DynNet: Physics-based neural architecture design for linear and nonlinear structural response modeling and prediction
This addresses the need for efficient data-driven models in structural engineering for applications like system identification and damage diagnosis, representing a novel method for a known bottleneck.
The study tackled the problem of predicting dynamic responses in linear and nonlinear structural systems by designing a physics-based recurrent neural network that learns from ground motion data, achieving higher accuracy with fewer trainable variables compared to advanced counterparts for long trajectories.
Data-driven models for predicting dynamic responses of linear and nonlinear systems are of great importance due to their wide application from probabilistic analysis to inverse problems such as system identification and damage diagnosis. In this study, a physics-based recurrent neural network model is designed that is able to learn the dynamics of linear and nonlinear multiple degrees of freedom systems given a ground motion. The model is able to estimate a complete set of responses, including displacement, velocity, acceleration, and internal forces. Compared to the most advanced counterparts, this model requires a smaller number of trainable variables while the accuracy of predictions is higher for long trajectories. In addition, the architecture of the recurrent block is inspired by differential equation solver algorithms and it is expected that this approach yields more generalized solutions. In the training phase, we propose multiple novel techniques to dramatically accelerate the learning process using smaller datasets, such as hardsampling, utilization of trajectory loss function, and implementation of a trust-region approach. Numerical case studies are conducted to examine the strength of the network to learn different nonlinear behaviors. It is shown that the network is able to capture different nonlinear behaviors of dynamic systems with very high accuracy and with no need for prior information or very large datasets.