In material jetting or Inkjet Printing (IJP), predicting droplet evolution is crucial for maintaining print quality. However, long-horizon forecasts remain challenging due to error accumulation and the complex coupling of process variables. This work introduces the Diffusion-corrected Auto-Regressive Fourier Neural Operator (DiffARFNO), a two-stage framework that combines an autoregressive Fourier-MIONet with a conditional Denoising Diffusion Implicit Model (DDIM) corrector.
The Fourier-MIONet is trained as a coarse predictor and deployed autoregressively for long-horizon forecasting. In the second stage, a DDIM-based conditional corrector refines the coarse prediction within each sliding window through efficient iterative denoising. By combining coarse predictions from the Fourier-MIONet with a DDIM corrector that restores fine details, DiffARFNO aims to provide high-fidelity predictions for long-horizon forecasts.
Extensive experiments on droplet datasets from ANSYS Fluent demonstrate that DiffARFNO significantly outperforms existing state-of-the-art models.
Blogger's Review: The DiffARFNO framework presented in this paper showcases innovation in droplet evolution prediction, effectively combining the strengths of autoregressive and diffusion models to tackle the issue of error accumulation in long-term forecasts. This work significantly advances research in the relevant fields.