Optimization of Rectangular Section Belleville Spring with Artificial Neural Network

Öz

Machine learning has a crucial role in significantly reducing the time and costs devoted to analysis in product design. Optimization work with machine learning provides excellent advantages in terms of time and cost compared to finite element analysis. In this study, a machine learning model was trained for Belleville springs and aimed to use the trained model in the size optimization of Belleville springs. To show the applicability of single and multi-purpose optimization methods, the optimization of various Belleville springs with desired spring stiffness is discussed, and Pareto solutions are presented and examined. Finite element analyzes were carried out with the obtained design parameters, and artificial neural network and finite element results were compared. It has been seen that the optimization result can be reached within 4.5 seconds with the artificial neural network, and the accuracy of the obtained results (96.16%) is similar to the neural network success rate (97.67%).

Anahtar Kelimeler

• Belleville Spring
• Finite Element Analysis
• Machine Learning
• Artificial Neural Network
• Optimization
• Genetic Algorithm

Dikdörtgen Kesitli Disk Yayların Yapay Sinir Ağı İle Optimizasyonu

Öz

Ürün tasarımında analizlere ayrılan zamanın ve maliyetlerin önemli ölçüde azaltılmasında makine öğrenmesi kilit rol oynamaktadır. Makine öğrenmesi ile gerçekleştirilen optimizasyon çalışması, sonlu elemanlar analizine kıyasla zaman ve maliyet açısından büyük üstünlükler sağlamaktadır. Bu çalışmada, disk yaylar için bir makine öğrenmesi modeli eğitilmiş, eğitilen modelin disk yayların boyut optimizasyonunda kullanılması amaçlanmıştır. Tek ve çok amaçlı optimizasyon yöntemlerinin uygulanabilirliğini göstermek için istenilen yay rijitliğine sahip çeşitli disk yayların optimizasyonu ele alınmış ve Pareto çözümleri sunularak çözümler incelenmiştir. Elde edilen tasarım parametreleri ile sonlu elemanlar analizleri gerçekleştirilmiş ve yapay sinir ağı ile sonlu elemanlar sonuçları karşılaştırılmıştır. Yapay sinir ağı kullanımı ile optimizasyon sonucuna 4,5 saniye içerisinde ulaşılabildiği ve elde edilen sonuçların doğruluklarının (%96,16) sinir ağı başarı oranı (%97,67) ile benzer olduğu görülmüştür.

Anahtar Kelimeler

• Disk Yay
• Sonlu Elemanlar Analizi
• Makine Öğrenmesi
• Yapay Sinir Ağı
• Optimizasyon
• Genetik Algoritma

Kaynakça

1. N. Kaya and F. Öztürk, “Dikdörtgen Kesitli Disk Yayların Optimum Kesit Tasarımı,” Makina Tasarım ve İmalat Dergisi, vol. 4, no. 3, pp. 140–145, 2002.
2. R. Phellan, B. Hachem, J. Clin, J. M. Mac-Thiong, and L. Duong, “Real-time biomechanics using the finite element method and machine learning: Review and perspective,” Med Phys, vol. 48, no. 1, pp. 7–18, Jan. 2021, doi: 10.1002/MP.14602.
3. “Abaqus/CAE Student Edition 2020.”
4. M. Müller, X. Longl, M. Betsch, D. Böhmländer, and W. Utschick, “Real-Time Crash Severity Estimation with Machine Learning and 2D Mass-Spring-Damper Model,” IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC, vol. 2018-November, pp. 2036–2043, Dec. 2018.
5. Z. S. Ma, Q. Ding, and Y. J. Zhai, “Hybrid Modeling of Nonlinear-Jointed Structures via Finite-Element Model Reduction and Deep Learning Techniques,” Journal of Vibration Engineering and Technologies, vol. 9, no. 4, pp. 575–585, Jun. 2021.
6. Z. Qi, N. Zhang, Y. Liu, and W. Chen, “Prediction of mechanical properties of carbon fiber based on cross-scale FEM and machine learning,” Compos Struct, vol. 212, pp. 199–206, Mar. 2019.
7. C. N. N. Karina, P. Chun, and K. Okubo, “Tensile Strength Prediction of Corroded Steel Plates by Using Machine Learning Approach,” Steel and Composite Structures, vol. 24, no. 5, pp. 635–641, Aug. 2017.
8. L. Liang, M. Liu, C. Martin, and W. Sun, “A deep learning approach to estimate stress distribution: a fast and accurate surrogate of finite-element analysis,” J R Soc Interface, vol. 15, no. 138, Jan. 2018.

