Deep Learning for One-dimensional Consolidation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Bekele, Yared W.
Format: Preprint
Published: 2020
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917935614787584
author Bekele, Yared W.
author_facet Bekele, Yared W.
contents Neural networks with physical governing equations as constraints have recently created a new trend in machine learning research. In line with such efforts, a deep learning model for one-dimensional consolidation where the governing equation is applied as a constraint in the neural network is presented here. A review of related research is first presented and discussed. The deep learning model relies on automatic differentiation for applying the governing equation as a constraint. The total loss is measured as a combination of the training loss (based on analytical and model predicted solutions) and the constraint loss (a requirement to satisfy the governing equation). Two classes of problems are considered: forward and inverse problems. The forward problems demonstrate the performance of a physically constrained neural network model in predicting solutions for one-dimensional consolidation problems. Inverse problems show prediction of the coefficient of consolidation. Terzaghi's problem with varying boundary conditions are used as example and the deep learning model shows a remarkable performance in both the forward and inverse problems. While the application demonstrated here is a simple one-dimensional consolidation problem, such a deep learning model integrated with a physical law has huge implications for use in, such as, faster real-time numerical prediction for digital twins, numerical model reproducibility and constitutive model parameter optimization.
format Preprint
id arxiv_https___arxiv_org_abs_2004_11689
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Deep Learning for One-dimensional Consolidation
Bekele, Yared W.
Computational Engineering, Finance, and Science
Image and Video Processing
Neural networks with physical governing equations as constraints have recently created a new trend in machine learning research. In line with such efforts, a deep learning model for one-dimensional consolidation where the governing equation is applied as a constraint in the neural network is presented here. A review of related research is first presented and discussed. The deep learning model relies on automatic differentiation for applying the governing equation as a constraint. The total loss is measured as a combination of the training loss (based on analytical and model predicted solutions) and the constraint loss (a requirement to satisfy the governing equation). Two classes of problems are considered: forward and inverse problems. The forward problems demonstrate the performance of a physically constrained neural network model in predicting solutions for one-dimensional consolidation problems. Inverse problems show prediction of the coefficient of consolidation. Terzaghi's problem with varying boundary conditions are used as example and the deep learning model shows a remarkable performance in both the forward and inverse problems. While the application demonstrated here is a simple one-dimensional consolidation problem, such a deep learning model integrated with a physical law has huge implications for use in, such as, faster real-time numerical prediction for digital twins, numerical model reproducibility and constitutive model parameter optimization.
title Deep Learning for One-dimensional Consolidation
topic Computational Engineering, Finance, and Science
Image and Video Processing
url https://arxiv.org/abs/2004.11689