RePaint-Enhanced Conditional Diffusion Model for Parametric Engineering Designs under Performance and Parameter Constraints

2026-01-30

AI Summary

This work addresses the challenge of efficiently generating complete and novel engineering designs from partial reference sketches while satisfying both performance and parametric constraints. We propose, for the first time, adapting the RePaint framework to engineering design generation by introducing a controllable completion method that requires no retraining. Our approach leverages a pre-trained denoising diffusion probabilistic model (DDPM) guided by a mask-resampling mechanism, enabling the integration of dual constraints—performance targets and geometric parameters—during inference. This allows simultaneous preservation of user-specified local regions and exploration of globally innovative solutions. Evaluated on hull and airfoil design tasks, the method consistently produces high-fidelity designs that meet prescribed constraints while achieving novelty comparable to or exceeding that of the original unconditional model, thereby overcoming key limitations of conventional conditional diffusion models in engineering synthesis.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Prompt Engineering / Prompting
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

This paper presents a RePaint-enhanced framework that integrates a pre-trained performance-guided denoising diffusion probabilistic model (DDPM) for performance- and parameter-constraint engineering design generation. The proposed method enables the generation of missing design components based on a partial reference design while satisfying performance constraints, without retraining the underlying model. By applying mask-based resampling during inference process, RePaint allows efficient and controllable repainting of partial designs under both performance and parameter constraints, which is not supported by conventional DDPM-base methods. The framework is evaluated on two representative design problems, parametric ship hull design and airfoil design, demonstrating its ability to generate novel designs with expected performance based on a partial reference design. Results show that the method achieves accuracy comparable to or better than pre-trained models while enabling controlled novelty through fixing partial designs. Overall, the proposed approach provides an efficient, training-free solution for parameter-constraint-aware generative design in engineering applications.

Problem

• conditional diffusion model
• performance constraints
• parameter constraints
• generative design
• engineering design

Innovation

• RePaint
• conditional diffusion model
• performance constraints
• parameter-constrained design
• mask-based resampling