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

TL;DR

This paper presents BladeSDF, a novel implicit generative model for turbine blade geometries that enables controllable, performance-aware, and high-fidelity 3D shape synthesis using signed distance functions.

Contribution

It introduces a domain-specific generative framework leveraging DeepSDF for turbine blades, with an interpretable latent space and performance-informed geometry generation.

Findings

High reconstruction accuracy with surface errors within 1% of blade size

Robust generalization to unseen blade designs

Controlled synthesis through latent space interpolation and sampling

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.