Exploring Various Sequential Learning Methods for Deformation History Modeling
26th International Conference on Engineering Applications of Neural Networks, EANN 2025, Limassol, Kıbrıs (Gkry), 26 - 29 Haziran 2025, cilt.2581 CCIS, ss.168-180, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Cilt numarası: 2581 CCIS
- Doi Numarası: 10.1007/978-3-031-96196-0_13
- Basıldığı Şehir: Limassol
- Basıldığı Ülke: Kıbrıs (Gkry)
- Sayfa Sayıları: ss.168-180
- Anahtar Kelimeler: Sequential Learning, Recurrent Neural Networks, Localization in Sheet Metal, Surrogate Modelling
- Boğaziçi Üniversitesi Adresli: Evet
Özet
Current neural network (NN) models can learn patterns from data points with historical dependence. Specifically, in natural language processing (NLP), sequential learning has transitioned from recurrence-based architectures to transformer-based architectures. However, it is unknown which NN architectures will perform the best on datasets containing deformation history due to mechanical loading. Thus, this study ascertains the appropriateness of 1D-convolutional, recurrent, and transformer-based architectures for predicting deformation localization based on the earlier states in the form of deformation history. Following this investigation, the crucial incompatibility issues between the mathematical computation of the prediction process in the best-performing NN architectures and the actual values derived from the natural physical properties of the deformation paths are examined in detail.