BlendedNet++: A Large-Scale Blended Wing Body Aerodynamics Dataset and Benchmark

2025-12-02

AI Summary

Aerodynamic surrogate modeling is hindered by the lack of large-scale, high-resolution public datasets. Method: This work introduces the first field-level aerodynamic dataset for blended-wing-body (BWB) configurations—comprising 12,490 steady-state RANS simulation samples—covering both forward (geometry-to-flow) and inverse (target-flow-to-geometry) aerodynamic mapping tasks. We propose a standardized evaluation protocol enabling fair benchmarking across diverse models (GraphSAGE, GraphUNet, PointNet, Transolver, FiLMNet, GNOT) and pioneer the integration of conditional diffusion models into BWB inverse design, coupled with optimization in a hybrid paradigm. Contribution/Results: Our forward surrogate achieves high-fidelity pointwise prediction of aerodynamic force fields; the inverse design framework converges rapidly and reproducibly under target lift-to-drag ratio constraints, substantially improving design efficiency. This work advances reproducibility and unifies methodological paradigms in aerodynamic surrogate modeling.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Planning with Language Models
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Web data generation and simulation
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Despite progress in machine learning-based aerodynamic surrogates, the scarcity of large, field-resolved datasets limits progress on accurate pointwise prediction and reproducible inverse design for aircraft. We introduce BlendedNet++, a large-scale aerodynamic dataset and benchmark focused on blended wing body (BWB) aircraft. The dataset contains over 12,000 unique geometries, each simulated at a single flight condition, yielding 12,490 aerodynamic results for steady RANS CFD. For every case, we provide (i) integrated force/moment coefficients CL, CD, CM and (ii) dense surface fields of pressure and skin friction coefficients Cp and (Cfx, Cfy, Cfz). Using this dataset, we standardize a forward-surrogate benchmark to predict pointwise fields across six model families: GraphSAGE, GraphUNet, PointNet, a coordinate Transformer (Transolver-style), a FiLMNet (coordinate MLP with feature-wise modulation), and a Graph Neural Operator Transformer (GNOT). Finally, we present an inverse design task of achieving a specified lift-to-drag ratio under fixed flight conditions, implemented via a conditional diffusion model. To assess performance, we benchmark this approach against gradient-based optimization on the same surrogate and a diffusion-optimization hybrid that first samples with the conditional diffusion model and then further optimizes the designs. BlendedNet++ provides a unified forward and inverse protocol with multi-model baselines, enabling fair, reproducible comparison across architectures and optimization paradigms. We expect BlendedNet++ to catalyze reproducible research in field-level aerodynamics and inverse design; resources (dataset, splits, baselines, and scripts) will be released upon acceptance.

Problem

• Addresses scarcity of large aerodynamic datasets for accurate prediction
• Standardizes forward-surrogate benchmark for pointwise field prediction
• Presents inverse design task for specified lift-to-drag ratio

Innovation

• Large-scale dataset with 12,000 blended wing body aerodynamic simulations
• Standardized benchmark for forward prediction using six neural network models
• Inverse design via conditional diffusion model and hybrid optimization methods