Two-phase flow involves the simultaneous dynamics of two distinct phases, with numerous important implications in the industrial field. However, accurately modeling these flows, whether through experiments or numerical simulations, requires substantial computational resources to capture the complex interfacial dynamics. In this study, we tested three different neural operators—the Fourier neural operator (FNO), physics-aware recurrent convolutions (PARC), and the deep operator network (DeepONet), with the aim of accelerating the simulation of dynamics in two-phase flows. We employed two benchmark problems of single bubble rising (140 cases) to bubble condensation (50 cases) for predicting the volume fraction, pressure, velocity fields, and more. Our framework considers only initial and boundary conditions to predict the entire temporal evolution, where physical parameters such as fluid density, fluid dynamic viscosity, and surface tension coefficient are set to the initial conditions. As a result, in the single bubble rising case, FNO achieved the best accuracy, yielding a root mean square error (RMSE) of 0.0154 in predicting the volume fraction field. On the other hand, for the bubble condensation case, DeepONet exhibited the lowest RMSE value of 0.0123. Additionally, we examined the computational efficiency and distinctive characteristics of each technique, as well as its applicability to modeling two-phase flows. Overall, this study offered practical insights into utilizing neural operators for solving fundamental benchmark problems, further demonstrating the potential of neural operators as efficient surrogate models for a wide range of physical phenomena at significantly reduced computational costs.

Modeling unsteady, fast transient, and advection-dominated physics problems is a pressing challenge for physics-aware deep learning (PADL). The physics of complex systems is governed by large systems of partial differential equations (PDEs) and ancillary constitutive models with nonlinear structures, as well as evolving state fields exhibiting sharp gradients and rapidly deforming material interfaces. Here, we investigate an inductive bias approach that is versatile and generalizable to model generic nonlinear field evolution problems. Our study focuses on the recent physics-aware recurrent convolutions (PARC), which incorporates a differentiator-integrator architecture that inductively models the spatiotemporal dynamics of generic physical systems. We extend the capabilities of PARC to simulate unsteady, transient, and advection-dominant systems. The extended model, referred to as PARCv2, is equipped with differential operators to model advection-reaction-diffusion equations, as well as a hybrid integral solver for stable, long-time predictions. PARCv2 is tested on both standard benchmark problems in fluid dynamics, namely Burgers and Navier-Stokes equations, and then applied to more complex shock-induced reaction problems in energetic materials. We evaluate the behavior of PARCv2 in comparison to other physics-informed and learning bias models and demonstrate its potential to model unsteady and advection-dominant dynamics regimes.

We recently developed the quadratic integration- exploited model predictive current control (QIMPCC) and the binary capacitor voltage control-based modular multilevel converter (BCVC-MMC) with a new hybrid arm design to effectively enhance the DC-AC power-conversion quality-and- efficiency and the closed-loop control performance of MPCC- based multilevel converters in low nominal DC-voltage applications. Due to the technical limits of its predicted cost- function optimization method utilizing a finite three-phase switching combination set, QIMPCC cannot be directly applied to BCVC-MMC; moreover, there is room for improved closed-loop control performance. To address these drawbacks, this paper proposes the voltage-control reference estimation (VCRE)-based QIMPCC exploiting the QI method’s superior accuracy. The proposed algorithm substantially improves the closed-loop control performance of this class of converters. Finally, simulation results demonstrate and quantify the claimed technical advantages.

The main ideas of our scheme are that the storage nodes are selected according to the updating frequency of data for reducing the transmission and the delay, and the relay nodes can be acted as the owners of data instead of the real owner of data for protecting the user's privacy. Furthermore, by using the DIFF method, the user can effectively modify the stored data with the lower transmission cost and delay.