Rapid and sparse reconstruction of high-speed steady-state and transient compressible flow fields using physics-informed graph neural networks
Authors:
- Jiang-Zhou PengJPJiang-Zhou Peng
- Zhi-Qiao WangZWZhi-Qiao Wang
- Xiaoli RongXRXiaoli Rong
- Mei MeiMMMei Mei
- Mingyang WangMWMingyang Wang
- Yong HeYHYong He
- Wei-Tao WuWWWei-Tao Wu
- 1 April 2024
- journal article
- research article
- Published by AIP Publishing in Physics of Fluids
- Vol. 36 (4)
Abstract
Explosion flow fields are characterized by shock waves with varying intensity and position (i.e., explosive loads), which are the primary causes of structural damage. Accurate and rapid prediction of explosive loads is crucial for structural blast-resistant design and daily security management. While existing empirical models and numerical simulation methods can capture the propagation characteristics of explosive shock waves, high-precision simulation requires a massive computational workload, which is insufficient to meet the fast computational demands of various explosive scenarios. To address this contradiction, this study constructed a sparse reconstruction model for two-dimensional explosion fields based on machine learning algorithms. The model utilizes sparse observational data to establish a mapping relationship to the distribution of the entire flow field. The model is built by a physics-informed graph neural network (PIGN). The graph neural network is employed to associate node features, while the physical network is utilized to control model convergence, aiming to enhance model performance. Using the constructed dataset, the PIGN model was tested. Performance and generalization capabilities of the model were assessed by comparing its results with numerical simulation. This evaluation analyzed the relative error distribution and error statistical results of the reconstructed flow field. The results indicate that the PIGN model can effectively reconstruct explosion fields, with an average error in the reconstructed flow field below 4%. Furthermore, when the number of probe points reaches 10, the average error of the flow field reconstructed by the model is close to 6%. This model not only provides a highly reliable distribution of explosion overpressure and pressure-time variations but also, with a well-trained model, accomplishes flow field reconstruction within 1 ms. It offers a novel approach for achieving rapid and reasonable prediction of explosion fields or two-dimensional compressible flow fields.Keywords
This publication has 37 references indexed in Scilit:
- Numerical Simulations of Blast Wave Propagation After a High-Energy ExplosionInternational Journal of Aeronautical and Space Sciences, 2023
- A comparative study on the most effective machine learning model for blast loading prediction: From GBDT to TransformerEngineering Structures, 2022
- Machine intelligence in dynamical systems: \A state‐of‐art reviewWIREs Data Mining and Knowledge Discovery, 2022
- Cause analysis and damage mechanism of explosive destruction with case investigation involving LPG tank trailerEngineering Failure Analysis, 2022
- Dynamic behavior of functional graded cementitious composite under the coupling of high speed penetration and explosionComposite Structures, 2021
- Machine learning for biochemical engineering: A reviewBiochemical Engineering Journal, 2021
- Non-intrusive reduced order modeling for flowfield reconstruction based on residual neural networkActa Astronautica, 2021
- Numerical modeling for compressible two-phase flows and application to near-field underwater explosionsComputers & Fluids, 2021
- Modeling of the whole process of shock wave overpressure of free-field air explosionDefence Technology, 2019
- Environmentally sustainable mining through proper selection of explosives in blasting operationEnvironmental Earth Sciences, 2017