Meta-modeling game for deriving theoretical-consistent, micro-structural-based traction-separation laws via deep reinforcement learning

Abstract

This paper presents a new meta-modeling framework to employ deep reinforcement learning (DRL) to generate mechanical constitutive models for interfaces. The constitutive models are conceptualized as information flow in directed graphs. The process of writing constitutive models are simplified as a sequence of forming graph edges with the goal of maximizing the model score (a function of accuracy, robustness and forward prediction quality). Thus meta-modeling can be formulated as a Markov decision process with well-defined states, actions, rules, objective functions, and rewards. By using neural networks to estimate policies and state values, the computer agent is able to efficiently self-improve the constitutive model it generated through self-playing, in the same way AlphaGo Zero (the algorithm that outplayed the world champion in the game of Go)improves its gameplay. Our numerical examples show that this automated meta-modeling framework not only produces models which outperform existing cohesive models on benchmark traction-separation data but is also capable of detecting hidden mechanisms among micro-structural features and incorporating them in constitutive models to improve the forward prediction accuracy, which are difficult tasks to do manually.

References in corpus (5)

• Adam: A Method for Stochastic Optimization
• Scikit-learn: Machine Learning in Python
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
• Stress-induced anisotropy in granular materials: fabric, stiffness, and permeability

Cited by in corpus (29)

• Physics-Informed Multi-LSTM Networks for Metamodeling of Nonlinear Structures
• Transfer learning based physics-informed neural networks for solving inverse problems in engineering structures under different loading scenarios
• Geometric deep learning for computational mechanics Part I: Anisotropic Hyperelasticity
• Deep Learning in Deterministic Computational Mechanics
• Recent Advances and Applications of Machine Learning in Experimental Solid Mechanics: A Review
• Denoising diffusion algorithm for inverse design of microstructures with fine-tuned nonlinear material properties
• Machine learning materials physics: Multi-resolution neural networks learn the free energy and nonlinear elastic response of evolving microstructures
• A phase field model for cohesive fracture in micropolar continua
• Recurrent Neural Networks (RNNs) with dimensionality reduction and break down in computational mechanics; application to multi-scale localization step
• Deep material network with cohesive layers: Multi-stage training and interfacial failure analysis
• A cooperative game for automated learning of elasto-plasticity knowledge graphs and models with AI-guided experimentation
• ILS-MPM: an implicit level-set-based material point method for frictional particulate contact mechanics of deformable particles
• Discovering interpretable elastoplasticity models via the neural polynomial method enabled symbolic regressions
• General solutions for nonlinear differential equations: a rule-based self-learning approach using deep reinforcement learning
• Physics informed deep learning for computational elastodynamics without labeled data
• Artificial Intelligence in Materials Science and Engineering: Current Landscape, Key Challenges, and Future Trajectorie
• Deep Learning and Crystal Plasticity: A Preconditioning Approach for Accurate Orientation Evolution Prediction
• A non-cooperative meta-modeling game for automated third-party calibrating, validating, and falsifying constitutive laws with parallelized adversarial attacks
• A Neural Network Transformer Model for Composite Microstructure Homogenization
• Towards out of distribution generalization for problems in mechanics
• Beyond Games: A Systematic Review of Neural Monte Carlo Tree Search Applications
• Bayesian neural networks for weak solution of PDEs with uncertainty quantification
• A graph theoretic framework for representation, exploration and analysis on computed states of physical systems
• How machine learning can help the design and analysis of composite materials and structures?
• Thermodynamic Consistent Neural Networks for Learning Material Interfacial Mechanics
• Exploring the potential of transfer learning for metamodels of heterogeneous material deformation
• Data-driven discovery of interpretable causal relations for deep learning material laws with uncertainty propagation
• A novel generative reverse net assisted evolution algorithm for expensive-computational optimizations
• An immersed phase field fracture model for fluid-infiltrating porous media with evolving Beavers-Joseph-Saffman condition