BUILDING DIGITAL TWINS TO SIMULATE MANUFACTURING VARIATION

To improve the quality of a manufactured part in industry, a variety of techniques are used to scan a built geometry to bring it back to the physics based simulation world to assess its true performance. There are various laser and structured light measurement techniques (GOM), Computed Tomography ( CT) scan as well as touch-point probes in the form of CMM cloud of data that can provide an estimate for the shape of an object. However, there are many challenges on how to construct the digital geometry from the scan in order not to lose any deviations and defects and yet being able to mesh a solid manifold for simulation purposes. In this paper, a novel method based on multi-layered Artificial Intelligence (AI) is presented to produce a meaningful engineering design space to perturb the design-intent geometry to match the manufactured data cloud. The inverse mapping techniques has been applied to a range of real turbomachinery components to demonstrate its flexibility and robustness, even when the original GOM is not perfect. A case study is presented based on a real modern jet engine bypass outlet guide vane (BOGV) to show how constructing and using its digital twin and high-fidelity simulation can save a significant cost for a fleet of engines/aircraft.