Neuro-DynaStress: Predicting Dynamic Stress Distributions in Structural Components

TL;DR

Neuro-DynaStress is a deep learning framework designed to predict dynamic stress distributions in structural components during extreme events, enabling real-time analysis and decision-making.

Contribution

It introduces a novel deep learning model that accurately predicts stress sequences from finite element simulation data, reducing computational costs.

Findings

Achieves high accuracy in stress prediction compared to FEM simulations

Operates in real-time suitable for disaster response

Reduces computational complexity of stress analysis

Abstract

Structural components are typically exposed to dynamic loading, such as earthquakes, wind, and explosions. Structural engineers should be able to conduct real-time analysis in the aftermath or during extreme disaster events requiring immediate corrections to avoid fatal failures. As a result, it is crucial to predict dynamic stress distributions during highly disruptive events in real-time. Currently available high-fidelity methods, such as Finite Element Models (FEMs), suffer from their inherent high complexity and are computationally prohibitive. Therefore, to reduce computational cost while preserving accuracy, a deep learning model, Neuro-DynaStress, is proposed to predict the entire sequence of stress distribution based on finite element simulations using a partial differential equation (PDE) solver. The model was designed and trained to use the geometry, boundary conditions and sequence of loads as input and predict the sequences of high-resolution stress contours. The performance of the proposed framework is compared to finite element simulations using a PDE solver.