Cargando…
FLUID-GPT (Fast Learning to Understand and Investigate Dynamics with a Generative Pre-Trained Transformer): Efficient Predictions of Particle Trajectories and Erosion
[Image: see text] The deleterious impact of erosion due to high-velocity particle impingement adversely affects a variety of engineering and industrial systems, resulting in irreversible mechanical wear of materials/components. Brute force computational fluid dynamics (CFD) calculations are commonly...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
American Chemical Society
2023
|
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10548597/ https://www.ncbi.nlm.nih.gov/pubmed/37799452 http://dx.doi.org/10.1021/acs.iecr.3c01639 |
_version_ | 1785115302659358720 |
---|---|
author | Yang, Steve D. Ali, Zulfikhar A. Wong, Bryan M. |
author_facet | Yang, Steve D. Ali, Zulfikhar A. Wong, Bryan M. |
author_sort | Yang, Steve D. |
collection | PubMed |
description | [Image: see text] The deleterious impact of erosion due to high-velocity particle impingement adversely affects a variety of engineering and industrial systems, resulting in irreversible mechanical wear of materials/components. Brute force computational fluid dynamics (CFD) calculations are commonly used to predict surface erosion by directly solving the Navier–Stokes equations for fluid and particle dynamics; however, these numerical approaches often require significant computational resources. In contrast, recent data-driven approaches using machine learning (ML) have shown immense promise for more efficient and accurate predictions to sidestep computationally demanding CFD calculations. To this end, we have developed FLUID-GPT (Fast Learning to Understand and Investigate Dynamics with a Generative Pre-Trained Transformer), a new hybrid ML architecture for accurately predicting particle trajectories and erosion on an industrial-scale steam header geometry. Our FLUID-GPT approach utilizes a Generative Pre-Trained Transformer 2 (GPT-2) with a convolutional neural network (CNN) for the first time to predict surface erosion using only information from five initial conditions: particle size, main-inlet speed, main-inlet pressure, subinlet speed, and subinlet pressure. Compared to the bidirectional long- and short-term memory (BiLSTM) ML techniques used in previous work, our FLUID-GPT model is much more accurate (a 54% decrease in the mean squared error) and efficient (70% less training time). Our work demonstrates that FLUID-GPT is an accurate and efficient ML approach for predicting time-series trajectories and their subsequent spatial erosion patterns in these complex dynamic systems. |
format | Online Article Text |
id | pubmed-10548597 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | American Chemical Society |
record_format | MEDLINE/PubMed |
spelling | pubmed-105485972023-10-05 FLUID-GPT (Fast Learning to Understand and Investigate Dynamics with a Generative Pre-Trained Transformer): Efficient Predictions of Particle Trajectories and Erosion Yang, Steve D. Ali, Zulfikhar A. Wong, Bryan M. Ind Eng Chem Res [Image: see text] The deleterious impact of erosion due to high-velocity particle impingement adversely affects a variety of engineering and industrial systems, resulting in irreversible mechanical wear of materials/components. Brute force computational fluid dynamics (CFD) calculations are commonly used to predict surface erosion by directly solving the Navier–Stokes equations for fluid and particle dynamics; however, these numerical approaches often require significant computational resources. In contrast, recent data-driven approaches using machine learning (ML) have shown immense promise for more efficient and accurate predictions to sidestep computationally demanding CFD calculations. To this end, we have developed FLUID-GPT (Fast Learning to Understand and Investigate Dynamics with a Generative Pre-Trained Transformer), a new hybrid ML architecture for accurately predicting particle trajectories and erosion on an industrial-scale steam header geometry. Our FLUID-GPT approach utilizes a Generative Pre-Trained Transformer 2 (GPT-2) with a convolutional neural network (CNN) for the first time to predict surface erosion using only information from five initial conditions: particle size, main-inlet speed, main-inlet pressure, subinlet speed, and subinlet pressure. Compared to the bidirectional long- and short-term memory (BiLSTM) ML techniques used in previous work, our FLUID-GPT model is much more accurate (a 54% decrease in the mean squared error) and efficient (70% less training time). Our work demonstrates that FLUID-GPT is an accurate and efficient ML approach for predicting time-series trajectories and their subsequent spatial erosion patterns in these complex dynamic systems. American Chemical Society 2023-09-08 /pmc/articles/PMC10548597/ /pubmed/37799452 http://dx.doi.org/10.1021/acs.iecr.3c01639 Text en © 2023 The Authors. Published by American Chemical Society https://creativecommons.org/licenses/by-nc-nd/4.0/Permits non-commercial access and re-use, provided that author attribution and integrity are maintained; but does not permit creation of adaptations or other derivative works (https://creativecommons.org/licenses/by-nc-nd/4.0/). |
spellingShingle | Yang, Steve D. Ali, Zulfikhar A. Wong, Bryan M. FLUID-GPT (Fast Learning to Understand and Investigate Dynamics with a Generative Pre-Trained Transformer): Efficient Predictions of Particle Trajectories and Erosion |
title | FLUID-GPT (Fast
Learning to Understand and Investigate
Dynamics with a Generative Pre-Trained Transformer): Efficient Predictions
of Particle Trajectories and Erosion |
title_full | FLUID-GPT (Fast
Learning to Understand and Investigate
Dynamics with a Generative Pre-Trained Transformer): Efficient Predictions
of Particle Trajectories and Erosion |
title_fullStr | FLUID-GPT (Fast
Learning to Understand and Investigate
Dynamics with a Generative Pre-Trained Transformer): Efficient Predictions
of Particle Trajectories and Erosion |
title_full_unstemmed | FLUID-GPT (Fast
Learning to Understand and Investigate
Dynamics with a Generative Pre-Trained Transformer): Efficient Predictions
of Particle Trajectories and Erosion |
title_short | FLUID-GPT (Fast
Learning to Understand and Investigate
Dynamics with a Generative Pre-Trained Transformer): Efficient Predictions
of Particle Trajectories and Erosion |
title_sort | fluid-gpt (fast
learning to understand and investigate
dynamics with a generative pre-trained transformer): efficient predictions
of particle trajectories and erosion |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10548597/ https://www.ncbi.nlm.nih.gov/pubmed/37799452 http://dx.doi.org/10.1021/acs.iecr.3c01639 |
work_keys_str_mv | AT yangsteved fluidgptfastlearningtounderstandandinvestigatedynamicswithagenerativepretrainedtransformerefficientpredictionsofparticletrajectoriesanderosion AT alizulfikhara fluidgptfastlearningtounderstandandinvestigatedynamicswithagenerativepretrainedtransformerefficientpredictionsofparticletrajectoriesanderosion AT wongbryanm fluidgptfastlearningtounderstandandinvestigatedynamicswithagenerativepretrainedtransformerefficientpredictionsofparticletrajectoriesanderosion |