Abstract
.3 boyutlu (3D) baskı Endüstri 4.0’ın önde gelen ve hızla gelişen teknolojilerinden biridir. Sanal ortamda 3 boyutlu olarak modellenen cisimler 3 boyutlu yazıcılar kullanılarak farklı teknik ve malzemelerle hızlı şekilde prototiplenebilmektedir. 3D baskıda üretilen ürünün amaca uygun, mümkün olduğunca düşük maliyetli ve ideal şekilde dayanıklı olması beklenmektedir. Üretilecek çıktının nitelikleri eldeki baskı teknolojisinin kısıtlarına bağlı olarak şekillenir. Ürünün niteliğini etkileyen diğer önemli bir unsur da baskı için kullanılacak olan malzemedir. Farklı teknik özellikler, dayanım ve kullanım alanları olan ABS ve PLA malzemelerden uygun olanın seçilmesi amaca uygun çıktıların elde edilmesi noktasında önem taşımaktadır. Bu çalışmada 3D yazıcılara ait çeşitli ayar parametreleri ve üretilecek ürünün niteliklerini ifade eden toplam 12 öznitelikten oluşan bir veri seti üzerinde basım için kullanılacak malzemenin tahminlenmesine yönelik makine öğrenmesi temelli sınıflandırmalar gerçekleştirilmiştir. Destek Vektör Makinesi (DVM), K-En yakın Komşu (KNN), Karar Ağacı (KA), Rastgele Orman (RO) ve Lojistik Regresyon (LR) olmak üzere beş ayrı yöntemle ve 5 kat çapraz doğrulama ile gerçekleştirilen sınıflandırma işlemlerinde en yüksek doğruluk %100 olarak LR algoritması ile elde edilmiştir.
References
- 1. Günay, M., Gündüz, S., Yılmaz, H., Yaşar, N., Kaçar, R., “PLA esaslı numunelerde çekme dayanımı için 3D baskı işlem parametrelerinin optimizasyonu”, Politeknik Dergisi., Cilt 23, Sayı 1, Sayfa 73-79, 2020.
- 2. Bourell, D. L., Leu, M. C., Rosen, D. W., “Roadmap for additive manufacturing: identifying the future of freeform processing”, Univ. Tex. Austin Austin TX, Vol. 32, Issue 1, Pages 11-15, 2009.
- 3. Özsoy, K., Aksoy, B., Yücel, M., “Design and Manufacture Of Continuous Automatic 3D Printing Device With Conveyor System By Image Processing Technology”, Erzincan Üniversitesi Fen Bilimleri Enstitüsü Dergisi, Cilt 13, Sayı 2, Sayfa. 392-403, 2020.
- 4. Şahin, K., Turan, B.O., “Üç Boyutlu Yazıcı Teknolojilerinin Karşılaştırmalı Analizi”, Strat. ve Sos. Araştırmalar Dergisi, Cilt 2, Sayı 2, Sayfa 97-116, 2018.
- 5. Tymrak, B., Kreiger, M., Pearce, J. M. , “Mechanical properties of components fabricated with open-source 3-D printers under realistic environmental conditions”, Mater. Des., Vol. 58, Issue 1, Pages 242-246, 2014.
- 6. Aksoy, B., Selbaş, R., “Estimation of Wind Turbine Energy Production Value by Using Machine Learning Algorithms and Development of Implementation Program”, Energy Sources Part Recovery Util. Environ. Eff., Vol. 43, Issue 6, Pages 692-704, 2021.
- 7. Delli, U., Chang, S., “Automated Process Monitoring in 3D Printing Using Supervised Machine Learning”, Procedia Manuf., Vol. 26, Issue 1, Pages 865-870, 2018. 8. Li, Z., Zhang, Z., Shi, J., Wu, D., “Prediction of surface roughness in extrusion-based additive manufacturing with machine learning”, Robot. Comput.-Integr. Manuf., Vol. 57, Issue 1, Pages 488-495, 2019.
- 9. Wu, D., Wei, Y., Terpenny, J., “Surface roughness prediction in additive manufacturing using machine learning”, International Manufacturing Science and Engineering Conference, Vol. 3, Pages 51371, 2018.
- 10. Tripathi A., Singla, R., “Surface Roughness Prediction of 3D Printed Surface Using Artificial Neural Networks”, Advances in Interdisciplinary Engineering Conference, Pages 09-120., Singapore, 2021.
