Robust training approach of neural networks for fluid flow state estimations

TL;DR

This paper explores robust neural network training methods for fluid flow state estimation, demonstrating improved accuracy and resilience across various flow types and sensor limitations.

Contribution

It introduces effective training strategies for CNNs to enhance robustness in fluid flow estimation under sensor scarcity and nonlinear complexities.

Findings

CNNs successfully estimate velocity fields from limited sensors.

Robust training approaches improve model resilience to sensor loss.

Applicability across laminar and turbulent flows is demonstrated.

Abstract

State estimation from limited sensor measurements is ubiquitously found as a common challenge in a broad range of fields including mechanics, astronomy, and geophysics. Fluid mechanics is no exception -- state estimation of fluid flows is particularly important for flow control and processing of experimental data. However, strong nonlinearities and spatio-temporal high degrees of freedom of fluid flows cause difficulties in reasonable estimations. To handle these issues, neural networks (NNs) have recently been applied to the fluid flow estimation instead of conventional linear methods. The present study focuses on the capability of NNs to various fluid flow estimation problems from a practical viewpoint regarding robust training. Three types of unsteady laminar and turbulent flows are considered for the present demonstration: 1. square cylinder wake, 2. turbulent channel flow, and 3. laminar to turbulent transitional boundary layer. We utilize a convolutional neural network (CNN) to estimate velocity fields from sectional sensor measurements. To assess the practicability of the CNN models, physical quantities required for the input and robustness against lack of sensors are investigated. We also examine the effectiveness of several considerable approaches for model training to gain more robustness against the lack of sensors. The knowledge acquired through the present study in terms of effective training approaches can be transferred towards practical machine learning in fluid flow modeling.