Exploring Various Sequential Learning Methods for Deformation History Modeling
This work addresses a domain-specific problem in materials science by evaluating sequential learning methods for deformation modeling, but it is incremental as it applies existing architectures to a new dataset.
The study compared 1D-convolutional, recurrent, and transformer-based neural network architectures for predicting deformation localization from mechanical loading history, identifying the best-performing ones and analyzing incompatibilities between their predictions and physical properties.
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.