- 11. Magar, R.,Ghule, L., Doshi, R., Khalid, A., Seshadri, S., Farimani, A. B., “ManufacturingNet: A Machine Learning Toolbox for Engineers”, Workshop on machine learning for engineering modeling, simulation and design, 2020.
- 12. Wu, M., Phoha, V. V., Moon, Y. B., Belman, A. K., “Detecting Malicious Defects in 3D Printing Process Using Machine Learning and Image Classification”, ASME 2016 International Mechanical Engineering Congress and Exposition, Vol. 14, Arizona, 2016.
- 13. Farhan Khan M., “Real-time defect detection in 3D printing using machine learning”, Second Int. Conf. Recent Adv. Mater. Manuf., Vol. 42, Pages 521-528, 2021.
- 14. Vapnik, V., Golowich, S. E., Smola, A., “Support vector method for function approximation, regression estimation, and signal processing”, Adv. Neural Inf. Process. Syst., Pages 281-287, 1997.
- 15. Shen L., “Evolving support vector machines using fruit fly optimization for medical data classification”, Knowl.-Based Syst., Vol. 96, Pages 61-75, 2016.
- 16. Fix E., Hodges Jr J. L., “Discriminatory analysis-nonparametric discrimination: Small sample performance”, California Univ Berkeley, 1952.
- 17. Altman, N.S., “An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression”, Am. Stat., Vol. 46, Issue 3, Pages 175-185, 1992.
- 18. Ho, T. K., “Random decision forests”, Proceedings of 3rd international conference on document analysis and recognition, Vol. 1, Pages 278-282, 1995.
- 19. Breiman, L., “Random forests”, Mach. Learn., Vol. 45, Issue 1, Pages 5-32, 2001.
- 20. Yang Y., Loog M., “A benchmark and comparison of active learning for logistic regression”, Pattern Recognit., Vol. 83, Pages 401-415, 2018.
Abstract
3D printing is one of the leading and rapidly developing technologies of Industry 4.0. Objects modeled in 3D in the virtual environment can be quickly prototyped with different techniques and materials using 3D printers. The output produced in 3D printing is expected to be fit for purpose, cost-effective as possible, and ideally durable. The qualities of the output to be produced are shaped by the limitations of the available printing technology. Another important factor affecting the quality of the output product is the material to be used for printing. Selecting the appropriate ABS and PLA materials, which have different technical properties, strength and usage areas, is important in terms of obtaining appropriate outputs. In this study, machine learning-based classifications for the estimation of the material to be used for printing were carried out on a data set consisting of a total of 12 attributes expressing the various setting parameters of 3D printers and the qualities of the product to be produced. In classification processes performed with five different methods namely Support Vector Machine (DVM), K-Nearest Neighbor (KNN), Decision Tree (KA), Random Forest (RO) and Logistic Regression (LR), and 5 fold cross-validation, the highest accuracy was obtained as 100% with the LR algorithm.
References
- 1. Günay, M., Gündüz, S., Yılmaz, H., Yaşar, N., Kaçar, R., “PLA esaslı numunelerde çekme dayanımı için 3D baskı işlem parametrelerinin optimizasyonu”, Politeknik Dergisi., Cilt 23, Sayı 1, Sayfa 73-79, 2020.
- 2. Bourell, D. L., Leu, M. C., Rosen, D. W., “Roadmap for additive manufacturing: identifying the future of freeform processing”, Univ. Tex. Austin Austin TX, Vol. 32, Issue 1, Pages 11-15, 2009.
- 3. Özsoy, K., Aksoy, B., Yücel, M., “Design and Manufacture Of Continuous Automatic 3D Printing Device With Conveyor System By Image Processing Technology”, Erzincan Üniversitesi Fen Bilimleri Enstitüsü Dergisi, Cilt 13, Sayı 2, Sayfa. 392-403, 2020.
- 4. Şahin, K., Turan, B.O., “Üç Boyutlu Yazıcı Teknolojilerinin Karşılaştırmalı Analizi”, Strat. ve Sos. Araştırmalar Dergisi, Cilt 2, Sayı 2, Sayfa 97-116, 2018.
