比较三种模型预测材料变形历史，发现其物理兼容性差异。
Exploring Various Sequential Learning Methods for Deformation History Modeling
- 对比1D卷积、循环和注意力机制在变形历史建模中的表现。
- 最优模型在数学计算与物理规律间存在关键不匹配问题。
- 适合关注模型物理合理性的力学仿真研究者。
现有神经网络可从具有历史依赖性的数据中学习模式。自然语言处理中，序列学习已从基于循环的架构转向基于Transformer的架构。然而，对于包含机械加载下变形历史的数据集，哪种神经网络架构表现最佳尚不清楚。本研究评估了1D卷积、循环和Transformer架构在基于早期变形状态预测变形局部化时的适用性。随后，深入分析了表现最佳的神经网络架构在预测过程的数学计算与实际变形路径物理特性之间的关键不兼容问题。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。