Physics-based Data-Augmented Deep Learning for Enhanced Autogenous Shrinkage Prediction on Experimental Dataset

Vishu Gupta, Yuhui Lyu, Derick Suarez, Yuwei Mao, Wei Keng Liao, Alok Choudhary, Wing Kam Liu, Gianluca Cusatis, Ankit Agrawal

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Scopus citations

Abstract

Prediction of the autogenous shrinkage referred to as the reduction of apparent volume of concrete under seal and isothermal conditions is of great significance in the service life analysis and design of durable concrete structures, especially with the increasing use of concrete with low water-to-cement ratios. However, due to the highly complex mechanism of autogenous shrinkage, it is hard to design accurate mechanistic models for it. Existing state-of-the-art models for autogenous shrinkage do not perform well for several reasons such as not being able to capture faster shrinkage change at early ages (swelling), coefficients used are derived using statistical optimization methods to fit certain databases only, and mechanism to identify the most influencing factors on autogenous shrinkage is not present. Moreover, it is also challenging to deploy a machine learning framework directly to perform predictive analysis due to the sparse and noisy nature of the available experimental dataset. In this paper, we study and propose a method to combine the physics-based knowledge and the predictive ability of deep regression neural networks to mitigate the shortcomings of the existing models. We introduce a novel data augmentation technique that utilizes physics based knowledge to improve the accuracy while maintaining the characteristics of autogenous shrinkage in its predictions simultaneously. Using state-of-the-art B4 model, a genetic algorithm, and a deep neural network trained using raw data for comparison, we show that the proposed methods help improve the accuracy of the model as compared to other methods. We also observe that the proposed method is able to successfully learn and predict the swelling component of the shrinkage strain curve as well, which cannot be predicted using the existing state-of-the-art models.

Original languageEnglish (US)
Title of host publication15th International Conference on Contemporary Computing, IC3 2023
EditorsSundaraja Sitharama Iyengar, Vikas Saxena
PublisherAssociation for Computing Machinery
Pages188-197
Number of pages10
ISBN (Electronic)9798400700224
DOIs
StatePublished - Aug 3 2023
Event15th International Conference on Contemporary Computing, IC3 2023 - Noida, India
Duration: Aug 3 2023Aug 5 2023

Publication series

NameACM International Conference Proceeding Series

Conference

Conference15th International Conference on Contemporary Computing, IC3 2023
Country/TerritoryIndia
CityNoida
Period8/3/238/5/23

Funding

The authors would like to thank Dr. Zdenek P Bazant and Dr. Ahmet Abdullah Dönmez for helpful discussions. This work is supported in part by the following grants: National Institute of Standards and Technology (NIST) award 70NANB19H005; Predictive Science and Engineering Design Cluster (PS&ED, Northwestern University); Department of Energy (DOE) awards DE-SC0019358, DE-SC0021399; NSF award CMMI-2053929, and Northwestern Center for Nanocom-binatorics.

Keywords

  • Autogenous Shrinkage
  • Deep Learning
  • Deep Regression
  • Physics Based Data Augmentation
  • Predictive Modeling

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Fingerprint

Dive into the research topics of 'Physics-based Data-Augmented Deep Learning for Enhanced Autogenous Shrinkage Prediction on Experimental Dataset'. Together they form a unique fingerprint.

Cite this