神经网络作为物理一致的替代模型:一种用于学习本构关系的可解释人工智能验证框架
Neural Networks as Physics-Consistent Surrogates: An \textit{Explainable AI} Validation Framework for Learning Constitutive Relations
AI总结:
本文提出一种XAI框架,通过验证神经网络学习材料本构关系的物理机制,证明其能捕捉材料刚度、历史依赖性和时间衰减等物理特性。
摘要:
本文提出了一种物理-可解释人工智能(XAI)框架,用于验证和解释神经网络在固体力学本构建模中的应用。该研究通过将数据驱动模型与连续力学理论相结合,应用一系列可解释性方法来验证训练于三种不同材料行为(超弹性(Mooney-Rivlin)、弹塑性(Chaboche)和粘弹性(Fractional Zener))的神经网络。首先,通过合成数据训练高保真替代模型,包括密集前馈网络、LSTMs和GRUs,以准确捕捉复杂材料响应。核心工作则采用XAI技术来“打开黑箱”,验证网络确实学习了物理上有意义的原理。对于超弹性,基于梯度的归因(Grad Input (GI))成功匹配了分析切线模量,证明了网络学习了材料刚度。对于弹塑性,SHapley Additive exPlanations (SHAP) 和 Principal Component Analysis (PCA) 表明循环神经网络(RNN)内部化了路径依赖的记忆,SHAP识别出塑性应变是主导特征,决定了应力预测。对于粘弹性,对GRU层的潜在空间和小波分析揭示了清晰的时间层次结构,不同层编码了即时弹性响应、中间松弛和长期分数记忆。最终,该研究证明XAI框架能够验证神经网络并非仅仅拟合曲线,而是确实在学习刚度、历史依赖性和时间衰减的底层物理机制。
英文摘要:
This paper presents a Physics-\textit{Explainable AI} (XAI) framework to validate and interpret neural networks for the constitutive modeling of solid materials. The study bridges the gap between data-driven models and continuum mechanics by applying a suite of explainability methods to neural networks trained on three distinct material behaviors: hyperelasticity (\textit{Mooney-Rivlin}), elastoplasticity (\textit{Chaboche}), and viscoelasticity (\textit{Fractional Zener}). First, high-fidelity surrogate models, including dense feed-forward networks, LSTMs, and GRUs, are trained on synthetically generated data to accurately capture complex material responses. The core of the work then employs XAI techniques to "open the black box" and confirm that the networks learn physically meaningful principles. For hyperelasticity, gradient-based attributions (\textit{Grad Input} (GI)) successfully match the analytical tangent modulus, proving the network learned material stiffness. For elastoplasticity, \textit{SHapley Additive exPlanations} (SHAP) and \textit{Principal Component Analysis} (PCA) demonstrate the \textit{Recurrent Neural Network} (RNN) internalizes path-dependent memory, with SHAP identifying \textit{plastic strain} as the dominant feature governing the stress prediction. For viscoelasticity, latent-space and wavelet analyses of the \textit{Gated Recurrent Unit. } GRU layers reveal a clear temporal hierarchy, with different layers encoding instantaneous elastic response, intermediate relaxation, and long-term fractional memory. Ultimately, the study demonstrates that the XAI framework can verify that the neural networks are not merely curve-fitting but are, in fact, learning the underlying physical mechanisms of stiffness, history-dependence, and temporal damping.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。