De-Risking Robotic Welding for In-Space Metal Joining Through Physics-Grounded Digital Twins
Abstract
Growing interest in in-space servicing, manufacturing, and assembly has renewed attention on reliable metal joining for modular construction and on-orbit repair. Robotic welding is promising, but reduced-gravity and low-pressure operation remains poorly characterised and flight-like tests are limited. The UK Space Agency-supported ISPARK project is developing a physics-grounded digital twin for structured process de-risking. This paper evaluates a model-based prototype combining a finite-volume thermal weld-pool model, Gaussian-process (GP) and neural-network surrogates, and a simulated six-axis manipulator. The reduced model includes solid-liquid phase change, effective thermocapillary transport, and a local-pressure parameter. Gravity is assessed separately through a hydrostatic-to-capillary pressure ratio and does not enter the thermal energy equation. Across repeated five-fold cross-validation, the GP has lower normalised mean absolute error than the neural network for all eight outputs. In 10 held-out boundary cases, 74 of 80 solver responses fall within nominal 90% GP predictive intervals. A three-output GP query takes 249 microseconds, including scaling and predictive variance. In a simulated UR5 L-shaped-seam study, a proportional controller adjusts the synergic power-source setting as travel speed falls near the corner. Finite-volume re-evaluation finds all 12 closed-loop operating points and 9 of 12 open-loop points within an illustrative 1.0-3.0 mm root-side-width band. These simulation results support using the framework to screen welding conditions and control strategies before experimental tests. Thermal-vacuum, targeted reduced-gravity, and robotic hardware-in-the-loop studies are needed to assess the model and controller.
Related
- The Physics De-Risking Register: Gate-by-Gate Evidence, Independently Re-Run and Stamped, Across a Compact Spherical-Tokamak Breeder and Its D–³He Tandem-Mirror Burners
- Reliable LLM-Generated Programs for High-Energy Physics Experiments through Graph-Grounded Software Knowledge
- Robust OCT-based weld-depth estimation in laser welding using spatial-temporal context and axial evidence
- High-performance silicon-metal laser welding resisting extreme conditions
- A Geometrically Parameterized Quasi-Stationary 3D Model for High-Frequency Induction Tube Welding
BibTeX
@misc{hao2026derisking,
title = {{De-Risking Robotic Welding for In-Space Metal Joining Through Physics-Grounded Digital Twins}},
author = {Zhou Daniel Hao and Umer Masood Chaudry and Robert Shaw and Andrew Cheney and Nick Ludford and Mark Sims and Hongbiao Dong},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.21939},
eprint = {2610.21939},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.21939},
}
RIS
TY - UNPB
TI - De-Risking Robotic Welding for In-Space Metal Joining Through Physics-Grounded Digital Twins
AU - Zhou Daniel Hao
AU - Umer Masood Chaudry
AU - Robert Shaw
AU - Andrew Cheney
AU - Nick Ludford
AU - Mark Sims
AU - Hongbiao Dong
PY - 2026
DA - 2026/10/15
PB - arXiv
DO - 10.48550/arxiv.2610.21939
UR - https://arxiv.org/abs/2610.21939
AB - Growing interest in in-space servicing, manufacturing, and assembly has renewed attention on reliable metal joining for modular construction and on-orbit repair. Robotic welding is promising, but reduced-gravity and low-pressure operation remains poorly characterised and flight-like tests are limited. The UK Space Agency-supported ISPARK project is developing a physics-grounded digital twin for structured process de-risking. This paper evaluates a model-based prototype combining a finite-volume thermal weld-pool model, Gaussian-process (GP) and neural-network surrogates, and a simulated six-axis manipulator. The reduced model includes solid-liquid phase change, effective thermocapillary transport, and a local-pressure parameter. Gravity is assessed separately through a hydrostatic-to-capillary pressure ratio and does not enter the thermal energy equation. Across repeated five-fold cross-validation, the GP has lower normalised mean absolute error than the neural network for all eight outputs. In 10 held-out boundary cases, 74 of 80 solver responses fall within nominal 90% GP predictive intervals. A three-output GP query takes 249 microseconds, including scaling and predictive variance. In a simulated UR5 L-shaped-seam study, a proportional controller adjusts the synergic power-source setting as travel speed falls near the corner. Finite-volume re-evaluation finds all 12 closed-loop operating points and 9 of 12 open-loop points within an illustrative 1.0-3.0 mm root-side-width band. These simulation results support using the framework to screen welding conditions and control strategies before experimental tests. Thermal-vacuum, targeted reduced-gravity, and robotic hardware-in-the-loop studies are needed to assess the model and controller.
ER -