FluidZero: Mastering Diverse Tasks in Fluid Systems through a Single Generative Model

Fluid mechanics is a cornerstone of science and engineering, such as spacecraft, submersibles, and biomedicine, which are important to understand and optimize, involving four key tasks throughout history: prediction, parameter identification, design, and control. Although each task has made significant strides individually, current approaches remain fragmented; existing models are limited to their specific domains and lack the capability to generalize across different tasks. To overcome this issue while utilizing the correlation between tasks to improve the performance on each task, we propose FluidZero , a unified deep generative model to tackle all these tasks using one single model. FluidZero is encouraged by the success of large foundation models in several domains, inspiring it possible to develop a unified fluid model capable of handling all these tasks. The key advantage of FluidZero is that it facilitates cross-modal and cross-task interactions on diverse data, enabling effective physical principle learning and significantly enhancing performance on all tasks across a wide range of fluid scenarios. We evaluate FluidZero across multiple datasets, including simulation data and real-world measured data obtained through Particle Image Velocimetry (PIV). Moreover, the designed foil is directly transferred to real-world experiments through 3D printing. Notably, FluidZero shows remarkable generalization capabilities in all scenarios, achieving superior performance even in out-of-distribution (OOD) situations and real-world applications. By integrating diverse fluid system tasks across varied scenarios into a unified model, FluidZero demonstrates the revolutionary impact of generative Artificial Intelligence (AI) approaches in fluid mechanics, opening new avenues for the adoption of integrated fluid system understanding and optimization throughout scientific and engineering domains.