Fractional rheology-informed neural networks for data-driven identification of viscoelastic constitutive models
Fractional rheology-informed neural networks for data-driven identification of viscoelastic constitutive models
复制标题
用于数据驱动识别粘弹性本构模型的基于分数流变学的神经网络
DOI：
10.1007/s00397-023-01408-w
复制
发表时间：
2023
期刊：
影响因子：
2.3
通讯作者：
Jamali, Safa
中科院分区：
文献类型：
--
作者：
Dabiri, Donya;Saadat, Milad;Mangal, Deepak;Jamali, Safa
开发能够描述复杂流体对施加刺激的响应的本构模型一直是流变学家的重要追求之一。模型的复杂性通常与观察到的行为密切相关，并且根据材料和/或流程协议的选择，模型很快就会变得令人望而却步。因此，通过寻求这些本构模型的紧凑表示来减少拟合参数的数量可以避免限制参数空间的额外实验。为此，物质的微分响应接受非整数阶的分数导数已显示出希望。在这里，我们开发了由一系列不同的分数本构模型提供信息的神经网络。然后使用这些分数流变学神经网络 (RhINN) 来恢复三个分数粘弹性本构模型（即分数麦克斯韦模型、开尔文-沃伊特模型和齐纳模型）的相关参数（分数阶导数阶数）。我们发现，对于所有三个研究模型，RhINN 都能准确地恢复观察到的行为，尽管在某些情况下，恢复的分数阶导数阶数与所谓的基本事实存在显着偏差。这表明当材料响应相对简单时，额外的分数元素是多余的。因此，为给定的材料响应选择分数本构模型取决于响应的复杂性，因为分数单元体现了广泛的瞬态材料行为。
Developing constitutive models that can describe a complex fluid’s response to an applied stimulus has been one of the critical pursuits of rheologists. The complexity of the models typically goes hand-in-hand with that of the observed behaviors and can quickly become prohibitive depending on the choice of materials and/or flow protocols. Therefore, reducing the number of fitting parameters by seeking compact representations of those constitutive models can obviate extra experimentation to confine the parameter space. To this end, fractional derivatives in which the differential response of matter accepts non-integer orders have shown promise. Here, we develop neural networks that are informed by a series of different fractional constitutive models. These fractional rheology-informed neural networks (RhINNs) are then used to recover the relevant parameters (fractional derivative orders) of three fractional viscoelastic constitutive models, i.e., fractional Maxwell, Kelvin-Voigt, and Zener models. We find that for all three studied models, RhINNs recover the observed behavior accurately, although in some cases, the fractional derivative order is recovered with significant deviations from what is known as ground truth. This suggests that extra fractional elements are redundant when the material response is relatively simple. Therefore, choosing a fractional constitutive model for a given material response is contingent upon the response complexity, as fractional elements embody a wide range of transient material behaviors.
登录
查看更多内容
影响因子：
2.7
作者：
Reyes, Brandon;Howard, Amanda A.;Tartakovsky, Alexandre M.
通讯作者：
Tartakovsky, Alexandre M.
分数阶电容器时域分析中黎曼-刘维尔和卡普托导数定义的比较研究
DOI：
10.1109/tcsii.2019.2952693
发表时间：
2020-10-01
影响因子：
4.4
作者：
Jiang, Yanwei;Zhang, Bo
通讯作者：
Zhang, Bo
分数阶粘弹性模型
DOI：
--
发表时间：
2010
期刊：
影响因子：
--
作者：
F. Mainardi
通讯作者：
F. Mainardi
影响因子：
19.6
作者：
Bantawa, Minaspi;Keshavarz, Bavand;Geri, Michela;Bouzid, Mehdi;Divoux, Thibaut;McKinley, Gareth H.;Del Gado, Emanuela
通讯作者：
Del Gado, Emanuela
影响因子：
3.3
作者：
Mahmoudabadbozchelou, Mohammadamin;Caggioni, Marco;Jamali, Safa
通讯作者：
Jamali, Safa