Minimizing Structural Vibrations via Guided Flow Matching Design Optimization

2025-06-18

AI Summary

Vibration-induced noise in engineering structures (e.g., automobiles, aircraft) severely compromises ride comfort. To address the challenge of vibration suppression in plate-like structures, this paper proposes a generative optimization method based on Guided Flow Matching. Our approach uniquely couples a generative flow matching model with a physics-informed vibration surrogate model, enabling end-to-end differentiable optimization. It employs implicit design space modeling—eliminating manual parameter tuning—and supports customizable target optimization for specific eigenfrequencies. The generated dimple layouts exhibit high diversity, manufacturability, and superior vibration attenuation performance. Experimental results demonstrate that our method significantly outperforms random search, heuristic design, and genetic algorithms in suppressing vibration response within critical frequency bands.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Optimization
• Computer Vision: Learning & Optimization for CV

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

Structural vibrations are a source of unwanted noise in engineering systems like cars, trains or airplanes. Minimizing these vibrations is crucial for improving passenger comfort. This work presents a novel design optimization approach based on guided flow matching for reducing vibrations by placing beadings (indentations) in plate-like structures. Our method integrates a generative flow matching model and a surrogate model trained to predict structural vibrations. During the generation process, the flow matching model pushes towards manufacturability while the surrogate model pushes to low-vibration solutions. The flow matching model and its training data implicitly define the design space, enabling a broader exploration of potential solutions as no optimization of manually-defined design parameters is required. We apply our method to a range of differentiable optimization objectives, including direct optimization of specific eigenfrequencies through careful construction of the objective function. Results demonstrate that our method generates diverse and manufacturable plate designs with reduced structural vibrations compared to designs from random search, a criterion-based design heuristic and genetic optimization. The code and data are available from https://github.com/ecker-lab/Optimizing_Vibrating_Plates.

Problem

• Minimizing structural vibrations in engineering systems
• Optimizing plate designs using guided flow matching
• Reducing noise in cars, trains, and airplanes

Innovation

• Guided flow matching for vibration reduction
• Generative model with manufacturability constraints
• Surrogate model predicts structural vibrations