NATURE-INSPIRED DESIGN IDEA GENERATION WITH GENERATIVE ADVERSARIAL NETWORKS

Öz

Generating new, creative, and innovative ideas in the early stages of the design process is crucial for developing better and original products. Human designers may become too attached to specific design ideas, preventing them from generating new concepts and achieving ideal designs. To come up with original design ideas, a designer needs to have a creative mind, as well as knowledge, experience, and talent. Verbal, written, and visual sources of inspiration can also be valuable for generating ideas and concepts. This study presents a visual integration model that uses a data-supported Artificial Intelligence (AI) method to generate creative design ideas. The proposed model is based on a generative adversarial network (GAN) that combines target object and biological object images to produce new creative product images inspired by nature. The model was successfully applied to an aircraft design problem and the resulting sketches inspired designers to generate new and creative design ideas and variants in a case study. It was seen that this approach improved the quality of the ideas produced and simplified the idea and concept generation process.

Anahtar Kelimeler

• Generative Adversarial Network
• Biomimicry
• Idea Generation
• Deep Learning
• data-driven design

Kaynakça

1. 1. Börklü, H. R., Yüksel, N., Çavdar, K. and Sezer, H. K. “A practical application for machine design education”, Journal of Advanced Mechanical Design, Systems, and Manufacturing, Vol. 12, Issue 2, 2018.
2. 2. Yüksel N. and Börklü, H. R., “Yapay Zekâ Destekli Kavramsal Tasarım: Tekerlekli Sandalye Tasarım Seçenekleri Değerlendirmede Bulanık Mantık Kullanımı,” Gazi Journal of Engineering Sciences, Vol. 7, Pages 309-316, 2021.
3. 3. Huang, Y., Li, J. and Fu, J., "Review on Application of Artificial Intelligence in Civil Engineering", Computer Modeling in Engineering \& Sciences, Vol. 121, Issue 3, Pages 845-875, 2019. [Online]. Available: http://www.techscience.com/CMES/v121n3/38073
4. 4. Han, J., Shi, F., Chen, L. and Childs, P. R. N. "The Combinator – a computer-based tool for creative idea generation based on a simulation approach", Design Science, Vol. 4, Pages e11, 2018.
5. 5. Vasconcelos L. A. and Crilly, N., "Inspiration and fixation: Questions, methods, findings, and challenges," Design Studies, Vol. 42, Pages 1-32, 2016/01/01/ 2016.
6. 6. Jansson, D. G. and Smith, S. M., "Design fixation", Design Studies, Vol. 12, Issue. 1, Pages 3-11, 1991.
7. 7. Goldschmidt, G. and Smolkov, M., "Variances in the impact of visual stimuli on design problem solving performance", Design Studies, Vol. 27, Issue 5, Pages 549-569, 2006.
8. 8. Goldschmidt, G. and Sever, A. L., "Inspiring design ideas with texts", Design Studies, Vol. 32, Issue 2, Pages 139-155, 2011.

