PRIMS：多模态传感中用于流体识别的物理引导表示
PRIMS: Physics-guided Representation for Fluid Identification in Multimodal Sensing
浏览论文内容
中文总结 AI 辅助
研究针对微流体应用中流体识别挑战，提出PRIMS物理感知多模态Transformer，通过三个模块集成物理知识于表示学习和注意力机制，实现可解释、数据高效的流体分类，实验显示其性能优越且鲁棒性强。
中文摘要 AI 辅助
准确的设备上流体识别对微流体应用至关重要，但在变化的流量、压力和温度下保持可靠性仍是关键挑战。现有基于学习的方法常将传感器信号视为与领域无关的特征，忽略了控制流体行为的潜在物理关系。为此，我们提出PRIMS，一种物理感知的多模态Transformer，通过三个专用模块将物理知识集成到表示学习和注意力机制中：基于物理的令牌矢量化将原始科里奥利和压力传感器信号转换为具有物理意义的令牌嵌入；物理组件合成器对流量、压力和密度之间与粘度相关的依赖性进行建模；物理引导融合通过基于注意力的集成捕获跨物理相关性。通过将这些基于物理的关系直接嵌入模型架构，PRIMS架起了分析流体力学和深度学习之间的桥梁，实现了可解释、数据高效且有弹性的流体分类。在动态流量、压力和温度条件下对五流体基准进行的评估表明，PRIMS仅用46万个参数就实现了98.92%的平均F1分数，比基于Transformer的现有方法减少了14倍。在分布外转移到未见过的温度范围和未见过的流速范围时，PRIMS也始终优于先前的SOTA模型，表明对训练期间未观察到的操作条件具有很强的鲁棒性。这些发现表明，设计明确反映控制物理关系的架构可以使它们学习可转移、与环境无关 的表示，提高微流体传感在现实世界中的可靠性。
英文摘要
Accurate on-device fluid identification is essential for microfluidic applications, yet maintaining reliability under varying flow, pressure, and temperature remains a key challenge. Existing learning-based methods often treat sensor signals as domain-agnostic features, neglecting the underlying physical relationships that govern fluid behavior, thereby limiting generalization and interpretability. To address this, we propose PRIMS, a physics-aware multimodal Transformer that integrates physical knowledge into representation learning and attention mechanisms through three dedicated modules: (1) Physics-based Token Vectorization transforms raw Coriolis and pressure sensor signals into physically meaningful token embeddings; (2) Physical Component Synthesizer models viscosity-related dependencies among flow, pressure, and density; and (3) Physics-guided Fusion captures cross-physical correlations through attention-based integration. By embedding these physics-based relationships directly into the model architecture, PRIMS bridges analytical fluid mechanics and deep learning, enabling interpretable, data-efficient, and resilient fluid classification. Evaluations on a five-fluid benchmark under dynamic flow, pressure, and temperature conditions show that PRIMS achieves 98.92% average F1-score with only 0.46 million parameters, a 14 times reduction compared to state-of-the-art Transformer-based methods. PRIMS also consistently outperforms prior SOTA models under out-of-distribution shifts to unseen temperature ranges and unseen flow-rate ranges, indicating strong robustness to operating conditions not observed during training. These findings suggest that designing architectures that explicitly mirror governing physical relationships can make them learn transferable, environment-independent representations, improving real-world reliability for microfluidic sensing.
发表机构
- University of Twente（特文特大学）
- Nagoya University（名古屋大学）
机构由 AI 辅助整理，请以论文原文为准。
