Reduced-order modeling for stochastic large-scale and time-dependent flow problems using deep spatial and temporal convolutional autoencoders

Advanced Modeling and Simulation in Engineering Sciences

Research Article

Azzedine Abdedou¹  Azzeddine Soulaimani¹ 

[1] Department of Mechanical Engineering, Ecole de technologie superieure, 1100 Notre-Dame W., H3C 1K3, Montreal, QC, Canada;

关键词: Uncertainty propagation;    Reduced-order modeling;    Deep learning;    Convolutional autoencoders;   

DOI  :  10.1186/s40323-023-00244-0

 received in 2023-01-05, accepted in 2023-04-27,  发布年份 2023

来源: Springer

【 摘 要 】

A non-intrusive reduced-order model based on convolutional autoencoders is proposed as a data-driven tool to build an efficient nonlinear reduced-order model for stochastic spatiotemporal large-scale flow problems. The objective is to perform accurate and rapid uncertainty analyses of the flow outputs of interest for which the input parameters are deemed uncertain. The data are constituted from a set of high-fidelity snapshots, collected using an inhouse high-fidelity flow solver, which correspond to a sample of the uncertain input parameters. The method uses a 1D-convolutional autoencoder to reduce the spatial dimension of the unstructured meshes used by the flow solver. Another convolutional autoencoder is used for the time compression. The encoded latent vectors, generated from the two compression levels, are then mapped to the input parameters using a regression-based multilayer perceptron. The proposed model allows for rapid predictions for unseen parameter values, allowing the output statistical moments to be computed efficiently. The accuracy of the proposed approach is compared to that of the linear reduced-order technique based on an artificial neural network through two benchmark tests (the one-dimensional Burgers and Stoker’s solutions) and a hypothetical dam break flow problem, with an unstructured mesh and over a complex bathymetry river. The numerical results show that the proposed methods present strong predictive capabilities to accurately approximate the statistical moments of the outputs. In particular, the predicted statistical moments are oscillations-free, unlike those obtained with the traditional proper orthogonal decomposition method. The proposed reduction framework is simple to implement and can be applied to other parametric and time-dependent problems governed by partial differential equations, which are commonly encountered in many engineering and science problems.

