Physics‐informed neural network applied to surface‐tension‐driven liquid film flows. (19th April 2022)

• Record Type: Journal Article
• Authors: Nakamura, Yo; Shiratori, Suguru; Takagi, Ryota; Sutoh, Michihiro; Sugihara, Iori; Nagano, Hideaki; Shimano, Kenjiro
• Is Part Of: International journal for numerical methods in fluids. Volume 94:Number 9(2022)
• Page Start: 1359
• Page End: 1378
• Publication Date: 2022-04-19
• Subjects: Laplace pressure -- long‐wave approximation -- lubrication equation -- machine learning -- thickness variation; Fluid dynamics -- Mathematics -- Periodicals; 532
• DOI: 10.1002/fld.5093
• Languages: English
• ISSNs: 0271-2091

Abstract

Abstract: A physics‐informed neural network (PINN), which has been recently proposed by Raissi et al. [ J Comput Phys . 2019;378:686–707], is applied to the partial differential equation (PDE) of liquid film flows. The PDE considered is the time evolution of the thickness distribution h ( x, t ) $$ h\left(x, t\right) $$ owing to the Laplace pressure, which involves fourth‐order spatial derivative and fourth‐order nonlinear term. Even for such a PDE, it is confirmed that the PINN can predict the solutions with sufficient accuracy. Nevertheless, some improvements are needed in training convergence and accuracy of the solutions. The precision of floating‐point numbers is a critical issue for the present PDE. When the calculation is executed with a single precision floating‐point number, the optimization is terminated due to the loss of significant digits. Calculation of the automatic differentiation dominates the computational time required for training and becomes exponentially longer with increasing order of derivatives. By splitting the original fourth‐order single PDE into lower‐order coupled PDEs, the computational time for each training iteration is greatly reduced. The sampling density of training data also significantly affects training convergence. For the problem considered in this study, improved convergence was obtained by allowing the sampling density of training data to be greater in earlier time ranges, where the rapid flattening of the thickness occurs. Abstract : 1. A physics‐informed neural network is applied for the first time to a partial differential equation (PDE) involving fourth‐order derivative and fourth‐order nonlinearity. 2. Improved training convergence can be achieved by allowing the sampling density of training data to be greater in earlier time ranges. 3. By splitting the fourth‐order single PDE into lower order coupled PDEs, computational time for a single training iteration can be greatly reduced.