Visual design intuition: Predicting dynamic properties of beams from raw cross-section images

TL;DR

This paper demonstrates that convolutional neural networks can predict static and dynamic properties of beams directly from raw cross-section images with high accuracy, offering a fast surrogate for traditional finite element analysis.

Contribution

The study introduces a CNN-based approach to estimate beam properties from images without prior geometric or physical knowledge, significantly accelerating structural analysis.

Findings

CNN models predict beam deflection with 4.54% MAPE

Eigenfrequencies are predicted with 1.43% MAPE

Prediction speed is over 1000 times faster than FEA

Abstract

In this work we aim to mimic the human ability to acquire the intuition to estimate the performance of a design from visual inspection and experience alone. We study the ability of convolutional neural networks to predict static and dynamic properties of cantilever beams directly from their raw cross-section images. Using pixels as the only input, the resulting models learn to predict beam properties such as volume maximum deflection and eigenfrequencies with 4.54% and 1.43% Mean Average Percentage Error (MAPE) respectively, compared to the Finite Element Analysis (FEA) approach. Training these models doesn't require prior knowledge of theory or relevant geometric properties, but rather relies solely on simulated or empirical data, thereby making predictions based on "experience" as opposed to theoretical knowledge. Since this approach is over 1000 times faster than FEA, it can be adopted to create surrogate models that could speed up the preliminary optimization studies where numerous consecutive evaluations of similar geometries are required. We suggest that this modeling approach would aid in addressing challenging optimization problems involving complex structures and physical phenomena for which theoretical models are unavailable.