Neural Network Accelerated Process Design of Polycrystalline Microstructures

• URL: http://arxiv.org/abs/2305.00003v2
• Date: Wed, 3 May 2023 04:07:49 GMT
• Title: Neural Network Accelerated Process Design of Polycrystalline Microstructures
• Authors: Junrong Lin, Mahmudul Hasan, Pinar Acar, Jose Blanchet and Vahid Tarokh
• Abstract summary: We develop a neural network (NN)-based method with physics-infused constraints to predict microstructural evolution. In this study, our NN-based method is applied to maximize the homogenized stiffness of a Copper microstructure. It is found to be 686 times faster while achieving 0.053% error in the resulting homogenized stiffness compared to the traditional finite element simulator.
• Score: 23.897115046430635
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Computational experiments are exploited in finding a well-designed processing path to optimize material structures for desired properties. This requires understanding the interplay between the processing-(micro)structure-property linkages using a multi-scale approach that connects the macro-scale (process parameters) to meso (homogenized properties) and micro (crystallographic texture) scales. Due to the nature of the problem's multi-scale modeling setup, possible processing path choices could grow exponentially as the decision tree becomes deeper, and the traditional simulators' speed reaches a critical computational threshold. To lessen the computational burden for predicting microstructural evolution under given loading conditions, we develop a neural network (NN)-based method with physics-infused constraints. The NN aims to learn the evolution of microstructures under each elementary process. Our method is effective and robust in finding optimal processing paths. In this study, our NN-based method is applied to maximize the homogenized stiffness of a Copper microstructure, and it is found to be 686 times faster while achieving 0.053% error in the resulting homogenized stiffness compared to the traditional finite element simulator on a 10-process experiment.

Related papers

• Quantum-inspired Reinforcement Learning for Synthesizable Drug Design [20.00111975801053]
  We introduce a novel approach using the reinforcement learning method with quantum-inspired simulated annealing policy neural network to navigate the vast discrete space of chemical structures intelligently. Specifically, we employ a deterministic REINFORCE algorithm using policy neural networks to output transitional probability to guide state transitions and local search. Our methods are evaluated with the Practical Molecular Optimization (PMO) benchmark framework with a 10K query budget.
  arXiv  Detail & Related papers  (2024-09-13T20:43:16Z)
• Mechanistic Design and Scaling of Hybrid Architectures [114.3129802943915]
  We identify and test new hybrid architectures constructed from a variety of computational primitives. We experimentally validate the resulting architectures via an extensive compute-optimal and a new state-optimal scaling law analysis. We find MAD synthetics to correlate with compute-optimal perplexity, enabling accurate evaluation of new architectures.
  arXiv  Detail & Related papers  (2024-03-26T16:33:12Z)
• A Neural Network Transformer Model for Composite Microstructure Homogenization [1.2277343096128712]
  Homogenization methods, such as the Mori-Tanaka method, offer rapid homogenization for a wide range of constituent properties. This paper illustrates a transformer neural network architecture that captures the knowledge of various microstructures. The network predicts the history-dependent, non-linear, and homogenized stress-strain response.
  arXiv  Detail & Related papers  (2023-04-16T19:57:52Z)
• A micromechanics-based recurrent neural networks model for path-dependent cyclic deformation of short fiber composites [0.0]
  In this work, a recurrent deep neural network model is trained to predict the path-dependent elasto-plastic stress response of short fiber reinforced composites. The model gives very accurate predictions in a computationally efficient manner when compared with independent micromechanical simulations.
  arXiv  Detail & Related papers  (2022-09-27T12:14:15Z)
• Multi-fidelity Hierarchical Neural Processes [79.0284780825048]
  Multi-fidelity surrogate modeling reduces the computational cost by fusing different simulation outputs. We propose Multi-fidelity Hierarchical Neural Processes (MF-HNP), a unified neural latent variable model for multi-fidelity surrogate modeling. We evaluate MF-HNP on epidemiology and climate modeling tasks, achieving competitive performance in terms of accuracy and uncertainty estimation.
  arXiv  Detail & Related papers  (2022-06-10T04:54:13Z)
• Three-dimensional microstructure generation using generative adversarial neural networks in the context of continuum micromechanics [77.34726150561087]
  This work proposes a generative adversarial network tailored towards three-dimensional microstructure generation. The lightweight algorithm is able to learn the underlying properties of the material from a single microCT-scan without the need of explicit descriptors.
  arXiv  Detail & Related papers  (2022-05-31T13:26:51Z)
• A deep learning driven pseudospectral PCE based FFT homogenization algorithm for complex microstructures [68.8204255655161]
  It is shown that the proposed method is able to predict central moments of interest while being magnitudes faster to evaluate than traditional approaches. It is shown, that the proposed method is able to predict central moments of interest while being magnitudes faster to evaluate than traditional approaches.
  arXiv  Detail & Related papers  (2021-10-26T07:02:14Z)
• Efficient Micro-Structured Weight Unification and Pruning for Neural Network Compression [56.83861738731913]
  Deep Neural Network (DNN) models are essential for practical applications, especially for resource limited devices. Previous unstructured or structured weight pruning methods can hardly truly accelerate inference. We propose a generalized weight unification framework at a hardware compatible micro-structured level to achieve high amount of compression and acceleration.
  arXiv  Detail & Related papers  (2021-06-15T17:22:59Z)
• EBM-Fold: Fully-Differentiable Protein Folding Powered by Energy-based Models [53.17320541056843]
  We propose a fully-differentiable approach for protein structure optimization, guided by a data-driven generative network. Our EBM-Fold approach can efficiently produce high-quality decoys, compared against traditional Rosetta-based structure optimization routines.
  arXiv  Detail & Related papers  (2021-05-11T03:40:29Z)
• De-homogenization using Convolutional Neural Networks [1.0323063834827415]
  This paper presents a deep learning-based de-homogenization method for structural compliance minimization. For an appropriate choice of parameters, the de-homogenized designs perform within $7-25%$ of the homogenization-based solution.
  arXiv  Detail & Related papers  (2021-05-10T09:50:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.