Structural System Identification via Validation and Adaptation

TL;DR

This paper introduces a neural network-based method for structural system identification that estimates parameters directly from data, validates models using independent datasets, and improves understanding of complex system dynamics.

Contribution

It presents a novel neural network framework inspired by generative models for direct parameter estimation, validation, and uncertainty quantification in structural systems.

Findings

Accurate parameter estimation demonstrated on nonlinear structural systems.

Effective validation using independent datasets and discriminator networks.

Applicable to both analytical and real experimental data.

Abstract

Estimating the governing equation parameter values is essential for integrating experimental data with scientific theory to understand, validate, and predict the dynamics of complex systems. In this work, we propose a new method for structural system identification (SI), uncertainty quantification, and validation directly from data. Inspired by generative modeling frameworks, a neural network maps random noise to physically meaningful parameters. These parameters are then used in the known equation of motion to obtain fake accelerations, which are compared to real training data via a mean square error loss. To simultaneously validate the learned parameters, we use independent validation datasets. The generated accelerations from these datasets are evaluated by a discriminator network, which determines whether the output is real or fake, and guides the parameter-generator network. Analytical and real experiments show the parameter estimation accuracy and model validation for different nonlinear structural systems.