Graph Neural Network Assisted Genetic Algorithm for Structural Dynamic Response and Parameter Optimization
Sagnik Mukherjee
TL;DR
This paper tackles the high computational cost of optimizing dynamic structural parameters in Single Degree of Freedom systems by proposing a hybrid Graph Neural Network (GNN) surrogate and Genetic Algorithm (GA) optimizer. The GNN learns the mapping from the parameter triplet ($m$, $k$, $c$) to the maximum displacement, enabling rapid predictions, while the GA searches for globally optimal configurations using these surrogates, with data generated by the Newmark–Beta method. A graph representation encodes the SDoF as nodes (masses) and edges (stiffness/damping), and the approach yields $R^2=0.7144$, $MAE=0.00977$, and $MAPE=15.31\%$, significantly reducing computational cost relative to full simulations and producing parameters validated by direct NM runs. Overall, the work demonstrates the viability of combining ML surrogates with evolutionary optimization for automated, intelligent structural design in dynamic environments.
Abstract
The optimization of structural parameters, such as mass(m), stiffness(k), and damping coefficient(c), is critical for designing efficient, resilient, and stable structures. Conventional numerical approaches, including Finite Element Method (FEM) and Computational Fluid Dynamics (CFD) simulations, provide high-fidelity results but are computationally expensive for iterative optimization tasks, as each evaluation requires solving the governing equations for every parameter combination. This study proposes a hybrid data-driven framework that integrates a Graph Neural Network (GNN) surrogate model with a Genetic Algorithm (GA) optimizer to overcome these challenges. The GNN is trained to accurately learn the nonlinear mapping between structural parameters and dynamic displacement responses, enabling rapid predictions without repeatedly solving the system equations. A dataset of single-degree-of-freedom (SDOF) system responses is generated using the Newmark Beta method across diverse mass, stiffness, and damping configurations. The GA then searches for globally optimal parameter sets by minimizing predicted displacements and enhancing dynamic stability. Results demonstrate that the GNN and GA framework achieves strong convergence, robust generalization, and significantly reduced computational cost compared to conventional simulations. This approach highlights the effectiveness of combining machine learning surrogates with evolutionary optimization for automated and intelligent structural design.