Physics-informed PointNet: A deep learning solver for steady-state incompressible flows and thermal fields on multiple sets of irregular geometries

Ali Kashefi, Tapan Mukerji

Abstract: Highlights•PIPN is a novel physics-informed deep learning framework.•PIPN solves forward and inverse time-independent problems on several irregular domains by training only once.•PIPN overcomes the shortcoming of regular PINNs that need to be retrained for any single domain with a new geometry.•Applications of PIPN are shown for incompressible flows and thermal fields.