Deep Learning-Based Rapid Flow Field Reconstruction Model with Limited Monitoring Point Information DOI Creative Commons
Ping Wang,

Guangzhong Hu,

Wenli Hu

et al.

Aerospace, Journal Year: 2024, Volume and Issue: 11(11), P. 871 - 871

Published: Oct. 24, 2024

The rapid reconstruction of the internal flow field within pressure vessel equipment based on features from limited detection points was significant value for online monitoring and construction a digital twin. This paper proposed surrogate model that combined Proper Orthogonal Decomposition (POD) with deep learning to capture dynamic mapping relationship between sensor point information global state during operation, enabling temperature velocity field. Using POD, order tested reduced by 99.75%, 99.13%, effectively decreasing dimensionality Our analysis revealed first modal coefficient snapshot data, after decomposition, had higher energy proportion compared along more pronounced marginal effect. indicates modes need be retained achieve total proportion. By constructing CSSA-BP represent coefficients fields data collected points, comparison made BP method in reconstructing shell-and-tube heat exchanger. yielded maximum mean squared error (MSE) 9.84 reconstructed field, absolute (MAE) 1.85. For MSE 0.0135 MAE 0.0728. errors were 4.85%, 3.65%, 4.29%, respectively. 17.72%, 11.30%, 16.79%, indicating established this study has high accuracy. Conventional CFD simulation methods require several hours, whereas here can rapidly reconstruct 1 min training is completed, significantly reducing time. work provides new quickly obtaining under offering reference development twins equipment.

Language: Английский

An enhanced temperature field inversion model by POD-BPNN-GA method for a 3D wing with limited sensors DOI
Jiaxin Hu, Jian‐Jun Gou, Chunlin Gong

et al.

International Communications in Heat and Mass Transfer, Journal Year: 2025, Volume and Issue: 164, P. 108778 - 108778

Published: March 5, 2025

Language: Английский

Citations

0

Internal flow characteristics of a tank with multiple jet inflows and liquid sloshing DOI

Junwen Liang,

Xinuo Tu,

Z.T. Liang

et al.

Physics of Fluids, Journal Year: 2025, Volume and Issue: 37(4)

Published: April 1, 2025

This paper conducted numerical investigations into the flow field characteristics of a multi-inlet tank, focusing on coupled effects jet inflows and liquid sloshing. Turbulent swirling was numerically investigated using Reynolds Stress Model, combined with Volume Fluid method Adaptive Mesh Refinement technique for accurate free surface capturing. The vorticity structure identified Q-criterion. Numerical simulations were validated against experimental data, confirming reliability accuracy model. A systematic parametric study to investigate inlet pipe diameter, inflow rate, tank immersed depth. Four points fitting curves established describe relationships between maximum velocity these parameters. results indicated that distribution uniformity mostly affected by diameter. Additionally, various filling levels analyzed sloshing induced surge motion. probability index significantly at an depth 0.8 m. hybrid neural network framework integrating Proper Orthogonal Decomposition (POD) Long Short-Term Memory (LSTM) networks developed predict field. POD employed extract dominant modes, while corresponding temporal coefficients fed LSTM prediction. reconstructed fields demonstrated effectiveness POD-LSTM model in accurately predicting evolution field, as confirmed comparisons simulated results.

Language: Английский

Citations

0

Deep Learning-Based Rapid Flow Field Reconstruction Model with Limited Monitoring Point Information DOI Creative Commons
Ping Wang,

Guangzhong Hu,

Wenli Hu

et al.

Aerospace, Journal Year: 2024, Volume and Issue: 11(11), P. 871 - 871

Published: Oct. 24, 2024

The rapid reconstruction of the internal flow field within pressure vessel equipment based on features from limited detection points was significant value for online monitoring and construction a digital twin. This paper proposed surrogate model that combined Proper Orthogonal Decomposition (POD) with deep learning to capture dynamic mapping relationship between sensor point information global state during operation, enabling temperature velocity field. Using POD, order tested reduced by 99.75%, 99.13%, effectively decreasing dimensionality Our analysis revealed first modal coefficient snapshot data, after decomposition, had higher energy proportion compared along more pronounced marginal effect. indicates modes need be retained achieve total proportion. By constructing CSSA-BP represent coefficients fields data collected points, comparison made BP method in reconstructing shell-and-tube heat exchanger. yielded maximum mean squared error (MSE) 9.84 reconstructed field, absolute (MAE) 1.85. For MSE 0.0135 MAE 0.0728. errors were 4.85%, 3.65%, 4.29%, respectively. 17.72%, 11.30%, 16.79%, indicating established this study has high accuracy. Conventional CFD simulation methods require several hours, whereas here can rapidly reconstruct 1 min training is completed, significantly reducing time. work provides new quickly obtaining under offering reference development twins equipment.

Language: Английский

Citations

2