【 授权许可】

CC BY   
© The Author(s) 2023

【 图 表 】

41116_2023_36_Article_IEq8.gif

41116_2023_36_Article_IEq1.gif

Fig. 6

Fig. 1

Fig. 2

40517_2023_256_Article_IEq163.gif

Fig. 4

Fig. 5

Fig. 1

Fig. 1

Fig. 29

40517_2023_256_Article_IEq152.gif

Fig. 4

Fig. 24

Fig. 2

12864_2023_9380_Article_IEq7.gif

Fig. 23

Fig. 1

Fig. 3

Fig. 1

Fig. 21

Fig. 2

Fig. 1

Fig. 1

Fig. 18

40517_2023_256_Article_IEq119.gif

Fig. 3

40517_2023_256_Article_IEq118.gif

40517_2023_256_Article_IEq115.gif

40517_2023_256_Article_IEq114.gif

Fig. 2

Fig. 1

40517_2023_256_Article_IEq108.gif

Fig. 5

40517_2023_256_Article_IEq107.gif

40517_2023_256_Article_IEq103.gif

40517_2023_256_Article_IEq102.gif

Fig. 3

Fig. 1

Fig. 2

41512_2023_147_Article_IEq89.gif

Fig. 12

Fig. 3

40517_2023_256_Article_IEq78.gif

Fig. 11

40517_2023_256_Article_IEq73.gif

Fig. 9

Fig. 8

Fig. 5

Fig. 1

Fig. 1

Fig. 5

40517_2023_256_Article_IEq64.gif

40517_2023_256_Article_IEq62.gif

Fig. 1

Fig. 3

13731_2023_296_Article_IEq2.gif

40517_2023_256_Article_IEq60.gif

Fig. 1

40517_2023_256_Article_IEq59.gif

Fig. 3

40517_2023_256_Article_IEq55.gif

Fig. 3

Fig. 3

Fig. 2

40517_2023_256_Article_IEq53.gif

Fig. 2

40517_2023_256_Article_IEq52.gif

40517_2023_256_Article_IEq51.gif

Fig. 2

12888_2023_4880_Article_IEq1.gif

Fig. 1

Fig. 1

40517_2023_256_Article_IEq47.gif

Fig. 3

Fig. 3

Fig. 2

Fig. 6

Fig. 2

Fig. 1

Fig. 5

Fig. 1

Fig. 3

Fig. 7

Fig. 2

Fig. 6

Fig. 4

Fig. 1

40517_2023_256_Article_IEq39.gif

Fig. 2

40517_2023_256_Article_IEq38.gif

40517_2023_256_Article_IEq36.gif

40517_2023_256_Article_IEq35.gif

40517_2023_256_Article_IEq34.gif

Fig. 1

Fig. 2

40517_2023_258_Article_IEq68.gif

40517_2023_258_Article_IEq138.gif

40517_2023_258_Article_IEq137.gif

Fig. 8

40517_2023_258_Article_IEq135.gif

Fig. 1

40517_2023_258_Article_IEq133.gif

40517_2023_258_Article_IEq132.gif

40517_2023_258_Article_IEq131.gif

40517_2023_258_Article_IEq129.gif

40517_2023_258_Article_IEq128.gif

40517_2023_258_Article_IEq127.gif

40517_2023_258_Article_IEq126.gif

40517_2023_258_Article_IEq125.gif

Fig. 2

Fig. 1

Fig. 1

40517_2023_258_Article_IEq115.gif

40517_2023_258_Article_IEq114.gif

40517_2023_258_Article_IEq113.gif

Fig. 1

40517_2023_256_Article_IEq14.gif

Fig. 8

Fig. 6

Fig. 7

40517_2023_256_Article_IEq11.gif

Fig. 5

40517_2023_256_Article_IEq5.gif

40517_2023_256_Article_IEq4.gif

41116_2023_36_Article_IEq117.gif

Fig. 2

41116_2023_36_Article_IEq116.gif

41116_2023_36_Article_IEq115.gif

41116_2023_36_Article_IEq818.gif

41116_2023_36_Article_IEq817.gif

41116_2023_36_Article_IEq816.gif

41116_2023_36_Article_IEq815.gif

41116_2023_36_Article_IEq813.gif

41116_2023_36_Article_IEq809.gif

40517_2023_258_Article_IEq102.gif

41116_2023_36_Article_IEq806.gif

41116_2023_36_Article_IEq805.gif

41116_2023_36_Article_IEq803.gif

41116_2023_36_Article_IEq801.gif

41116_2023_36_Article_IEq799.gif

41116_2023_36_Article_IEq797.gif

41116_2023_36_Article_IEq795.gif

Fig. 1

41116_2023_36_Article_IEq793.gif

41116_2023_36_Article_IEq791.gif

41116_2023_36_Article_IEq789.gif

41116_2023_36_Article_IEq786.gif

41116_2023_36_Article_IEq785.gif

41116_2023_36_Article_IEq783.gif

41116_2023_36_Article_IEq781.gif

41116_2023_36_Article_IEq778.gif

41116_2023_36_Article_IEq777.gif

41116_2023_36_Article_IEq774.gif

Fig. 2

Fig. 2

41116_2023_36_Article_IEq768.gif

41116_2023_36_Article_IEq767.gif

41116_2023_36_Article_IEq765.gif

41116_2023_36_Article_IEq763.gif

41116_2023_36_Article_IEq761.gif

41116_2023_36_Article_IEq759.gif

41116_2023_36_Article_IEq757.gif

41116_2023_36_Article_IEq754.gif

41116_2023_36_Article_IEq753.gif

41116_2023_36_Article_IEq749.gif

41116_2023_36_Article_IEq748.gif

41116_2023_36_Article_IEq747.gif

Fig. 1

41116_2023_36_Article_IEq734.gif

41116_2023_36_Article_IEq733.gif

41116_2023_36_Article_IEq731.gif

40517_2023_258_Article_IEq58.gif

Fig. 3

Fig. 1

41116_2023_36_Article_IEq726.gif

41116_2023_36_Article_IEq724.gif

Fig. 6

41116_2023_36_Article_IEq722.gif

40517_2023_258_Article_IEq51.gif

41116_2023_36_Article_IEq718.gif

41116_2023_36_Article_IEq716.gif

Fig. 2

41116_2023_36_Article_IEq710.gif

41116_2023_36_Article_IEq708.gif

41116_2023_36_Article_IEq706.gif

41116_2023_36_Article_IEq675.gif

41116_2023_36_Article_IEq674.gif

41116_2023_36_Article_IEq672.gif

41116_2023_36_Article_IEq670.gif

41116_2023_36_Article_IEq667.gif

41116_2023_36_Article_IEq664.gif

41116_2023_36_Article_IEq663.gif

41116_2023_36_Article_IEq658.gif

41116_2023_36_Article_IEq657.gif

41116_2023_36_Article_IEq656.gif

41116_2023_36_Article_IEq655.gif

41116_2023_36_Article_IEq653.gif

41116_2023_36_Article_IEq649.gif

41116_2023_36_Article_IEq644.gif

41116_2023_36_Article_IEq639.gif

41116_2023_36_Article_IEq631.gif

Fig. 1

40798_2023_579_Article_IEq3.gif

41116_2023_36_Article_IEq503.gif

41116_2023_36_Article_IEq501.gif

Fig. 1

40517_2023_258_Article_IEq8.gif

Fig. 1

41116_2023_36_Article_IEq499.gif

41116_2023_36_Article_IEq497.gif

41116_2023_36_Article_IEq482.gif