Recurrent neural networks (RNNs) learn the constitutive law of viscoelasticity

被引:55
作者
Chen, Guang [1 ]
机构
[1] Univ Connecticut, Dept Mech Engn, Storrs, CT 06269 USA
关键词
Constitutive modeling; Deep learning; History-dependent materials; Recurrent neural networks; Viscoelasticity; INTELLIGENCE; PLASTICITY; FRAMEWORK; DESIGN;
D O I
10.1007/s00466-021-01981-y
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
Recurrent neural networks (RNNs) have demonstrated very impressive performances in learning sequential data, such as in language translation and music generation. Here, we show that the intrinsic computational aspect of RNNs is very similar to that of classical stress update algorithms in modeling history-dependent materials with an emphasis on viscoelasticity. Several numerical examples are designed, including 1-dimensional and 3-dimensional cases, which testify the ability of RNN model to compute the viscoelastic response when predicting on unseen test data. Additionally, it is found that the RNN model trained only on linear and step strain inputs can perform very well on prediction of completely different quadratic strain inputs, demonstrating certain level of generalization ability in extrapolation. Moreover, it is observed that the extrapolation ability depends on the types of strain inputs. The performance is better for continuous strain inputs than that for jump strain inputs. The differences in the generalization ability of RNN models in viscoelasticity and other history-dependent materials are discussed. It suggests that RNN data-driven modeling can be an alternative to the conventional viscoelasticity models.
引用
收藏
页码:1009 / 1019
页数:11
相关论文
共 39 条
[1]  
Abadi M, 2016, PROCEEDINGS OF OSDI'16: 12TH USENIX SYMPOSIUM ON OPERATING SYSTEMS DESIGN AND IMPLEMENTATION, P265
[2]   Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) [J].
Adadi, Amina ;
Berrada, Mohammed .
IEEE ACCESS, 2018, 6 :52138-52160
[3]  
[Anonymous], 1913, NACHR GES WISS GOETT
[4]  
Belytschko T., 2013, SAP2000 Version 19.0. 0
[5]   A framework for data-driven analysis of materials under uncertainty: Countering the curse of dimensionality [J].
Bessa, M. A. ;
Bostanabad, R. ;
Liu, Z. ;
Hu, A. ;
Apley, Daniel W. ;
Brinson, C. ;
Chen, W. ;
Liu, Wing Kam .
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 2017, 320 :633-667
[6]   Machine Learning for Fluid Mechanics [J].
Brunton, Steven L. ;
Noack, Bernd R. ;
Koumoutsakos, Petros .
ANNUAL REVIEW OF FLUID MECHANICS, VOL 52, 2020, 52 :477-508
[7]   Drug design by machine learning: support vector machines for pharmaceutical data analysis [J].
Burbidge, R ;
Trotter, M ;
Buxton, B ;
Holden, S .
COMPUTERS & CHEMISTRY, 2001, 26 (01) :5-14
[8]   A machine-learning-assisted study of the permeability of small drug-like molecules across lipid membranes [J].
Chen, Guang ;
Shen, Zhiqiang ;
Li, Ying .
PHYSICAL CHEMISTRY CHEMICAL PHYSICS, 2020, 22 (35) :19687-19696
[9]   Machine-Learning-Assisted De Novo Design of Organic Molecules and Polymers: Opportunities and Challenges [J].
Chen, Guang ;
Shen, Zhiqiang ;
Iyer, Akshay ;
Ghumman, Umar Farooq ;
Tang, Shan ;
Bi, Jinbo ;
Chen, Wei ;
Li, Ying .
POLYMERS, 2020, 12 (01)
[10]  
Cho K., 2014, C EMP METH NAT LANG, P1724, DOI [10.3115/v1/D14-1179, DOI 10.3115/V1/D14-1179]