Surrogate Modeling using Physics-guided Learning
Pages 130 - 135
Abstract
Computer simulation models are used extensively in scientific and engineering problems for complex design tasks and decision processes. Surrogate models generated using data-driven techniques can approximate the behavior of complex simulation models with high fidelity and can accelerate the design process. This paper presents a physics-guided learning architecture that integrates parameters extracted from physics-based simulations into the intermediate layers of a neural network to constrain the learning process during the training of surrogate models and to improve their generalization. The proposed architecture is used to develop a surrogate model for evaluating the structural integrity of the hull of an unmanned underwater vehicle. It is shown that physics-guided learning can improve generalization in less explored regions of the design space compared to black-box models. In addition, the architecture improves the explainability of the model predictions using physics-based parameters and allows the designer to make decisions based on the input and physics-based intermediate parameters.
References
[1]
ANSYS. 2022. Student Version, 2022 R2. Ansys, Inc., Canonsburg, Pennsylvania.
[2]
Sebastian Bach, Alexander Binder, Grégoire Montavon, Frederick Klauschen, Klaus-Robert Müller, and Wojciech Samek. 2015. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PloS one 10, 7 (2015), e0130140.
[3]
Adam Cobb, Anirban Roy, Daniel Elenius, and Susmit Jha. 2022. Trinity AI Co-Designer for Hierarchical Oracle-guided Design of Cyber-Physical Systems. In 2022 IEEE Workshop on Design Automation for CPS and IoT (DESTION). IEEE, 42–44.
[4]
Arka Daw, Anuj Karpatne, William D Watkins, Jordan S Read, and Vipin Kumar. 2017. Physics-guided neural networks (pgnn): An application in lake temperature modeling. In Knowledge-Guided Machine Learning. Chapman and Hall/CRC, 353–372.
[5]
Matthew Emerson and Janos Sztipanovits. 2006. Techniques for metamodel composition. In OOPSLA–6th Workshop on Domain Specific Modeling. 123–139.
[6]
David Jones, Chris Snider, Aydin Nassehi, Jason Yon, and Ben Hicks. 2020. Characterising the Digital Twin: A systematic literature review. CIRP Journal of Manufacturing Science and Technology 29 (2020), 36–52.
[7]
Alexander Kaszynski. 2020. pyansys: Python Interface to MAPDL and Associated Binary and ASCII Files. https://doi.org/10.5281/zenodo.4009467
[8]
Michael D McKay, Richard J Beckman, and William J Conover. 2000. A comparison of three methods for selecting values of input variables in the analysis of output from a computer code. Technometrics 42, 1 (2000), 55–61.
[9]
R v Mises. 1913. Mechanik der festen Körper im plastisch-deformablen Zustand. Nachrichten von der Gesellschaft der Wissenschaften zu Göttingen, Mathematisch-Physikalische Klasse 1913 (1913), 582–592.
[10]
Grégoire Montavon, Alexander Binder, Sebastian Lapuschkin, Wojciech Samek, and Klaus-Robert Müller. 2019. Layer-wise relevance propagation: an overview. Explainable AI: interpreting, explaining and visualizing deep learning (2019), 193–209.
[11]
Ali I Ozdagli and Xenofon Koutsoukos. 2021. Model-based Damage Detection through Physics Guided Learning. In Annual Conference of the PHM Society, Vol. 13.
[12]
V Papadopoulos, G Soimiris, DG Giovanis, and M Papadrakakis. 2018. A neural network-based surrogate model for carbon nanotubes with geometric nonlinearities. Computer Methods in Applied Mechanics and Engineering 328 (2018), 411–430.
[13]
Nestor V Queipo, Raphael T Haftka, Wei Shyy, Tushar Goel, Rajkumar Vaidyanathan, and P Kevin Tucker. 2005. Surrogate-based analysis and optimization. Progress in aerospace sciences 41, 1 (2005), 1–28.
[14]
DL Shrestha, N Kayastha, and DP Solomatine. 2009. A novel approach to parameter uncertainty analysis of hydrological models using neural networks. Hydrology and Earth System Sciences 13, 7 (2009), 1235–1248.
[15]
Mahendra Pratap Singh and Bilas Chowdhury. 2011. Control of autonomous underwater vehicles. Ph. D. Dissertation. National Institute of Technology, Rourkela.
[16]
J Sreekanth and Bithin Datta. 2010. Multi-objective management of saltwater intrusion in coastal aquifers using genetic programming and modular neural network based surrogate models. Journal of hydrology 393, 3-4 (2010), 245–256.
[17]
Ruiyang Zhang, Yang Liu, and Hao Sun. 2020. Physics-guided convolutional neural network (PhyCNN) for data-driven seismic response modeling. Engineering Structures 215 (2020), 110704.
Recommendations
Some considerations regarding the use of multi-fidelity Kriging in the construction of surrogate models
Surrogate models or metamodels are commonly used to exploit expensive computational simulations within a design optimization framework. The application of multi-fidelity surrogate modeling approaches has recently been gaining ground due to the potential ...
A physics and data co-driven surrogate modeling method for high-dimensional rare event simulation
AbstractThis paper presents a physics and data co-driven surrogate modeling method for efficient rare event simulation of civil and mechanical systems with high-dimensional input uncertainties. The method fuses interpretable low-fidelity physical models ...
Highlights- Physics-data-driven surrogate modeling method for estimating small probabilities.
- Fusion of physical model, error correction, active learning, and importance sampling.
- Highly efficient for rare event simulation with high-...
Data-efficient surrogate modeling using meta-learning and physics-informed deep learning approaches
AbstractThis paper proposes physics-informed meta-learning-based surrogate modeling (PI-MLSM), a novel approach that combines meta-learning and physics-informed deep learning to train surrogate models with limited labeled data. PI-MLSM consists of two ...
Highlights- A proposed approach uses meta-learning and PIDL to train surrogates with small data.
- A model-agnostic meta-learning model is introduced to learn surrogate model weights.
- A PIDL approach is introduced to adapt to target tasks with ...
Comments
Information & Contributors
Information
Published In
May 2023
419 pages
ISBN:9798400700491
DOI:10.1145/3576914
Copyright © 2023 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 09 May 2023
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Funding Sources
- DARPA
Conference
CPS-IoT Week '23
Sponsor:
CPS-IoT Week '23: Cyber-Physical Systems and Internet of Things Week 2023
May 9 - 12, 2023
TX, San Antonio, USA
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 226Total Downloads
- Downloads (Last 12 months)153
- Downloads (Last 6 weeks)41
Reflects downloads up to 28 Feb 2025
Other Metrics
Citations
View Options
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML FormatLogin options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in