9. F. C. Babalık and K. Çavdar, Makine Elemanları ve Konstrüksiyon Örnekleri, 8th ed. Bursa: Dora Yayınları, 2015.
10. D. L. Venkatesh and H. Zhou, “Designing Belleville Spring Washers,” Int. J. Eng. Res. Technol, vol. 7, no. 12, pp. 168–174, 2018.
11. D. Bhope, S. Tahilyani, and K. Singh, “Effects of Slots on Deflection and Stresses in Belleville Spring,” The International Journal of Engineering And Science (IJES), pp. 2–3, 2013.
12. X. Liu, C. E. Athanasiou, N. P. Padture, B. W. Sheldon, and H. Gao, “A machine learning approach to fracture mechanics problems,” Acta Mater, vol. 190, pp. 105–112, May 2020.
13. S. Fahle, C. Prinz, and B. Kuhlenkötter, “Systematic review on machine learning (ML) methods for manufacturing processes – Identifying artificial intelligence (AI) methods for field application,” Procedia CIRP, vol. 93, pp. 413–418, Jan. 2020.
14. S. Müller, A., & Guido, Introduction to Machine Learning with Python. O’Reilly Media, Inc., 2016.
15. F. Chollet, Deep Learning with Python. Manning Publisher Co., 2018.
16. N. Gunantara, “A review of multi-objective optimization: Methods and its applications,” Cogent Eng, vol. 5, no. 1, pp. 1–16, Jan. 2018.
17. E. S. Andradbttir, K. J. Healy, D. H. Withers, B. L. Nelson, Y. Carson, and A. Maria, “Simulation optimization,” Proceedings of the 29th conference on Winter simulation - WSC ’97, pp. 118–126, 1997.
18. I. Ahmadianfar, O. Bozorg-Haddad, and X. Chu, “Gradient-based optimizer: A new metaheuristic optimization algorithm,” Inf Sci (N Y), vol. 540, pp. 131–159, Nov. 2020.
19. M. Marseguerra, E. Zio, and S. Martorell, “Basics of genetic algorithms optimization for RAMS applications,” Reliab Eng Syst Saf, vol. 91, no. 9, pp. 977–991, Sep. 2006.
20. A. R. Yıldız, N. Öztürk, N. Kaya, and F. Öztürk, “Hybrid multi-objective shape design optimization using Taguchi’s method and genetic algorithm,” Structural and Multidisciplinary Optimization , vol. 25, no. 4, pp. 251–260, 2003.
21. A. Konak, D. W. Coit, and A. E. Smith, “Multi-objective optimization using genetic algorithms: A tutorial,” Reliab Eng Syst Saf, vol. 91, pp. 992–1007, 2006.
22. F. Cappello and A. Mancuso, “A genetic algorithm for combined topology and shape optimisations,” Computer-Aided Design, vol. 35, no. 8, pp. 761–769, 2003.
23. R. T. Marler and J. S. Arora, “Survey of multi-objective optimization methods for engineering,” Structural and Multidisciplinary Optimization, vol. 26, no. 6, pp. 369–395, Mar. 2004.
24. K. Deb, A. Pratap, S. Agarwal, and T. Meyarivan, “A fast and elitist multiobjective genetic algorithm: NSGA-II,” IEEE Transactions on Evolutionary Computation, vol. 6, no. 2, pp. 182–197, Apr. 2002.
25. D. P. Kingma and J. L. Ba, “Adam: A Method for Stochastic Optimization,” 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings, Dec. 2014.
26. J. Blank and K. Deb, “Pymoo: Multi-Objective Optimization in Python,” IEEE Access, vol. 8, pp. 89497–89509, 2020.