9. 9. Jiang, S. Luo, J., Ruiz-Pava, G., Hu, J. and Magee, C. L., "Deriving Design Feature Vectors for Patent Images Using Convolutional Neural Networks", Journal of Mechanical Design, Vol. 143, Issue 6, 2021.
10. 10. Liu, Q., Wang, K., Li, Y. and Liu, Y., "Data-Driven Concept Network for Inspiring Designers’ Idea Generation", Journal of Computing and Information Science in Engineering, Vol. 20, Issue 3, 2020.
11. 11. Boden, M. A., “The Creative Mind: Myths and Mechanisms”, London, UK: Routledge, 2004.
12. 12. Ward, T. B., and Kolomyts, Y., "Cognition and Creativity," in The Cambridge Handbook of Creativity, J. C. Kaufman and R. J. Sternberg Eds., Cambridge Handbooks in Psychology. Cambridge: Cambridge University Press, Pages 93-112, 2010.
13. 13. Jin, X., and Dong, H., "New desıgn heurıstıcs ın the dıgıtal era," Proceedings of the Design Society: DESIGN Conference, Vol. 1, Pages 607-616, 2020.
14. 14. Yilmaz, S., Daly, S. R. Seifert, C. M. and Gonzalez, R., "Evidence-based design heuristics for idea generation", Design Studies, Vol. 46, Pages 95-124, 2016.
15. 15. Shi, F., Chen, L., Han, J. and hilds, P. C., "A Data-Driven Text Mining and Semantic Network Analysis for Design Information Retrieval", Journal of Mechanical Design, Vol. 139, Issue 11, 2017.
16. 16. Bell, S. and Bala, K., "Learning visual similarity for product design with convolutional neural networks", ACM Transactions on Graphics, Vol. 34, Pages 98:1-98:10, 2015.
17. 17. Yu, S., Dong, H., Wang, P., Wu, C., and Guo, Y., "Generative Creativity: Adversarial Learning for Bionic Design", Cham, 2019: Springer International Publishing, in Artificial Neural Networks and Machine Learning – ICANN 2019: Image Processing, Pages 525-536, 2019.
18. 18. Chen, L. et al., "An artificial intelligence based data-driven approach for design ideation", Journal of Visual Communication and Image Representation, Vol. 61, Pages. 10-22, 2019.
19. 19. Salehi, H. and Burgueño, R., "Emerging artificial intelligence methods in structural engineering," Engineering Structures, Vol. 171, Pages 170-189, 2018.
20. 20. Alpaydın, E., Dietterich, T., “Ed. Introduction to Machine Learning”, 3 ed. London: MIT Press, 2014.
21. 21. Rebala, G., Ravi, A., and Churiwala, S., “An Introduction to Machine Learning”, 1 ed. Cham: Springer, 2019.
22. 22. Houssein, E. H., Emam, M. M., Ali, A. A. and Suganthan, P. N. "Deep and machine learning techniques for medical imaging-based breast cancer: A comprehensive review", Expert Systems with Applications, Vol. 167, Page 114161, 2021.
23. 23. Gal, Y. "Uncertainty in Deep Learning", PhD thesis, Department of Engineering, University of Cambridge, Cambridge, 2016.
24. 24. Oh, S., Jung, Y. Kim, S., Lee, I., and Kang, N., "Deep generative design: Integration of topology optimization and generative models", Journal of Mechanical Design, Vol. 141, Issue 11, 2019.
25. 25. Singh, R. D., Mittal, A. and Bhatia, R. K., "3D convolutional neural network for object recognition: a review", Multimedia Tools and Applications, Vol. 78, Issue 12, Pages 15951-15995, 2019.
26. 26. Yi, X. Walia, E. and Babyn, P. "Generative adversarial network in medical imaging: A review", Medical Image Analysis, Vol. 58, Page 101552, 2019.
27. 27. Jin, L., Tan, F. and Jiang, S., "Generative Adversarial Network Technologies and Applications in Computer Vision", Computational Intelligence and Neuroscience, Vol. 2020, Page 1459107, 2020.
28. 28. Rahman, R., "Using Generative Adversarial Networks for Content Generation in Games", MSc thesis, Departman of Computer Games Technology, Abertay University, Dundee, 2020.
29. 29. Ray, S. "A Quick Review of Machine Learning Algorithms," in 2019 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon), 14-16 Feb. 2019. Pages 35-39,
30. 30. Brynjolfsson, E. and Mitchell, T., "What can machine learning do? Workforce implications", Science, Vol. 358, Issue 6370, Pages 1530, 2017.
31. 31. Mayda, M. and Börklü, H. “Yeni bir kavramsal tasarım işlem modeli”, TÜBAV Bilim Dergisi, Vol. 1, Issue 1, Pages 13-25, 2008.
32. 32. Börklü, H. “Computer-aided conceptual design based on design catalogues”, Politeknik Dergisi, Vol. 4, Issue 3, Pages. 77-78, 2001.
33. 33. Koestler, A., “The Act of Creation”, Macmillan, Oxford, England, 1964.
34. 34. Yi, X., Walia, E., and Babyn, P., "Generative adversarial network in medical imaging: A review", Medical Image Analysis, Vol. 58, Page 101552, 2019.
35. 35. Jin, L., Tan F. and Jiang, S., "Generative Adversarial Network Technologies and Applications in Computer Vision", Computational Intelligence and Neuroscience, Vol. 2020, Pages 1459107, 2020.
36. 36. Rahman, R., "Using Generative Adversarial Networks for Content Generation in Games," Thesis, School of Design and Informatics, Abertay University, 2020.
37. 37. Oh, S., Jung, Y., Kim, S. Lee, I. and Kang, N. "Deep generative design: Integration of topology optimization and generative models," Journal of Mechanical Design, Vol. 141, Issue 11, 2019.
38. 38. Goodfellow, I., Pouget-Abadie, J., Mirza, M. Xu, B., Warde-Farley, D., Ozair, S., Courville, A. and Bengio, Y., “Generative Adversarial Nets,” Advances in Neural Information Processing Systems 27, Montréal, Canada, Dec. 8–13, Pages 2672–2680, 2014.
39. 39. Creswell, A., White, T., Dumoulin, V., Arulkumaran, K., Sengupta, B. And Bharath, A. A. “Generative Adversarial Networks: An Overview,” IEEE Signal Processing Magazine, Vol. 35, Issue 1, Pages 53-65, 2018.
40. 40. Fang, W., Zhang, F., Sheng, V. S., and Ding, Y. “A method for improving CNN-based image recognition using DCGAN,” Computers, Materials and Continua, Vol. 57, Issue 1, Pages 167-178, 2018.
41. 41. Yüksel, N., Börklü, H. R., Sezer, H. K. and Canyurt, O. E. (2023). Review of artificial intelligence applications in engineering design perspective. Engineering Applications of Artificial Intelligence, Vol. 118, Pages 105697, 2023.
42. 42. Daly, S. R., Seifert, C. M., Yilmaz, S. and Gonzalez, R., "Comparing Ideation Techniques for Beginning Designers." ASME. Journal of Mechanical Design, Vol. 138, Issue 10, Pages 101108, 2016.