Machine learning modeling based on informer for predicting complex unsteady flow fields to reduce consumption of computational fluid dynamics simulation

Accurately predicting the dynamic behaviour of complex flow fields has always been a major challenge in Computational Fluid Dynamics (CFD) research. This paper proposes an innovative approach based on the Informer model for efficient prediction of unsteady flow fields. This study focuses on the two-...

Full description

Saved in:
Bibliographic Details
Main Authors: Mingkun Fang, Fangfang Zhang, Di Zhu, Ruofu Xiao, Ran Tao
Format: Article
Language:English
Published: Taylor & Francis Group 2025-12-01
Series:Engineering Applications of Computational Fluid Mechanics
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/19942060.2024.2443118
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850250672054730752
author Mingkun Fang
Fangfang Zhang
Di Zhu
Ruofu Xiao
Ran Tao
author_facet Mingkun Fang
Fangfang Zhang
Di Zhu
Ruofu Xiao
Ran Tao
author_sort Mingkun Fang
collection DOAJ
description Accurately predicting the dynamic behaviour of complex flow fields has always been a major challenge in Computational Fluid Dynamics (CFD) research. This paper proposes an innovative approach based on the Informer model for efficient prediction of unsteady flow fields. This study focuses on the two-dimensional National Advisory Committee for Aeronautics (NACA) 0009 hydrofoil wake vortices and introduces the machine learning model Informer to predict unsteady wake vortices. In the prediction area, a grid of 10 ×10 monitoring points is established, and various error evaluation criteria are employed to assess the prediction results. Simultaneously, the predicted cloud maps at 24-time steps are compared with the CFD-calculated cloud maps to validate the feasibility of using machine learning models for predicting unsteady flow fields. The results indicate that the Informer model achieves favorable predictions for unsteady flow fields, with average Root Mean Square Error (RMSE) values along three paths being 0.0061, 0.017, and 0.0103, respectively. As the prediction length increases, the R-square (R2) increases from 0.9917 to 0.9984. The Informer model demonstrates commendable performance in predicting vorticity positions, sizes, and shapes, affirming its suitability for forecasting unsteady flow fields and consequently mitigating CFD computational resource consumption.
format Article
id doaj-art-2d1cdcea7d934404afe4e4c92254dabd
institution OA Journals
issn 1994-2060
1997-003X
language English
publishDate 2025-12-01
publisher Taylor & Francis Group
record_format Article
series Engineering Applications of Computational Fluid Mechanics
spelling doaj-art-2d1cdcea7d934404afe4e4c92254dabd2025-08-20T01:58:08ZengTaylor & Francis GroupEngineering Applications of Computational Fluid Mechanics1994-20601997-003X2025-12-0119110.1080/19942060.2024.2443118Machine learning modeling based on informer for predicting complex unsteady flow fields to reduce consumption of computational fluid dynamics simulationMingkun Fang0Fangfang Zhang1Di Zhu2Ruofu Xiao3Ran Tao4College of Water Resources and Civil Engineering, China Agricultural University, Beijing, People’s Republic of ChinaCollege of Water Resources and Civil Engineering, China Agricultural University, Beijing, People’s Republic of ChinaCollege of Engineering, China Agricultural University, Beijing, People’s Republic of ChinaCollege of Water Resources and Civil Engineering, China Agricultural University, Beijing, People’s Republic of ChinaCollege of Water Resources and Civil Engineering, China Agricultural University, Beijing, People’s Republic of ChinaAccurately predicting the dynamic behaviour of complex flow fields has always been a major challenge in Computational Fluid Dynamics (CFD) research. This paper proposes an innovative approach based on the Informer model for efficient prediction of unsteady flow fields. This study focuses on the two-dimensional National Advisory Committee for Aeronautics (NACA) 0009 hydrofoil wake vortices and introduces the machine learning model Informer to predict unsteady wake vortices. In the prediction area, a grid of 10 ×10 monitoring points is established, and various error evaluation criteria are employed to assess the prediction results. Simultaneously, the predicted cloud maps at 24-time steps are compared with the CFD-calculated cloud maps to validate the feasibility of using machine learning models for predicting unsteady flow fields. The results indicate that the Informer model achieves favorable predictions for unsteady flow fields, with average Root Mean Square Error (RMSE) values along three paths being 0.0061, 0.017, and 0.0103, respectively. As the prediction length increases, the R-square (R2) increases from 0.9917 to 0.9984. The Informer model demonstrates commendable performance in predicting vorticity positions, sizes, and shapes, affirming its suitability for forecasting unsteady flow fields and consequently mitigating CFD computational resource consumption.https://www.tandfonline.com/doi/10.1080/19942060.2024.2443118Machine learningsignal predictioncomputational fluid dynamicsinformer
spellingShingle Mingkun Fang
Fangfang Zhang
Di Zhu
Ruofu Xiao
Ran Tao
Machine learning modeling based on informer for predicting complex unsteady flow fields to reduce consumption of computational fluid dynamics simulation
Engineering Applications of Computational Fluid Mechanics
Machine learning
signal prediction
computational fluid dynamics
informer
title Machine learning modeling based on informer for predicting complex unsteady flow fields to reduce consumption of computational fluid dynamics simulation
title_full Machine learning modeling based on informer for predicting complex unsteady flow fields to reduce consumption of computational fluid dynamics simulation
title_fullStr Machine learning modeling based on informer for predicting complex unsteady flow fields to reduce consumption of computational fluid dynamics simulation
title_full_unstemmed Machine learning modeling based on informer for predicting complex unsteady flow fields to reduce consumption of computational fluid dynamics simulation
title_short Machine learning modeling based on informer for predicting complex unsteady flow fields to reduce consumption of computational fluid dynamics simulation
title_sort machine learning modeling based on informer for predicting complex unsteady flow fields to reduce consumption of computational fluid dynamics simulation
topic Machine learning
signal prediction
computational fluid dynamics
informer
url https://www.tandfonline.com/doi/10.1080/19942060.2024.2443118
work_keys_str_mv AT mingkunfang machinelearningmodelingbasedoninformerforpredictingcomplexunsteadyflowfieldstoreduceconsumptionofcomputationalfluiddynamicssimulation
AT fangfangzhang machinelearningmodelingbasedoninformerforpredictingcomplexunsteadyflowfieldstoreduceconsumptionofcomputationalfluiddynamicssimulation
AT dizhu machinelearningmodelingbasedoninformerforpredictingcomplexunsteadyflowfieldstoreduceconsumptionofcomputationalfluiddynamicssimulation
AT ruofuxiao machinelearningmodelingbasedoninformerforpredictingcomplexunsteadyflowfieldstoreduceconsumptionofcomputationalfluiddynamicssimulation
AT rantao machinelearningmodelingbasedoninformerforpredictingcomplexunsteadyflowfieldstoreduceconsumptionofcomputationalfluiddynamicssimulation