EngiBench: A Framework for Data-Driven Engineering Design Research

2025-06-02

AI Summary

In engineering design, physics-based simulations hinder data-driven method development due to installation complexity, high computational cost, and reliance on domain expertise. To address this, we introduce EngiBench—the first open-source benchmarking framework spanning aerospace, heat transfer, photonics, and other domains. It provides a unified API, standardized test suites, and an automated data generation pipeline. EngiBench adopts a modular benchmark architecture integrating surrogate modeling, generative modeling, physics-simulation coupling, feasibility validation, and visualization. Complementing the framework is EngiOpt, an algorithm library enabling plug-and-play integration of optimization and machine learning methods, along with end-to-end experimental automation. Empirical evaluation demonstrates that EngiBench substantially lowers entry barriers for engineering AI research, improves reproducibility, enables fair cross-algorithm comparison, and reveals fundamental challenges in modeling engineering design manifolds with general-purpose models.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Computer Vision: Low Level & Physics-based Vision
• Humans and AI: Game Design — Virtual Humans, NPCs and Autonomous Characters

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

Engineering design optimization seeks to automatically determine the shapes, topologies, or parameters of components that maximize performance under given conditions. This process often depends on physics-based simulations, which are difficult to install, computationally expensive, and require domain-specific expertise. To mitigate these challenges, we introduce EngiBench, the first open-source library and datasets spanning diverse domains for data-driven engineering design. EngiBench provides a unified API and a curated set of benchmarks -- covering aeronautics, heat conduction, photonics, and more -- that enable fair, reproducible comparisons of optimization and machine learning algorithms, such as generative or surrogate models. We also release EngiOpt, a companion library offering a collection of such algorithms compatible with the EngiBench interface. Both libraries are modular, letting users plug in novel algorithms or problems, automate end-to-end experiment workflows, and leverage built-in utilities for visualization, dataset generation, feasibility checks, and performance analysis. We demonstrate their versatility through experiments comparing state-of-the-art techniques across multiple engineering design problems, an undertaking that was previously prohibitively time-consuming to perform. Finally, we show that these problems pose significant challenges for standard machine learning methods due to highly sensitive and constrained design manifolds.

Problem

• Addressing computational cost and expertise in physics-based simulations
• Providing unified benchmarks for engineering design optimization
• Challenging standard ML methods with sensitive design constraints

Innovation

• Open-source library for data-driven engineering design
• Unified API with diverse domain benchmarks
• Modular libraries for algorithm and problem integration