DynNet: Physics-based neural architecture design for linear and nonlinear structural response modeling and prediction

Abstract

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.

arXiv commentSubmitted to Elsevier

References in corpus (7)

• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Prioritized Experience Replay
• Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
• Recent Advances in Recurrent Neural Networks
• Physics-Informed Multi-LSTM Networks for Metamodeling of Nonlinear Structures
• Online Batch Selection for Faster Training of Neural Networks
• Second-Order Optimization for Non-Convex Machine Learning: An Empirical Study

Cited by in corpus (2)

• Deep recurrent-convolutional neural network learning and physics Kalman filtering comparison in dynamic load identification
• On the Application of Data-Driven Deep Neural Networks in Linear and Nonlinear Structural Dynamics