arXiv：cs.LG· Ali Maghami, Merten Stender, Michele Ciavarella, Antonio Papangelo·· 5 小时前AI 评分28
深度学习预测粘弹性 Hertzian 接触中的时间分辨粘附力
Deep learning-based prediction of time-resolved adhesive forces in viscoelastic Hertzian contacts
AI 导读
研究训练了一个标量条件化、有状态的序列到序列深度学习模型，从给定位移历史预测短程与长程粘附机制下的完整力演化轨迹。数据集覆盖四个数量级的加载与卸载速率，Tabor 参数从 0.2 到 3.2，并引入固定测量步长（FMS）表示以跨异构时间尺度学习。
正文
Abstract:Fast prediction of the response of adhesive soft viscoelastic contacts represents a current challenge in soft robotics and for gripping and manipulation tasks. Determining the complete time-resolved force trajectory requires full numerical simulations, whose computational cost is strongly parameter-dependent, making them impractical for real-time application or design-optimization loops. In this work, we overcome this limitation by training a scalar-conditioned, stateful, sequence-to-sequence deep learning model to predict the full force evolution from a prescribed displacement history for both short- and long-range adhesion regimes. The data set spans four orders of magnitude in loading and unloading rates and includes varied dwell times, with the Tabor parameter ranging from $0.2$ to $3.2$. To enable learning across these heterogeneous time scales, we introduce a fixed-measurement-step (FMS) representation that converts variable-length trajectories into fixed-length sequences while preserving their physical-time information. Different architectures were trained, including long short-term memory (LSTM) networks, temporal convolutional neural (TCN) networks, and time-distributed dense layers with three different Tabor-conditioning mechanisms. The models were compared using global waveform and error metrics. We found that the best-performing model has an LSTM architecture with concatenated conditioning, which achieves a held-out mean-squared error of $5.0\times10^{-4}$, a median pull-off-force error of $\approx2.2\%$, and a median hysteresis error of $\approx1.1\%$. For the held-out protocols, the model predicts a complete force trajectory with a median inference time of $0.16$ s. The model is tested across unseen parameter combinations and against analytical limiting cases, providing a rapid surrogate for repeated numerical evaluations with potential use in control-oriented applications.
| Subjects: | Machine Learning (cs.LG); Soft Condensed Matter (cond-mat.soft); Artificial Intelligence (cs.AI); Data Analysis, Statistics and Probability (physics.data-an); Machine Learning (stat.ML) |
| Cite as: | arXiv:2607.19060 [cs.LG] |
| (or arXiv:2607.19060v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2607.19060 arXiv-issued DOI via DataCite |
Submission history
From: Ali Maghami [view email]
[v1]
Tue, 21 Jul 2026 12:48:48 UTC (7,359 KB)
[v2]
Thu, 1 Oct 2026 22:51:13 UTC (12,590 KB)
来源：arXiv：cs.LG · arxiv.org