine dair veri seti kullanılarak üretilen malzemenin çekme dayanımı değerleri üç farklı makine öğrenmesi modeli kullanılarak tahmin edilmiştir. Sonuçlar, makine öğrenmesi algoritmaları kullanılarak çekme dayanımını Kısmi En Küçük Kareler algoritması ile %98,3 doğrulukla tahminlediğini göstermiştir.
Anahtar Kelimeler
Kaynakça
- [1] A. Erçetin, K. Aslantaş and Ö. Özgün, “Micro-end milling of biomedical TZ54 magnesium alloy produced through powder metallurgy,” Machining Science and Technology, vol. 24, no. 6, pp. 924-947, 2020.
- [2] A. Erçetin, “Sıcak presleme yöntemiyle üretilen Nb takviyeli Mg matrisli kompozitlerin mikroyapı ve mekanik özellikleri,” Düzce Üniversitesi Bilim ve Teknoloji Dergisi, c. 9, s. 5, ss. 2116-2127, 2021.
- [3] W. Wu, J. Jiang, H. Jiang, W. Liu, G. Li, B. Wang, M. Tang and J. Zhao, “Improving bending and dynamic mechanics performance of 3D printing through ultrasonic strengthening,” Materials Letters, vol. 220, pp. 317–320, 2018.
- [4] O.A. Mohamed, S.H. Masood, J.L. Bhowmik and A.E Somers, “Investigation on the tribological behavior and wear mechanism of parts processed by fused deposition additive manufacturing process,” Journal Manufacturing Process, vol. 29, pp. 149–159, 2017.
- [5] E. Karaman ve O. Çolak, “Eriyik biriktirme yönteminde farklı üretim parametrelerinin mekanik özelliklere etkisi,” ALKÜ Fen Bilimleri Dergisi, c. 1, s. 2, ss. 90-99, 2019.
- [6] J. Zhang, P. Wang and R.X. Gao, “Deep learning-based tensile strength prediction in fused deposition modeling,” Computers in Industry, vol. 107, pp. 11-21, 2019.
- [7] H. K. Dave, N.H. Patadiya, A.R. Prajapati and S.R. Rajpurohit, “Effect of ınfill pattern and ınfill density at varying part orientation on tensile properties of fused deposition modeling-printed poly-lactic acid part,” Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, vol. 235, no. 10, pp. 1811-1827, 2021.
- [8] F.G. Aytekin, “Fotolitografi işleminde uv sertleştirme parametrelerinin deney tasarımı ile eniyilenmesi,” Yüksek Lisans tezi, Fen Bilimleri Enstitüsü, Kocaeli Üniversitesi, Kocaeli, Türkiye, 2014.
- [9] G. Zhiqiang, S. Zhihuan, X.D. Steven and H. Biao, “Data mining and analytics in the process ındustry: the role of machine learning,” IEEE Access, vol. 5, pp. 20590–20616, 2017.
- [10] N.M. Mehat, S.M. Kassim and S. Kamaruddin, “Investigation on the effects of processing parameters on shrinkage behaviour and tensile properties of injection moulded plastic gear via the taguchi method,” In Journal of Physics: Conference Series, vol. 908, no. 1, pp. 12-49, 2017.
- [11] B. Aksoy and M. Koru, “Estimation of casting mold ınterfacial heat transfer coefficient in pressure die casting process by artificial ıntelligence methods,” Arabian Journal for Science and Engineering, vol. 45, pp. 8969-8980, 2020.
- [12] M.I. Jordan and T.M. Mitchell, “Machine learning: Trends, perspectives, and prospects,” Science, vol. 349, no. 6245, pp. 255-260, 2015.
- [13] M.B. Tümer, “Üç boyutlu yazıcılar ve günümüz mimarisinde kullanımı,” Yüksek Lisans tezi, Fen Bilimleri Enstitüsü, Işık Üniversitesi, İstanbul, Türkiye, 2020.
- [14] M. Vohland, J. Besold, J. Hill and H.C. Fründ, “Comparing different multivariate calibration methods for the determination of soil organic carbon pools with visible to near ınfrared spectroscopy,” Geoderma, vol. 166, no. 1, pp. 198-205, 2011.
- [15] K. Kavaklioglu, “Robust modeling of heating and cooling loads using partial least squares towards efficient residential building design,” Journal of Building Engineering, vol. 18, pp. 469, 2018.
- [16] C. Summers and M.J. Dinneen, “Improved mixed-example data augmentation,” in 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), Waikoloa Village, Hawaii, 2019, pp. 1262-1270.
- [17] L. Breiman. “Random forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.
- [18] M.A. Pillai, A. Ghosh, J. Joy, S. Kamal, C.C. Satheesh, A.A. Balakrishnan and M.H. Supriya, “Acoustic source localization using random forest regressor,” in 2019 International Symposium on Ocean Technology (SYMPOL), 2019, pp. 191-199.
- [19] P.K. Sen, “The theil-sen estimator in genomic high dimensional measurement error models perspectives,” Calcutta Statistical Association Bulletin, vol. 63, pp. 37-50, 2011.
- [20] S.S. Hussain and P. Sprent, “Non‐parametric regression,” Journal of the Royal Statistical Society: Series A (General), vol. 146, no. 2, pp. 182-191,1983.
- [21] A. Zheng, Evaluating Machine Learning Models, Farnham, UK: O’Reilly Media, 2015, ch. 2, pp. 7-18.
- [22] N. Hooda, J. S. Chohan, R. Gupta, and R. Kumar, “Deposition angle prediction of Fused Deposition Modeling process using ensemble machine learning, ” ISA transactions, vol. 116, pp. 121-128, 2021.
- [23] R. V. Pazhamannil, P. Govindan and P. Sooraj, “Prediction of the tensile strength of polylactic acid fused deposition models using artificial neural network technique,” Materials Today: Proceedings, vol. 46, pp. 9187-9193, 2021.
- [24] M. Samykano, “Mechanical property and prediction model for FDM-3D printed polylactic acid (PLA),” Arabian Journal for Science and Engineering, vol. 46, pp. 7875–7892, 2021.
- [25] M. Goudswaard, B. Hicks and A. Nassehi, “The creation of a neural network based capability profile to enable generative design and the manufacture of functional FDM parts,” The International Journal of Advanced Manufacturing Technology, vol. 113, no. 9, pp. 2951-2968, 2021.
- [26] R. Srinivasan, T. Pridhar, L.S. Ramprasath, N.S. Charan and W. Ruban, “Prediction of tensile strength in FDM printed ABS parts using response surface methodology (RSM),” Materials Today: Proceedings, vol. 27, pp. 1827-1832, 2020.
- [27] B.N. Panda, M.R. Bahubalendruni and B.B. Biswal, “A general regression neural network approach for the evaluation of compressive strength of FDM prototypes,” Neural Computing and Applications, vol. 26, no. 5, pp. 1129-1136, 2015.
Toplam 27 adet kaynakça vardır.
Ayrıntılar
| Birincil Dil | Türkçe |
|---|---|
| Konular | Mühendislik |
| Bölüm | Makaleler |
| Yazarlar | |
| Yayımlanma Tarihi | 31 Aralık 2021 |
| Yayımlandığı Sayı | Yıl 2021 Cilt: 9 Sayı: 6 - ICAIAME 2021 |
