Track trials, findings, and clinical evidence as it lands.
Search papers, labs, and topics across Lattice.
To overcome severe optical distortion and arc glare in wire-arc directed energy deposition, this work reconstructs 2D molten pool surface flow fields directly from high-speed video by coupling dense optical flow with physics-informed neural networks (PINNs). Resolving these dynamics is critical for predicting defect formation and solidification microstructures, bridging the gap between unanchored fluid simulations and noisy, sparse visual tracking. By regularizing vision observations with incompressible Navier-Stokes constraints, no-penetration boundaries, and cyclic phase conditioning, the system reliably recovers continuous, physically consistent flow fields across both quasi-steady convection and periodic droplet-impact regimes.
Optical flow in extreme visual environments becomes reliable when anchored by fluid mechanics, turning glare-distorted video of molten metal into fully resolved, Navier-Stokes-compliant velocity fields.
Molten pool flow significantly influences bead geometry, defect formation, and solidification microstructure in wire-arc directed energy deposition (DED). However, direct flow sensing remains an open challenge due to extreme temperatures, intense arc illumination, and complex flow patterns. Traditional research has relied either on computationally intensive fluid dynamics simulations, which require assumed boundary conditions and lack empirical anchoring, or on vision-based tracer particle tracking, which yields sparse, noisy, and physically unconstrained velocity estimates. This work bridges these two paradigms by reconstructing physics-constrained 2D surface flow fields from high-speed imaging of a GTAW-based wire-arc DED process under distinct flow regimes: quasi-steady convection and periodic droplet impact. The pipeline begins with homography correction to calibrate the oblique camera view, followed by dense optical flow extraction to provide raw velocity observations. For quasi-steady pools, a physics-informed neural network (PINN) reconstructs the surface velocity field by jointly enforcing data fidelity, incompressible Navier-Stokes momentum equations, no-penetration boundary conditions, and an arc-forcing prior through composite loss minimization. For pools subject to periodic droplet impact, a phase-conditioned time-dependent PINN is further developed to resolve the cyclic flow evolution throughout the impact period. This work provides a unified framework that bridges high-speed visual sensing and fluid mechanics, enabling physics-grounded flow diagnostics for wire-arc DED processes.