Skip to Main Content
 

Global Search Box

 
 
 

ETD Abstract Container

Abstract Header

Physics-Informed Deep Learning Networks for Increased Accuracy and Reliability of Material Simulations

Lenau, Ashley
http://rave.ohiolink.edu/etdc/view?acc_num=osu171344367525487

Abstract Details

2024, Doctor of Philosophy, Ohio State University, Materials Science and Engineering.
Simulations of materials are a cost-efcient way to study materials that aid in experimental planning and material design. For example, stress and plasticity analysis is readily performed by numerically-based simulations, like fnite element or spectral based methods, and are typically faster than performing the experiment itself. However, slow computation times of more complex simulations limit their use in the design space. Deep learning (DL) networks have been shown to be orders of magnitude faster than numerically-based simulations but are lacking in numerical accuracy by comparison. Furthermore, large datasets are required to train a DL network and collecting a sufcient amount is a difcult task in materials science. Incorporating physical laws of the material system within the DL model has been shown to create a more physically accurate network, but can be difcult to implement. In this thesis, DL networks are physically informed through the data, network architecture, or loss function to create a model that accurately refects the underlying physics of the material system. First, a network is proposed to study the feasibility of 3D grain reconstruction from mid-feld high energy difraction refections. Each refection corresponds to its own subnetwork, tailoring the weights to a specifc refection. In a diferent network, a U-Net is used to simulate the micromechanical evolution of a 3D polycrystal at small strain increments and predict the full-feld orientation and elastic strain. The network is physically informed about the Von Mises stress relationship from the predicted elastic strain tensors. The training requirements of networks having physics-informed characteristics are studied in more depth using stress feld prediction as a case study. A Pix2Pix model is used to translate a two-phase composite having high elastic contrast to the corresponding stress fields. Several diferent physics-based regularization methods are implemented to enforce stress equilibrium in the predictions. Separate hyperparameter fne-tuning is investigated for each implementation to achieve the best performance and more fair comparisons between the methods. The amount of time and data needed to train a network with or without known physics is studied. Finally, the model variation across different training sessions for a given implementation is studied, and results show that the networks having physically informed losses were significantly more consistent in enforcing stress equilibrium.
Stephen Niezgoda (Advisor)
Dennis Dimiduk (Committee Member)
Reeju Pokharel (Committee Member)
Aeriel Leonard (Committee Member)
Michael Groeber (Committee Member)
179 p.
Materials Science
physics informed, deep learning, machine learning, materials science, high-energy diffraction microscopy, micromechanical evolution, crystal plasticity

Recommended Citations

Citations

  • Lenau, A. (2024). Physics-Informed Deep Learning Networks for Increased Accuracy and Reliability of Material Simulations [Doctoral dissertation, Ohio State University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=osu171344367525487

    APA Style (7th edition)

  • Lenau, Ashley. Physics-Informed Deep Learning Networks for Increased Accuracy and Reliability of Material Simulations. 2024. Ohio State University, Doctoral dissertation. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=osu171344367525487.

    MLA Style (8th edition)

  • Lenau, Ashley. "Physics-Informed Deep Learning Networks for Increased Accuracy and Reliability of Material Simulations." Doctoral dissertation, Ohio State University, 2024. http://rave.ohiolink.edu/etdc/view?acc_num=osu171344367525487

    Chicago Manual of Style (17th edition)

osu171344367525487
162
© 2024, all rights reserved.
This open access ETD is published by The Ohio State University and OhioLINK.