Prediction of mechanical behavior of rocks with strong strain-softening effects by a deep-learning approach
Prediction of mechanical behavior of rocks with strong strain-softening effects by a deep-learning approach
复制标题
通过深度学习方法预测具有强应变软化效应的岩石的力学行为
DOI：
10.1016/j.compgeo.2022.105040
复制
发表时间：
2022-12
影响因子：
5.3
通讯作者：
Sun Haohang
中科院分区：
文献类型：
--
作者：
Shi Lingling;Zhang Jin;Zhu Qizhi;Sun Haohang
岩石材料具有多种力学特性，很难用单一的本构关系来描述具有强应变软化特性的应变-应力关系。在本研究中，提出了一种长短期记忆（LSTM）深度学习方法来预测材料在不同载荷条件下的变形。与传统的分析方法侧重于确定有效的切线刚度张量，所构建的基于LSTM的程序只需要在某些情况下的应变-应力值来预测未来的力学行为，即使是具有强应变软化的岩石材料，这表明加载历史可以考虑作为时间序列数据。为了验证模型的准确性，将LSTM模型应用于花岗岩和砂岩的常规三轴压缩变形预测，而不引入任何弹塑性参数或本构关系，其中用于训练LSTM模型的数据集从细观损伤分析模型和实验室实验中交替收集，并考虑了广泛的围压范围。不同的神经网络结构的精度和收敛速度的比较也进行了检查的最佳性能的程序。给出了将训练好的LSTM模型作为本构关系在有限元程序中的实现方法，并将其应用于砂岩的模拟。结果表明，LSTM-FEM方法具有较好的预测岩石力学行为的能力。
Rock materials exhibit various mechanical characteristics, and it is difficult to describe the strain–stress relation with strong strain-softening behavior by a single constitutive law. In the present study, a long short term memory (LSTM) deep learning method is proposed to predict the material’s deformation under different loading conditions. Unlike the traditional analysis method focusing on the determination of effective tangent stiffness tensor, the constructed LSTM-based procedure requires only the strain–stress values in certain cases to predict the future mechanical behaviors, even for rock materials with strong strain-softening, indicating that the loading history can be taken into account as time sequence data. In order to validate the accuracy, two applications are provided with the established LSTM model: predicting the deformation of granite and sandstone in conventional triaxial compression tests without introducing any elastoplastic parameters or constitutive laws, where the dataset for training the LSTM model is collected alternatively from an analytical micromechanical damage model and from laboratory experiments by considering a wide range of confining pressure. Comparisons of accuracy and convergence rate with different neural network structures are also carried out to check the best performance of the procedure. Implementation method of the trained LSTM model in Finite Element program as a constitutive relation is also provided and applied to the simulation of sandstone. Comparisons show that the LSTM-FEM method provides a good capacity to predict the mechanical behavior of rocks.
登录
查看更多内容
DOI：
10.1016/0045-7825(85)90061-1
发表时间：
1985-06
影响因子：
7.2
作者：
J. Simo;M. Ortiz
通讯作者：
J. Simo;M. Ortiz
影响因子：
0.8
作者：
Dormieux, Luc;Kondo, Djimedo;Ulm, Franz-Josef
通讯作者：
Ulm, Franz-Josef
影响因子：
4.7
作者：
Q. Peng;M. X. Chen
通讯作者：
Q. Peng;M. X. Chen
断续节理岩单轴循环压缩损伤本构模型
DOI：
10.1016/j.ijrmms.2018.01.046
发表时间：
2018-03-01
影响因子：
7.2
作者：
Liu, Yi;Dai, Feng
通讯作者：
Dai, Feng
一种精细的微机械损伤摩擦模型，可预测受压岩石材料的强度
DOI：
10.1016/j.ijsolstr.2015.02.005
发表时间：
2015-05
影响因子：
3.6
作者：
Q.Z. Zhu;J.F. Shao
通讯作者：
J.F. Shao