- 5. Tymrak, B., Kreiger, M., Pearce, J. M. , “Mechanical properties of components fabricated with open-source 3-D printers under realistic environmental conditions”, Mater. Des., Vol. 58, Issue 1, Pages 242-246, 2014.
- 6. Aksoy, B., Selbaş, R., “Estimation of Wind Turbine Energy Production Value by Using Machine Learning Algorithms and Development of Implementation Program”, Energy Sources Part Recovery Util. Environ. Eff., Vol. 43, Issue 6, Pages 692-704, 2021.
- 7. Delli, U., Chang, S., “Automated Process Monitoring in 3D Printing Using Supervised Machine Learning”, Procedia Manuf., Vol. 26, Issue 1, Pages 865-870, 2018. 8. Li, Z., Zhang, Z., Shi, J., Wu, D., “Prediction of surface roughness in extrusion-based additive manufacturing with machine learning”, Robot. Comput.-Integr. Manuf., Vol. 57, Issue 1, Pages 488-495, 2019.
- 9. Wu, D., Wei, Y., Terpenny, J., “Surface roughness prediction in additive manufacturing using machine learning”, International Manufacturing Science and Engineering Conference, Vol. 3, Pages 51371, 2018.
- 10. Tripathi A., Singla, R., “Surface Roughness Prediction of 3D Printed Surface Using Artificial Neural Networks”, Advances in Interdisciplinary Engineering Conference, Pages 09-120., Singapore, 2021.
- 11. Magar, R.,Ghule, L., Doshi, R., Khalid, A., Seshadri, S., Farimani, A. B., “ManufacturingNet: A Machine Learning Toolbox for Engineers”, Workshop on machine learning for engineering modeling, simulation and design, 2020.
- 12. Wu, M., Phoha, V. V., Moon, Y. B., Belman, A. K., “Detecting Malicious Defects in 3D Printing Process Using Machine Learning and Image Classification”, ASME 2016 International Mechanical Engineering Congress and Exposition, Vol. 14, Arizona, 2016.
- 13. Farhan Khan M., “Real-time defect detection in 3D printing using machine learning”, Second Int. Conf. Recent Adv. Mater. Manuf., Vol. 42, Pages 521-528, 2021.
- 14. Vapnik, V., Golowich, S. E., Smola, A., “Support vector method for function approximation, regression estimation, and signal processing”, Adv. Neural Inf. Process. Syst., Pages 281-287, 1997.
- 15. Shen L., “Evolving support vector machines using fruit fly optimization for medical data classification”, Knowl.-Based Syst., Vol. 96, Pages 61-75, 2016.
- 16. Fix E., Hodges Jr J. L., “Discriminatory analysis-nonparametric discrimination: Small sample performance”, California Univ Berkeley, 1952.
- 17. Altman, N.S., “An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression”, Am. Stat., Vol. 46, Issue 3, Pages 175-185, 1992.
- 18. Ho, T. K., “Random decision forests”, Proceedings of 3rd international conference on document analysis and recognition, Vol. 1, Pages 278-282, 1995.
- 19. Breiman, L., “Random forests”, Mach. Learn., Vol. 45, Issue 1, Pages 5-32, 2001.
- 20. Yang Y., Loog M., “A benchmark and comparison of active learning for logistic regression”, Pattern Recognit., Vol. 83, Pages 401-415, 2018.
Details
| Primary Language | Turkish |
|---|---|
| Subjects | Software Engineering (Other) |
| Journal Section | Research Article |
| Authors | |
| Publication Date | December 30, 2021 |
| Submission Date | November 21, 2021 |
| Published in Issue | Year 2021 Volume: 5 Issue: 3 |
Cite
Cited By
CNC TEZGAHLARININ DİJİTAL İKİZ MODELİ İLE KOMUT TAMAMLANMA SÜRELERİNİN TAHMİN EDİLMESİ
International Journal of 3D Printing Technologies and Digital Industry
https://doi.org/10.46519/ij3dptdi.1215353
COVID-19 SALGININDA 3B YAZICILARLA GELİŞTİRİLEN ÜRÜNLERİN İNCELENMESİ
International Journal of 3D Printing Technologies and Digital Industry
https://doi.org/10.46519/ij3dptdi.957098
International Journal of 3D Printing Technologies and Digital Industry is lisenced under Creative Commons Atıf-GayriTicari 4.0 Uluslararası Lisansı