WearGP: A computationally efficient machine learning framework for local erosive wear predictions via nodal Gaussian processes
Abstract
Computational fluid dynamics (CFD)-based wear predictions are computationally expensive to evaluate, even with a high-performance computing infrastructure. Thus, it is difficult to provide accurate local wear predictions in a timely manner. Data-driven approaches provide a more computationally efficient way to approximate the CFD wear predictions without running the actual CFD wear models. In this paper, a machine learning (ML) approach, termed WearGP, is presented to approximate the 3D local wear predictions, using numerical wear predictions from steady-state CFD simulations as training and testing datasets. The proposed framework is built on Gaussian process (GP) and utilized to predict wear in a much shorter time. The WearGP framework can be segmented into three stages. At the first stage, the training dataset is built by using a number of CFD simulations in the order of O (102). At the second stage, the data cleansing and data mining process are performed, where the nodal wear solutions are extracted from the solution database to build a training dataset. At the third stage, the wear predictions are made, using trained GP processes. Two CFD case studies including 3D slurry pump impeller and casing are used to demonstrate the WearGP framework, in which 144 training and 40more »
- Authors:
-
- Georgia Inst. of Technology, Atlanta, GA (United States). Woodruff School of Mechanical Engineering; GIW Industries Inc., Grovetown, GA (United States)
- GIW Industries Inc., Grovetown, GA (United States)
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
- Georgia Inst. of Technology, Atlanta, GA (United States). Woodruff School of Mechanical Engineering
- Publication Date:
- Research Org.:
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
- Sponsoring Org.:
- USDOE National Nuclear Security Administration (NNSA)
- OSTI Identifier:
- 1492797
- Report Number(s):
- SAND2019-0449J
Journal ID: ISSN 0043-1648; 671579
- Grant/Contract Number:
- AC04-94AL85000
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Wear
- Additional Journal Information:
- Journal Volume: 422-423; Journal Issue: C; Journal ID: ISSN 0043-1648
- Publisher:
- Elsevier
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 42 ENGINEERING
Citation Formats
Tran, Anh, Furlan, John M., Pagalthivarthi, Krishnan V., Visintainer, Robert J., Wildey, Tim, and Wang, Yan. WearGP: A computationally efficient machine learning framework for local erosive wear predictions via nodal Gaussian processes. United States: N. p., 2018.
Web. doi:10.1016/j.wear.2018.12.081.
Tran, Anh, Furlan, John M., Pagalthivarthi, Krishnan V., Visintainer, Robert J., Wildey, Tim, & Wang, Yan. WearGP: A computationally efficient machine learning framework for local erosive wear predictions via nodal Gaussian processes. United States. https://doi.org/10.1016/j.wear.2018.12.081
Tran, Anh, Furlan, John M., Pagalthivarthi, Krishnan V., Visintainer, Robert J., Wildey, Tim, and Wang, Yan. Thu .
"WearGP: A computationally efficient machine learning framework for local erosive wear predictions via nodal Gaussian processes". United States. https://doi.org/10.1016/j.wear.2018.12.081. https://www.osti.gov/servlets/purl/1492797.
@article{osti_1492797,
title = {WearGP: A computationally efficient machine learning framework for local erosive wear predictions via nodal Gaussian processes},
author = {Tran, Anh and Furlan, John M. and Pagalthivarthi, Krishnan V. and Visintainer, Robert J. and Wildey, Tim and Wang, Yan},
abstractNote = {Computational fluid dynamics (CFD)-based wear predictions are computationally expensive to evaluate, even with a high-performance computing infrastructure. Thus, it is difficult to provide accurate local wear predictions in a timely manner. Data-driven approaches provide a more computationally efficient way to approximate the CFD wear predictions without running the actual CFD wear models. In this paper, a machine learning (ML) approach, termed WearGP, is presented to approximate the 3D local wear predictions, using numerical wear predictions from steady-state CFD simulations as training and testing datasets. The proposed framework is built on Gaussian process (GP) and utilized to predict wear in a much shorter time. The WearGP framework can be segmented into three stages. At the first stage, the training dataset is built by using a number of CFD simulations in the order of O (102). At the second stage, the data cleansing and data mining process are performed, where the nodal wear solutions are extracted from the solution database to build a training dataset. At the third stage, the wear predictions are made, using trained GP processes. Two CFD case studies including 3D slurry pump impeller and casing are used to demonstrate the WearGP framework, in which 144 training and 40 testing data points are used to train and test the proposed method, respectively. The numerical accuracy, computational effiency and effectiveness between the WearGP framework and CFD wear model for both slurry pump impellers and casings are compared. It is shown that the WearGP framework can achieve highly accurate results that are comparable with the CFD results, with a relatively small size training dataset, with a computational time reduction in an order of 105 to 106.},
doi = {10.1016/j.wear.2018.12.081},
journal = {Wear},
number = C,
volume = 422-423,
place = {United States},
year = {Thu Dec 27 00:00:00 EST 2018},
month = {Thu Dec 27 00:00:00 EST 2018}
}
Web of Science