用于模拟双分散球体随机阵列中力和扭矩波动的物理信息神经网络
Physics-informed neural network for modelling force and torque fluctuations in a random array of bidisperse spheres
AI总结:
本研究提出一种基于成对相互作用和统一函数表示假设的PINN模型,用于预测双分散球体阵列的流体动力与扭矩波动,在多工况下表现优异且具备良好插值能力,可拓展至复杂颗粒流模拟。
摘要:
我们提出了一种物理信息神经网络(PINN,即Physics-informed neural network)模型,用于预测静止双分散球体随机阵列中的流体动力力和扭矩波动。该PINN模型基于两大假设构建:(i)成对相互作用假设,即通过有限数量有影响的邻近球体各自贡献的线性叠加,来近似计算作用在目标球体上的总力/扭矩;(ii)统一函数表示,即基于对双分散颗粒流中各种二元相互作用模式所得概率分布图的观察,提出可用单一函数形式描述不同邻近球体的贡献。我们据此构建了紧凑的PINN架构,通过同一个神经网络模块评估有影响邻近球体的单个力/扭矩贡献,大幅减少了未知参数数量,最终通过加权求和计算作用在目标球体上的总力/扭矩。我们将模型预测结果与8种不同工况的PR-DNS(即颗粒分辨直接数值模拟)数据进行了对比,工况范围为雷诺数$1\leq Re\leq100$、固体体积分数$10\\%\leq\phi\leq40\\%$、球体直径比$1.5\leq d_l^*/d_s^*\leq2.5$、体积比$1\leq V_l^*/V_s^*\leq4$,结果表明模型性能优异,力和扭矩预测的最优$R^2$均约为0.9。我们建立了一个适用于上述输入空间的通用模型,并通过多个额外数据集检验了其对未见过数据的插值能力。最后,我们提取了该PINN模型在二元和三元相互作用中的可解释信息,并讨论了其作为经典平均阻力定律的优良替代方案,向其他更复杂场景的颗粒流问题以及欧拉-拉格朗日模拟拓展的潜力。
英文摘要:
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 $10\%\leqϕ\leq40\%$, 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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。