BladeSDF : Unconditional and Conditional Generative Modeling of Representative Blade Geometries Using Signed Distance Functions

2026-01-19

AI Summary

This work proposes an implicit generative framework based on DeepSDF to address the limitations of conventional turbine blade generation methods, which often lack performance awareness, manufacturability guarantees, and geometric continuity. By leveraging signed distance functions (SDFs), the approach achieves high-fidelity geometric reconstruction and constructs an interpretable, near-Gaussian latent space aligned with key aerodynamic and structural parameters, enabling both unconditional synthesis and performance-driven conditional generation. A compact neural network maps engineering performance metrics end-to-end to latent codes, facilitating efficient geometry generation through interpolation and Gaussian sampling. Experimental results demonstrate that the reconstructed surfaces exhibit distance errors within 1% of the blade’s maximum dimension, achieving high fidelity while maintaining strong generalization to unseen designs.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Generative AI has emerged as a transformative paradigm in engineering design, enabling automated synthesis and reconstruction of complex 3D geometries while preserving feasibility and performance relevance. This paper introduces a domain-specific implicit generative framework for turbine blade geometry using DeepSDF, addressing critical gaps in performance-aware modeling and manufacturable design generation. The proposed method leverages a continuous signed distance function (SDF) representation to reconstruct and generate smooth, watertight geometries with quantified accuracy. It establishes an interpretable, near-Gaussian latent space that aligns with blade-relevant parameters, such as taper and chord ratios, enabling controlled exploration and unconditional synthesis through interpolation and Gaussian sampling. In addition, a compact neural network maps engineering descriptors, such as maximum directional strains, to latent codes, facilitating the generation of performance-informed geometry. The framework achieves high reconstruction fidelity, with surface distance errors concentrated within $1\%$ of the maximum blade dimension, and demonstrates robust generalization to unseen designs. By integrating constraints, objectives, and performance metrics, this approach advances beyond traditional 2D-guided or unconstrained 3D pipelines, offering a practical and interpretable solution for data-driven turbine blade modeling and concept generation.

Problem

• generative modeling
• turbine blade geometry
• performance-aware design
• manufacturable design
• 3D geometry generation

Innovation

• Signed Distance Function
• Generative Modeling
• Latent Space Interpretability
• Performance-Informed Design
• Turbine Blade Geometry