Reduction of Material Usage in 3D Printable Structures Using Topology Optimization Accelerated with U-Net Convolutional Neural Network

Authors

  • J. Rasulzade Department of Computer Science and Information Sciences, ADA University, 61 Ahmadbey Aghaoglu str., Baku, 1008, Azerbaijan
  • Y. Maksum Department of Mechanical Engineering, Satbayev University, 22 Satbaev str., Almaty, 050013, Kazakhstan; Department of Chemical Engineering, University of Birmingham, Birmingham, B15 2TT, UK
  • M. Nogaibayeva Department of Mechanical Engineering, Satbayev University, 22 Satbaev str., Almaty, 050013, Kazakhstan
  • S. Rustamov Department of Computer Science and Information Sciences, ADA University, 61 Ahmadbey Aghaoglu str., Baku, 1008, Azerbaijan
  • B. Akhmetov Department of Mechanical Engineering, Satbayev University, 22 Satbaev str., Almaty, 050013, Kazakhstan; Department of Mechanical and Aerospace Engineering, Nanyang Technological University, 50 Nanyang Ave., 639798, Singapore

DOI:

https://doi.org/10.18321/ectj1471

Keywords:

Material reduction, 3D printing, Topology optimization, Convolutional neural network

Abstract

Today’s 3D printers allow the creation of very advanced structures from various materials, starting from simple plastics up to metal alloys. Since the printing time and amount of material used to create structures are considered very important in terms of cost and energy consumption, it is better to optimize structures for that particular application taking into account all the conditions. In the current work, U-Net convolutional neural network-based topology optimization method (TO) that allows to reduce the material usage and eventually reduces the cost of 3D printing is introduced. The results showed that the accuracy of the method is highly reliable and can be used for designing various 3D printable structures and it applies to any type of materials since properties of materials can be included in TO.

References

(1). M. Shams, Z. Mansurov, C. Daulbayev, B. Bakbolat, Eurasian Chem.-Technol. J. 23 (2021) 257–266. Crossref

(2). J.N. Levesque, A Shah, S Ekhtiari, J.R. Yan, et al., EFORT Open Reviews 5 (2020) 430–441. Crossref

(3). O. Sigmund, K. Maute, Struct. Multidis. Optim. 48 (2013) 1031–1055. Crossref

(4). J. Martínez-Frutos, D. Herrero-Pérez, Comput. Methods Appl. Mech. Eng. 311 (2016) 393–414. Crossref

(5). T. Borrvall, J. Petersson, Comput. Methods Appl. Mech. Eng. 190 (2001) 6201–6229. Crossref

(6). A. Mahdavi, R. Balaji, M. Frecker, E.M. Mockensturm, Struct. Multidisc. Optim. 32 (2006) 121–132. Crossref

(7). K. Vemaganti, W.E. Lawrence, Comput. Methods Appl. Mech. Eng. 194 (2005) 3637–3667. Crossref

(8). S. Schmidt, V. Schulz, Comput. Visial Sci. 14 (2011) 249–256. Crossref

(9). K. Suresh, Struct. Multidisc. Optim. 42 (2010) 665–679. Crossref

(10). T. Zegard, G.H. Paulino, Struct. Multidisc. Optim. 48 (2013) 473–485. Crossref

(11). K. Paraskevoudis, P. Karayannis, E.P. Koumoulos, Processes 8 (2020) 1464. Crossref

(12). N.S. Johnson, P.S. Vulimiri, A.C. To, X. Zhang, et al., Addit. Manuf. 36 (2020) 101641. Crossref

(13). K. Guo, Z. Yang, C.-H. Yu, M.J. Buehler, Mater. Horiz. 4 (2021). Crossref

(14). I. Sosnovik, I. Oseledets, Russ. J. Numer. Anal. Math. Model. 54 (2019) 215–223. Crossref

(15). D. Wang, C. Xiang, Y. Pan, A. Chen, et al., Eng. Optim. 54 (2022) 973–988. Crossref

(16). Z. Nie, T. Lin, H. Jiang, L.B. Kara, J. Mech. Des. 143 (2021) 031715. Crossref

(17). M.P. Bendsøe, Struct. Optim. 1 (1989) 193–202. Crossref

(18). G.I.N. Rozvany, Struct. Multidisc. Optim. 37 (2009) 217–237. Crossref

(19). T.P. Ribeiro, L.F.A. Bernardo, J.M.A. Andrade, Appl. Sci. 11 (2021) 2112. Crossref

(20). D.J. Munk, G.A. Vio, G.P. Steven, Struct. Multidisc. Optim. 52 (2015) 613–631. Crossref

(21). J.D. Deaton, R.V. Grandhi, Struct. Multidisc. Optim. 49 (2014) 1–38. Crossref

(22). O. Sigmund, Struct. Multidisc. Optim. 21 (2001) 120–127. Crossref

(23). K. Svanberg, Int. J. Numer. Methods. Eng. 24 (1987) 359–373. Crossref

(24). C. Lundgaard, J. Alexandersen, M. Zhou, C. Schousboe, et al., Struct. Multidisc. Optim. 58 (2018) 969–95. Crossref

(25). T. Dbouk, Appl. Therm. Eng. 112 (2017) 841–854. Crossref

(26). E. Wadbro, M. Berggren, SIAM Review 51 (2009). Crossref

(27). A. Neofytou, F. Yu, L. Zhang, H.A. Kim. Level Set Topology Optimization for Fluid-Structure Interactions. AIAA 2021-1686. Session: Shape and Topology Optimization I, 2021. Crossref

(28). T. Gao, P. Xu, W. Zhang, Comput. Struct. 173 (2016) 150–160. Crossref

(29). F.J. Ramírez-Gil, E.C.N. Silva, W. Montealegre-Rubio, Comput. Methods Appl. Mech. Eng. 302 (2016) 44–69. Crossref

(30). F.J. Ramírez-Gil, C.M. Pérez-Madrid, E.C.N. Silva, W. Montealegre-Rubio, Sustain. Comput. Informatics Syst. 30 (2021) 100481. Crossref

(31). D. Jiang, R. Hoglund, D.E. Smith, Fibers 7 (2019). Crossref

(32). W. Hunter, et al., (2017), Topy - topology optimization with python, Crossref

Downloads

Published

2022-12-12

How to Cite

Rasulzade, J., Maksum, Y., Nogaibayeva, M., Rustamov, S., & Akhmetov, B. (2022). Reduction of Material Usage in 3D Printable Structures Using Topology Optimization Accelerated with U-Net Convolutional Neural Network. Eurasian Chemico-Technological Journal, 24(4), 277‒286. https://doi.org/10.18321/ectj1471

Issue

Section

Articles