An offline multi‐scale unsaturated poromechanics model enabled by self‐designed/self‐improved neural networks
An offline multi‐scale unsaturated poromechanics model enabled by self‐designed/self‐improved neural networks
复制标题
DOI：
10.1002/nag.3196
复制
发表时间：
2021-02
影响因子：
4
通讯作者：
Y. Heider;H. S. Suh;WaiChing Sun
中科院分区：
文献类型：
--
作者：
Y. Heider;H. S. Suh;WaiChing Sun
基于人工神经网络(ANN)的有监督机器学习在许多涉及多相流和孔隙力学的地质力学应用中得到了广泛的应用。对于非饱和孔隙力学问题，水力规律的多物理性质和复杂性使得深层神经网络的最优设置、结构和超参数的设计变得困难。本文提出了一种利用深度强化学习(DRL)自动发现最优神经网络设置的元建模方法，以最大化机器学习本构关系的预定义性能指标。这个元建模框架被转换为马尔可夫决策过程(MDP)，具有定义良好的状态(表示所建议的神经网络(NN)设置的状态子集)、动作和奖励。按照选择规则，人工智能(AI)代理通过NN在DRL中表示，通过在选择环境内采取一系列动作和接收反馈信号(奖励)进行自我学习。通过利用蒙特卡罗树搜索(MCTS)来更新策略/价值网络，AI代理取代了人类建模师来处理原本耗时的反复试验过程，该过程导致从高维参数空间进行优化设置选择。该方法被应用于非饱和孔隙力学问题的两个关键本构关系的生成：(1)具有不同的湿路径和干燥路径的路径相关的保留曲线。(2)由各向异性渗透率张量控制的微孔内流动。数值实验表明，所得到的ML生成的材料模型可以集成到有限元(FE)求解器中来求解初边值问题，以取代手工本构关系。
Supervised machine learning via artificial neural network (ANN) has gained significant popularity for many geomechanics applications that involves multi‐phase flow and poromechanics. For unsaturated poromechanics problems, the multi‐physics nature and the complexity of the hydraulic laws make it difficult to design the optimal setup, architecture, and hyper‐parameters of the deep neural networks. This paper presents a meta‐modeling approach that utilizes deep reinforcement learning (DRL) to automatically discover optimal neural network settings that maximize a pre‐defined performance metric for the machine learning constitutive laws. This meta‐modeling framework is cast as a Markov Decision Process (MDP) with well‐defined states (subsets of states representing the proposed neural network (NN) settings), actions, and rewards. Following the selection rules, the artificial intelligence (AI) agent, represented in DRL via NN, self‐learns from taking a sequence of actions and receiving feedback signals (rewards) within the selection environment. By utilizing the Monte Carlo Tree Search (MCTS) to update the policy/value networks, the AI agent replaces the human modeler to handle the otherwise time‐consuming trial‐and‐error process that leads to the optimized choices of setup from a high‐dimensional parametric space. This approach is applied to generate two key constitutive laws for the unsaturated poromechanics problems: (1) the path‐dependent retention curve with distinctive wetting and drying paths. (2) The flow in the micropores, governed by an anisotropic permeability tensor. Numerical experiments have shown that the resultant ML‐generated material models can be integrated into a finite element (FE) solver to solve initial‐boundary‐value problems as replacements of the hand‐craft constitutive laws.