Physics-informed neural network for modelling force and torque fluctuations in a random array of bidisperse spheres

TL;DR

This paper introduces a physics-informed neural network (PINN) model that accurately predicts force and torque fluctuations on spheres in bidisperse particle arrays, leveraging pairwise interactions and a unified functional approach.

Contribution

The paper develops a compact PINN architecture that models force and torque contributions from neighbors using a single neural network, reducing complexity and enhancing interpretability.

Findings

Achieves an R^2 of approximately 0.9 in predictions.

Demonstrates universal applicability within tested parameter ranges.

Shows good interpolation to unseen datasets.

Abstract

We present a physics-informed neural network (PINN) model to predict the hydrodynamic force and torque fluctuations in a random array of stationary bidisperse spheres. The PINN model is formulated based on two hypotheses: (i) pairwise interaction assumption that approximates the total force/torque exerted on a target sphere by linear superposition of individual contributions from a finite number of influential neighbors; (i) unified function representation that suggests a single functional form to describe the contribution from different neighbors based on the observation of probability distribution maps obtained with various binary interaction modes in bidisperse particle-laden flows. We accordingly establish a compact PINN architecture to evaluate individual force/torque contribution of influential neighbors through the same neural network block which tremendously reduces the number of unknown parameters, and ultimately compute the total force/torque exerted on target sphere by their weighted sum. We compare the model predictions to PR-DNS data of eight different cases in a range of Reynolds number $1\leq Re\leq100$, solid volume fraction $10\%\leq\phi\leq40\%$, sphere diameter ratio $1.5\leq d_l^*/d_s^*\leq2.5$ and volume ratio $1\leq V_l^*/V_s^*\leq 4$, which demonstrates excellent performance with an optimal $R^2\approx0.9$ for both force and torque predictions. We establish a universal model that is applicable within the aforementioned input space, and examine its interpolation capability to the unseen data with multiple additional datasets. Finally, we extract the interpretable information of our PINN model in binary and trinary interactions, and discuss its potential extensions to other particle-laden flow problems with more complicated scenarios and Eulerian-Lagrangian simulations as a superior alternative to the classic average drag laws.