Design and Optimization of an EV Battery Enclosure Using Machine Learning

Yıl 2025, Cilt: 23 Sayı: 1, 1 - 7, 27.05.2025

Burak Aydoğdu , Fatih Karpat , Necmettin Kaya

https://doi.org/10.56193/matim.1540273

Öz

In this study, structural optimization of an enclosure under bending and torsional constraints was carried out. Machine learning (ML) approach was used to calculate the objective and constraint functions in the optimization problem. The ML model was trained and validated with data obtained from finite element analyses. The optimization model was then solved by the differential evolution algorithm. Five thicknesses, which are the design parameters in the enclosure, were optimized for minimum mass, and according to the results, the enclosure’s mass decreased by 18.29%.

Anahtar Kelimeler

Battery Enclosure, Design Optimization, Machine Learning, Differential Evolution Algorithm

Destekleyen Kurum

Scientific and Technological Research Council of Turkey (TÜBİTAK)

Proje Numarası

22AG001

Teşekkür

This study was funded by the Scientific and Technological Research Council of Turkey (TÜBİTAK) 1004 Project Grant No: 22AG001

MAKİNE ÖĞRENMESİ KULLANILARAK BİR ELEKTRİKLİ ARAÇ BATARYA TAŞIYICISININ TASARIMI VE OPTİMİZASYONU

Öz

Bu çalışmada, eğilme ve burulma kısıtlamaları altında bir batarya muhafazasının yapısal optimizasyonu gerçekleştirilmiştir. Optimizasyon problemindeki amaç ve kısıt fonksiyonlarını hesaplamak için makine öğrenmesi yaklaşımı kullanılmıştır. Sonlu eleman analizlerinden elde edilen veriler ile makine öğrenmesi modeli eğitilmiş ve doğrulanmıştır. Optimizasyon modeli daha sonra diferansiyel evrim optimizasyon algoritması ile çözülmüştür. Batarya taşıyıcısındaki tasarım parametresi olan beş kalınlık minimum kütle için optimize edilmiş ve elde edilen sonuçlara göre taşıyıcı kütlesi %18,29 azalmıştır.

Anahtar Kelimeler

Batarya Taşıyıcısı, Tasarım Optimizasyonu, Makine Öğrenmesi, Diferensiyel Gelişim Algoritması

Proje Numarası

22AG001

Kaynakça

• 1. J. Long, W. Huang, W. Zhang, and others, ‘Lightweight investigation of extended-range electric vehicle based on collision failure using numerical simulation’, Shock and Vibration, vol. 2015, 2015.
• 2. G. Ruan, C. Yu, X. Hu, and J. Hua, ‘Simulation and optimization of a new energy vehicle power battery pack structure’, Journal of Theoretical and Applied Mechanics, vol. 59, no. 4, 2021.
• 3. G. Li, X. Fu, and Y. Yang, ‘Anti-vibration safety performance research of battery pack based on finite element method in electric vehicle’, in 2017 36th Chinese Control Conference (CCC), 2017, pp. 10281–10285.
• 4. J. Wang and X. Zhao, ‘Modal Analysis of Battery Box Based on ANSYS’, World Journal of Engineering and Technology, vol. 4, no. 2, pp. 290–295, 2016.
• 5. N. Yang, R. Fang, H. Li, and H. Xie, ‘Dynamic and static analysis of the battery box structure of an electric vehicle’, in IOP Conference Series: Materials Science and Engineering, 2019, p. 33082.
• 6. J. Li, X. Cao, and L. Guo, ‘Finite Element Analysis of Power Battery Box Chassis of Electric Bus’, in Journal of Physics: Conference Series, 2020, p. 12235.
• 7. Y. Pan, Y. Xiong, L. Wu, K. Diao, and W. Guo, ‘Lightweight design of an automotive battery-pack enclosure via advanced high-strength steels and size optimization’, International Journal of Automotive Technology, vol. 22, pp. 1279–1290, 2021.
• 8. L. Shui, F. Chen, A. Garg, X. Peng, N. Bao, and J. Zhang, ‘Design optimization of battery pack enclosure for electric vehicle’, Structural and Multidisciplinary Optimization, vol. 58, pp. 331–347, 2018.
• 9. Y. Xiong, Y. Pan, L. Wu, and B. Liu, ‘Effective weight-reduction-and crashworthiness-analysis of a vehicle’s battery-pack system via orthogonal experimental design and response surface methodology’, Eng Fail Anal, vol. 128, p. 105635, 2021.
• 10. C. Lin, F. Gao, W. Wang, and X. Chen, ‘Multi-objective optimization design for a battery pack of electric vehicle with surrogate models’, Journal of Vibroengineering, vol. 18, no. 4, pp. 2343–2358, 2016.
• 11. E. Alpaydin, Introduction to machine learning. MIT press, 2020.
• 12. Blank, J., & Deb, K. (2020). Pymoo: Multi-objective optimization in python. Ieee Access, 8, 89497–89509.